Rohrhofer Franz Martin, Posch Stefan, Gößnitzer Clemens, Geiger Bernhard
2023
Physics-informed neural networks (PINNs) have emerged as a promising deep learning method, capable of solving forward and inverse problems governed by differential equations. Despite their recent advance, it is widely acknowledged that PINNs are difficult to train and often require a careful tuning of loss weights when data and physics loss functions are combined by scalarization of a multi-objective (MO) problem. In this paper, we aim to understand how parameters of the physical system, such as characteristic length and time scales, the computational domain, and coefficients of differential equations affect MO optimization and the optimal choice of loss weights. Through a theoretical examination of where these system parameters appear in PINN training, we find that they effectively and individually scale the loss residuals, causing imbalances in MO optimization with certain choices of system parameters. The immediate effects of this are reflected in the apparent Pareto front, which we define as the set of loss values achievable with gradient-based training and visualize accordingly. We empirically verify that loss weights can be used successfully to compensate for the scaling of system parameters, and enable the selection of an optimal solution on the apparent Pareto front that aligns well with the physically valid solution. We further demonstrate that by altering the system parameterization, the apparent Pareto front can shift and exhibit locally convex parts, resulting in a wider range of loss weights for which gradient-based training becomes successful. This work explains the effects of system parameters on MO optimization in PINNs, and highlights the utility of proposed loss weighting schemes.
Ross-Hellauer Anthony, Klebel Thomas, Knoth Petr, Pontika Nancy
2023
There are currently broad moves to reform research assessment, especially to better incentivize open and responsible research and avoid problematic use of inappropriate quantitative indicators. This study adds to the evidence base for such decision-making by investigating researcher perceptions of current processes of research assessment in institutional review, promotion, and tenure processes. Analysis of an international survey of 198 respondents reveals a disjunct between personal beliefs and perceived institutional priorities (‘value dissonance’), with practices of open and responsible research, as well as ‘research citizenship’ comparatively poorly valued by institutions at present. Our findings hence support current moves to reform research assessment. But we also add crucial nuance to the debate by discussing the relative weighting of open and responsible practices and suggesting that fostering research citizenship activities like collegiality and mentorship may be an important way to rebalance criteria towards environments, which better foster quality, openness, and responsibility
Razouk Houssam, Liu Xinglan, Kern Roman
2023
The Failure Mode Effect Analysis process (FMEA) is widely used in industry for risk assessment, as it effectively captures and documents domain-specific knowledge. This process is mainly concerned with causal domain knowledge. In practical applications, FMEAs encounter challenges in terms of comprehensibility, particularly related to inadequate coverage of listed failure modes and their corresponding effects and causes. This can be attributed to the limitations of traditional brainstorming approaches typically employed in the FMEA process. Depending on the size and diversity in terms of disciplines of the team conducting the analysis, these approaches may not adequately capture a comprehensive range of failure modes, leading to gaps in coverage. To this end, methods for improving FMEA knowledge comprehensibility are highly needed. A potential approach to address this gap is rooted in recent advances in common-sense knowledge graph completion, which have demonstrated the effectiveness of text-aware graph embedding techniques. However, the applicability of such methods in an industrial setting is limited. This paper addresses this issue on FMEA documents in an industrial environment. Here, the application of common-sense knowledge graph completion methods on FMEA documents from semiconductor manufacturing is studied. These methods achieve over 20% MRR on the test set and 70% of the top 10 predictions were manually assessed to be plausible by domain experts. Based on the evaluation, this paper confirms that text-aware knowledge graph embedding for common-sense knowledge graph completion are more effective than structure-only knowledge graph embedding for improving FMEA knowledge comprehensibility. Additionally we found that language model in domain fine-tuning is beneficial for extracting more meaningful embedding, thus improving the overall model performance.
Malinverno Luca, Barros Vesna, Ghisoni Francesco, Visonà Giovanni, Kern Roman, Nickel Philip , Ventura Barbara Elvira, Simic Ilija, Stryeck Sarah, Manni Francesca , Ferri Cesar , Jean-Quartier Clair, Genga Laura , Schweikert Gabriele, Lovric Mario, Rosen-Zvi Michal
2023
Understanding the inner working of machine-learning models has become a crucial point of discussion in fairness and reliability of artificial intelligence (AI). In this perspective, we reveal insights from recently published scientific works on explainable AI (XAI) within the biomedical sciences. Specifically, we speculate that the COVID-19 pandemic is associated with the rate of publications in the field. Current research efforts seem to be directed more toward explaining black-box machine-learning models than designing novel interpretable architecture. Notably, an inflection period in the publication rate was observed in October 2020, when the quantity of XAI research in biomedical sciences surged upward significantly.While a universally accepted definition of explainability is unlikely, ongoing research efforts are pushing the biomedical field toward improving the robustness and reliability of applied machine learning, which we consider a positive trend.
Grill-Kiefer Gerhard, Schröcker Stefan, Krasser Hannes, Körner Stefan
2023
Die optimale und nachhaltige Gestaltung komplexer Prozesse in Produktionsunternehmen setzt ein strukturiertes Vorgehen in der Problemlösung voraus. Durch das breite Aufgabenspektrum und die miteinander in Konkurrenz stehenden Zielsetzungen gilt diese Rahmenbedingung insbesondere für das Supply Chain Management in der Automobilindustrie. Mit einem in mehrere Schritte gegliederten Prozess gelingen die Entwicklung und Anwendung eines Rechenmodells zur Optimierung der Gesamtkosten im Teileversorgungsprozess. Dieses stellt unter Einbindung der beteiligten Fachbereiche die ganzheitliche Optimierung der Versorgungsgesamtkosten und die Durchführung effizienter Planungsschleifen im operativen Betrieb sicher. Der Datenqualität kommt hierbei eine besondere Bedeutung zu.
Siddiqi Shafaq, Qureshi Faiza, Lindstaedt Stefanie , Kern Roman
2023
Outlier detection in non-independent and identically distributed (non-IID) data refers to identifying unusual or unexpected observations in datasets that do not follow an independent and identically distributed (IID) assumption. This presents a challenge in real-world datasets where correlations, dependencies, and complex structures are common. In recent literature, several methods have been proposed to address this issue and each method has its own strengths and limitations, and the selection depends on the data characteristics and application requirements. However, there is a lack of a comprehensive categorization of these methods in the literature. This study addresses this gap by systematically reviewing methods for outlier detection in non-IID data published from 2015 to 2023. This study focuses on three major aspects; data characteristics, methods, and evaluation measures. In data characteristics, we discuss the differentiating properties of non-IID data. Then we review the recent methods proposed for outlier detection in non-IID data, covering their theoretical foundations and algorithmic approaches. Finally, we discuss the evaluation metrics proposed to measure the performance of these methods. Additionally, we present a taxonomy for organizing these methods and highlight the application domain of outlier detection in non-IID categorical data, outlier detection in federated learning, and outlier detection in attribute graphs. We provide a comprehensive overview of datasets used in the selected literature. Moreover, we discuss open challenges in outlier detection for non-IID to shed light on future research directions. By synthesizing the existing literature, this study contributes to advancing the understanding and development of outlier detection techniques in non-IID data settings.
Müllner Peter , Lex Elisabeth, Schedl Markus, Kowald Dominik
2023
State-of-the-art recommender systems produce high-quality recommendations to support users in finding relevant content. However, through the utilization of users' data for generating recommendations, recommender systems threaten users' privacy. To alleviate this threat, often, differential privacy is used to protect users' data via adding random noise. This, however, leads to a substantial drop in recommendation quality. Therefore, several approaches aim to improve this trade-off between accuracy and user privacy. In this work, we first overview threats to user privacy in recommender systems, followed by a brief introduction to the differential privacy framework that can protect users' privacy. Subsequently, we review recommendation approaches that apply differential privacy, and we highlight research that improves the trade-off between recommendation quality and user privacy. Finally, we discuss open issues, e.g., considering the relation between privacy and fairness, and the users' different needs for privacy. With this review, we hope to provide other researchers an overview of the ways in which differential privacy has been applied to state-of-the-art collaborative filtering recommender systems.
Duricic Tomislav, Kowald Dominik, Emanuel Lacic, Lex Elisabeth
2023
By providing personalized suggestions to users, recommender systems have become essential to numerous online platforms. Collaborative filtering, particularly graph-based approaches using Graph Neural Networks (GNNs), have demonstrated great results in terms of recommendation accuracy. However, accuracy may not always be the most important criterion for evaluating recommender systems' performance, since beyond accuracy aspects such as recommendation diversity, serendipity, and fairness can strongly influence user engagement and satisfaction. This review paper focuses on addressing these dimensions in GNN-based recommender systems, going beyond the conventional accuracy-centric perspective. We begin by reviewing recent developments in approaches that improve not only the accuracy-diversity trade-off, but also promote serendipity and fairness in GNN-based recommender systems. We discuss different stages of model development including data preprocessing, graph construction, embedding initialization, propagation layers, embedding fusion, score computation, and training methodologies. Furthermore, we present a look into the practical difficulties encountered in assuring diversity, serendipity, and fairness, while retaining high accuracy. Finally, we discuss potential future research directions for developing more robust GNN-based recommender systems that go beyond the unidimensional perspective of focusing solely on accuracy. This review aims to provide researchers and practitioners with an in-depth understanding of the multifaceted issues that arise when designing GNN-based recommender systems.
Müllner Peter , Lex Elisabeth, Schedl Markus, Kowald Dominik
2023
User-based KNN recommender systems (UserKNN) utilize the rating data of a target user’s k nearest neighbors in the recommendation process. This, however, increases the privacy risk of the neighbors since their rating data might be exposed to other users or malicious parties. To reduce this risk, existing work applies differential privacy by adding randomness to the neighbors’ ratings, which reduces the accuracy of UserKNN. In this work, we introduce ReuseKNN, a novel differentially-private KNN-based recommender system. The main idea is to identify small but highly reusable neighborhoods so that (i) only a minimal set of users requires protection with differential privacy, and (ii) most users do not need to be protected with differential privacy, since they are only rarely exploited as neighbors. In our experiments on five diverse datasets, we make two key observations: Firstly, ReuseKNN requires significantly smaller neighborhoods, and thus, fewer neighbors need to be protected with differential privacy compared to traditional UserKNN. Secondly, despite the small neighborhoods, ReuseKNN outperforms UserKNN and a fully differentially private approach in terms of accuracy. Overall, ReuseKNN leads to significantly less privacy risk for users than in the case of UserKNN.
Rohrhofer Franz Martin, Posch Stefan, Gößnitzer Clemens, Geiger Bernhard
2023
This paper empirically studies commonly observed training difficulties of Physics-Informed Neural Networks (PINNs) on dynamical systems.Our results indicate that fixed points which are inherent to these systems play a key role in the optimization of the in PINNs embedded physics loss function.We observe that the loss landscape exhibits local optima that are shaped by the presence of fixed points.We find that these local optima contribute to the complexity of the physics loss optimization which can explain common training difficulties and resulting nonphysical predictions.Under certain settings, e.g., initial conditions close to fixed points or long simulations times, we show that those optima can even become better than that of the desired solution.
Hoffer Johannes G., Ranftl Sascha, Geiger Bernhard
2023
We consider the problem of finding an input to a stochastic black box function such that the scalar output of the black box function is as close as possible to a target value in the sense of the expected squared error. While the optimization of stochastic black boxes is classic in (robust) Bayesian optimization, the current approaches based on Gaussian processes predominantly focus either on (i) maximization/minimization rather than target value optimization or (ii) on the expectation, but not the variance of the output, ignoring output variations due to stochasticity in uncontrollable environmental variables. In this work, we fill this gap and derive acquisition functions for common criteria such as the expected improvement, the probability of improvement, and the lower confidence bound, assuming that aleatoric effects are Gaussian with known variance. Our experiments illustrate that this setting is compatible with certain extensions of Gaussian processes, and show that the thus derived acquisition functions can outperform classical Bayesian optimization even if the latter assumptions are violated. An industrial use case in billet forging is presented.
Iacono Lucas, Pacios David, Vázquez-Poletti José Luis
2023
A sustainable agricultural system focuses on technologies and methodologies applied to supply a variety of sufficient, nutritious, and safe foods at an affordable price to feed the world population. To meet this goal, farmers and agronomists need crop health metrics to monitor the farms and to early-detect problems such as diseases or droughts. Then, they can apply the necessary measures to correct crops' problems and maximize yields. Large datasets of multispectral images and cloud computing is a must to obtain such metrics. Cameras placed in Drones and Satellites collect large multispectral image datasets. The Cloud allows for storing the image datasets and execution services that extract crops' health metrics such as the Normalized Difference Vegetation Index (NDVI). NDVI cloud computation generates new research challenges, such as which cloud service would allow paying the minimum cost to compute a certain amount of images. This article presents erverless NDVI (SNDVI) a novel serverless computing-based framework for NDVI computation. The main goal of our framework is to minimize the economic costs related to the use of a Public Cloud while computing NDVI from large datasets. We deployed our application using Amazon Lambda and Amazon S3, and then we performed a validation experiment. The experiment consisted of the execution of the framework to extract NDVI from a dataset of multispectral images collected with the Landsat 8 satellite. Then, we evaluate the overall framework performance in terms of; execution time and economic costs. Finally, the experiment results allowed us to determine that the framework fulfils its objective and that Serverless computing Services are a potentially convenient option for NDVI computation from large image datasets.
Jantscher Michael, Gunzer Felix, Kern Roman, Hassler Eva, Tschauner Sebastian, Reishofer Gernot
2023
Recent advances in deep learning and natural language processing (NLP) have opened many new opportunities for automatic text understanding and text processing in the medical field. This is of great benefit as many clinical downstream tasks rely on information from unstructured clinical documents. However, for low-resource languages like German, the use of modern text processing applications that require a large amount of training data proves to be difficult, as only few data sets are available mainly due to legal restrictions. In this study, we present an information extraction framework that was initially pre-trained on real-world computed tomographic (CT) reports of head examinations, followed by domain adaptive fine-tuning on reports from different imaging examinations. We show that in the pre-training phase, the semantic and contextual meaning of one clinical reporting domain can be captured and effectively transferred to foreign clinical imaging examinations. Moreover, we introduce an active learning approach with an intrinsic strategic sampling method to generate highly informative training data with low human annotation cost. We see that the model performance can be significantly improved by an appropriate selection of the data to be annotated, without the need to train the model on a specific downstream task. With a general annotation scheme that can be used not only in the radiology field but also in a broader clinical setting, we contribute to a more consistent labeling and annotation process that also facilitates the verification and evaluation of language models in the German clinical setting
Gabler Philipp, Geiger Bernhard, Schuppler Barbara, Kern Roman
2023
Superficially, read and spontaneous speech—the two main kinds of training data for automatic speech recognition—appear as complementary, but are equal: pairs of texts and acoustic signals. Yet, spontaneous speech is typically harder for recognition. This is usually explained by different kinds of variation and noise, but there is a more fundamental deviation at play: for read speech, the audio signal is produced by recitation of the given text, whereas in spontaneous speech, the text is transcribed from a given signal. In this review, we embrace this difference by presenting a first introduction of causal reasoning into automatic speech recognition, and describing causality as a tool to study speaking styles and training data. After breaking down the data generation processes of read and spontaneous speech and analysing the domain from a causal perspective, we highlight how data generation by annotation must affect the interpretation of inference and performance. Our work discusses how various results from the causality literature regarding the impact of the direction of data generation mechanisms on learning and prediction apply to speech data. Finally, we argue how a causal perspective can support the understanding of models in speech processing regarding their behaviour, capabilities, and limitations.
Trügler Andreas, Scher Sebastian, Kopeinik Simone, Kowald Dominik
2023
The use of data-driven decision support by public agencies is becoming more widespread and already influences the allocation of public resources. This raises ethical concerns, as it has adversely affected minorities and historically discriminated groups. In this paper, we use an approach that combines statistics and data-driven approaches with dynamical modeling to assess long-term fairness effects of labor market interventions. Specifically, we develop and use a model to investigate the impact of decisions caused by a public employment authority that selectively supports job-seekers through targeted help. The selection of who receives what help is based on a data-driven intervention model that estimates an individual’s chances of finding a job in a timely manner and rests upon data that describes a population in which skills relevant to the labor market are unevenly distributed between two groups (e.g., males and females). The intervention model has incomplete access to the individual’s actual skills and can augment this with knowledge of the individual’s group affiliation, thus using a protected attribute to increase predictive accuracy. We assess this intervention model’s dynamics—especially fairness-related issues and trade-offs between different fairness goals- over time and compare it to an intervention model that does not use group affiliation as a predictive feature. We conclude that in order to quantify the trade-off correctly and to assess the long-term fairness effects of such a system in the real-world, careful modeling of the surrounding labor market is indispensable.
Edtmayer, Hermann, Brandl, Daniel, Mach, Thomas, Schlager Elke, Gursch Heimo, Lugmair, Maximilian, Hochenauer, Christoph
2023
Increasing demands on indoor comfort in buildings and urgently needed energy efficiency measures require optimised HVAC systems in buildings. To achieve this, more extensive and accurate input data are required. This is difficult or impossible to accomplish with physical sensors. Virtual sensors, in turn, can provide these data; however, current virtual sensors are either too slow or too inaccurate to do so. The aim of our research was to develop a novel digital-twin workflow providing fast and accurate virtual sensors to solve this problem. To achieve a short calculation time and accurate virtual measurement results, we coupled a fast building energy simulation and an accurate computational fluid dynamics simulation. We used measurement data from a test facility as boundary conditions for the models and managed the coupling workflow with a customised simulation and data management interface. The corresponding simulation results were extracted for the defined virtual sensors and validated with measurement data from the test facility. In summary, the results showed that the total computation time of the coupled simulation was less than 10 min, compared to 20 h of the corresponding CFD models. At the same time, the accuracy of the simulation over five consecutive days was at a mean absolute error of 0.35 K for the indoor air temperature and at 1.2 % for the relative humidity. This shows that the novel coupled digital-twin workflow for virtual sensors is fast and accurate enough to optimise HVAC control systems in buildings.
Hoffer Johannes Georg, Geiger Bernhard, Kern Roman
2023
This research presents an approach that combines stacked Gaussian processes (stacked GP) with target vector Bayesian optimization (BO) to solve multi-objective inverse problems of chained manufacturing processes. In this context, GP surrogate models represent individual manufacturing processes and are stacked to build a unified surrogate model that represents the entire manufacturing process chain. Using stacked GPs, epistemic uncertainty can be propagated through all chained manufacturing processes. To perform target vector BO, acquisition functions make use of a noncentral χ-squared distribution of the squared Euclidean distance between a given target vector and surrogate model output. In BO of chained processes, there are the options to use a single unified surrogate model that represents the entire joint chain, or that there is a surrogate model for each individual process and the optimization is cascaded from the last to the first process. Literature suggests that a joint optimization approach using stacked GPs overestimates uncertainty, whereas a cascaded approach underestimates it. For improved target vector BO results of chained processes, we present an approach that combines methods which under- or overestimate uncertainties in an ensemble for rank aggregation. We present a thorough analysis of the proposed methods and evaluate on two artificial use cases and on a typical manufacturing process chain: preforming and final pressing of an Inconel 625 superalloy billet.
Evangelidis Thomas, Giassa Ilektra-Chara , Lovric Mario
2022
Identifying hit compounds is a principal step in early-stage drug discovery. While many machine learning (ML) approaches have been proposed, in the absence of binding data, molecular docking is the most widely used option to predict binding modes and score hundreds of thousands of compounds for binding affinity to the target protein. Docking's effectiveness is critically dependent on the protein-ligand (P-L) scoring function (SF), thus re-scoring with more rigorous SFs is a common practice. In this pilot study, we scrutinize the PM6-D3H4X/COSMO semi-empirical quantum mechanical (SQM) method as a docking pose re-scoring tool on 17 diverse receptors and ligand decoy sets, totaling 1.5 million P-L complexes. We investigate the effect of explicitly computed ligand conformational entropy and ligand deformation energy on SQM P-L scoring in a virtual screening (VS) setting, as well as molecular mechanics (MM) versus hybrid SQM/MM structure optimization prior to re-scoring. Our results proclaim that there is no obvious benefit from computing ligand conformational entropies or deformation energies and that optimizing only the ligand's geometry on the SQM level is sufficient to achieve the best possible scores. Instead, we leverage machine learning (ML) to include implicitly the missing entropy terms to the SQM score using ligand topology, physicochemical, and P-L interaction descriptors. Our new hybrid scoring function, named SQM-ML, is transparent and explainable, and achieves in average 9\% higher AUC-ROC than PM6-D3H4X/COSMO and 3\% higher than Glide SP, but with consistent and predictable performance across all test sets, unlike the former two SFs, whose performance is considerably target-dependent and sometimes resembles that of a random classifier. The code to prepare and train SQM-ML models is available at \url{https://github.com/tevang/sqm-ml.git} and we believe that will pave the way for a new generation of hybrid SQM/ML protein-ligand scoring functions.
Pammer-Schindler Viktoria, Lindstaedt Stefanie
2022
Digitale Kompetenzen sind im Bereich des strategischen Managements selbstverständlich, AI Literacy allerdings nicht. In diesem Artikel diskutieren wir, welches grundlegende Verständnis über künstliche Intelligenz (Artificial Intelligence – AI) für Entscheidungsträger:Innen im strategischen Management wichtig ist und welches darüber hinausgehende kontextspezifische und strategische Wissen.Digitale Kompetenzen für einen Großteil von beruflichen Tätigkeitsgruppen sind in aller Munde, zu Recht. Auf der Ebene von Entscheidungsträger:Innen im strategischen Management allerdings greifen diese zu kurz; sie sind größtenteils selbstverständlich im notwendigen Ausmaß: digitales Informationsmanagement, die Fähigkeit zur Kommunikation und Zusammenarbeit im Digitalen wie auch die Fähigkeiten, digitale Technologien zum Wissenserwerb und Lernen und zur Unterstützung bei kreativen Prozessen einzusetzen (Liste dieser typischen digitalen Kompetenzen aus [1]).Anders stellt sich die Sache dar, wenn es um spezialisiertes Wissen über moderne Computertechnologien geht, wie Methoden der automatischen Datenauswertung (Data Analytics) und der künstlichen Intelligenz, Internet of Things, Blockchainverfahren etc. (Auflistung in Anlehnung an Abb. 3 in [2]). Dieses Wissen wird in der Literatur durchaus als in Organisationen notwendiges Wissen behandelt [2]; allerdings üblicherweise mit dem Fokus darauf, dass dieses von Spezialist:Innen abgedeckt werden soll.Zusätzlich, und das ist die erste Hauptthese in diesem Kommentar, argumentieren wir, dass Entscheidungsträger:Innen im strategischen Management Grundlagenwissen in diesen technischen Bereichen brauchen, um in der Lage zu sein, diese Technologien in Bezug auf ihre Auswirkungen auf das eigene Unternehmen bzw. dessen Geschäftsumfeld einschätzen zu können. In diesem Artikel wird genauer das nötige Grundlagenwissen in Bezug auf künstliche Intelligenz (Artificial Intelligence – AI) betrachtet, das wir hier als „AI Literacy“ bezeichnen.
Rüdisser Hannah, Windisch Andreas, Amerstorfer U. V., Möstl C., Amerstorfer T., Bailey R. L., Reiss M. A.
2022
Interplanetary coronal mass ejections (ICMEs) are one of the main drivers for space weather disturbances. In the past, different approaches have been used to automatically detect events in existing time series resulting from solar wind in situ observations. However, accurate and fast detection still remains a challenge when facing the large amount of data from different instruments. For the automatic detection of ICMEs we propose a pipeline using a method that has recently proven successful in medical image segmentation. Comparing it to an existing method, we find that while achieving similar results, our model outperforms the baseline regarding training time by a factor of approximately 20, thus making it more applicable for other datasets. The method has been tested on in situ data from the Wind spacecraft between 1997 and 2015 with a True Skill Statistic of 0.64. Out of the 640 ICMEs, 466 were detected correctly by our algorithm, producing a total of 254 false positives. Additionally, it produced reasonable results on datasets with fewer features and smaller training sets from Wind, STEREO-A, and STEREO-B with TSSs of 0.56, 0.57, and 0.53, respectively. Our pipeline manages to find the start of an ICME with a mean absolute error (MAE) of around 2 hr and 56 min, and the end time with a MAE of 3 hr and 20 min. The relatively fast training allows straightforward tuning of hyperparameters and could therefore easily be used to detect other structures and phenomena in solar wind data, such as corotating interaction regions.
Stipanicev Drazenka, Repec Sinisa, Vucic Matej, Lovric Mario, Klobucar Goran
2022
In order to prevent the spread of COVID-19, contingency measures in the form of lockdowns were implemented all over the world, including in Croatia. The aim of this study was to detect if those severe, imposed restrictions of social interactions reflected on the water quality of rivers receiving wastewaters from urban areas. A total of 18 different pharmaceuticals (PhACs) and illicit drugs (IDrgs), as well as their metabolites, were measured for 16 months (January 2020–April 2021) in 12 different locations at in the Sava and Drava Rivers, Croatia, using UHPLC coupled to LCMS. This period encompassed two major Covid lockdowns (March–May 2020 and October 2020–March 2021). Several PhACs more than halved in river water mass flow during the lockdowns. The results of this study confirm that Covid lockdowns caused lower cumulative concentrations and mass flow of measured PhACs/IDrgs in the Sava and Drava Rivers. This was not influenced by the increased use of drugs for the treatment of the COVID-19, like antibiotics and steroidal anti-inflammatory drugs. The decreases in measured PhACs/IDrgs concentrations and mass flows were more pronounced during the first lockdown, which was stricter than the second.
Santa Maria Gonzalez Tomas, Vermeulen Walter J.V., Baumgartner Rupert J.,
2022
The process of developing sustainable and circular business models is quite complex and thus hinders their wider implementation in the market. Further understanding and guidelines for firms are needed. Design thinking is a promising problem solving approach capable of facilitating the innovation process. However, design thinking does not necessarily include sustainability considerations, and it has not been sufficiently explored for application in business model innovation. Given the additional challenges posed by the need for time-efficiency and a digital environment, we have therefore developed a design thinking-based framework to guide the early development of circular business models in an online and efficient manner. We propose a new process framework called the Circular Sprint. This encompasses seven phases and contains twelve purposefully adapted activities. The framework development follows an Action Design Research approach, iteratively combining four streams of literature, feedback from sixteen experts and six workshops, and involved a total of 107 participants working in fourteen teams. The present paper describes the framework and its activities, together with evaluations of its usefulness and ease-of-use. The research shows that, while challenging, embedding sustainability, circularity and business model innovation within a design thinking process is indeed possible. We offer a flexible framework and a set of context-adaptable activities that can support innovators and practitioners in the complex process of circular business model innovation. These tools can also be used for training and educational purposes. We invite future researchers to build upon and modify our framework and its activities by adapting it to their required scenarios and purposes. A detailed step-by-step user guide is provided in the supplementary material.
Wolfbauer Irmtraud, Pammer-Schindler Viktoria, Maitz Katharina, Rosé Carolyn P.
2022
We present a script for conversational reflection guidance embedded in reflective practice. Rebo Junior, a non-adaptive conversational agent, was evaluated in a 12-week field study with apprentices. We analysed apprentices’ interactions with Rebo Junior in terms of reflectivity, and measured the development of their reflection competence via reflective essays at three points in time during the field study. Reflection competence, a key competency for lifelong professional learning, becomes significantly higher by the third essay, after repeated interactions with Rebo Junior (paired-samples t-test t13=3.00, p=.010 from Essay 1 to Essay 3). However, we also observed a significant decrease in reflectivity in the Rebo Junior interactions over time (paired-samples t-test between the first and eighth interaction: t7=2.50, p=.041). We attribute this decline to i) the novelty of Rebo Junior wearing off (novelty effect) and ii) the apprentices learning the script and experiencing subsequent frustration due to the script not fading over time. Overall, this work i) informs future design through the observation of consistent decreases in engagement over 8 interactions with static scaffolding, and ii) contributes a reflection script applicable for reflection on tasks that resemble future expected work tasks, a typical setting in lifelong professional learning, and iii) indicates increased reflection competence after repeated reflection guided by a conversational agent.
Jean-Quartier Claire, Mazón Miguel Rey, Lovric Mario, Stryeck Sarah
2022
Research and development are facilitated by sharing knowledge bases, and the innovation process benefits from collaborative efforts that involve the collective utilization of data. Until now, most companies and organizations have produced and collected various types of data, and stored them in data silos that still have to be integrated with one another in order to enable knowledge creation. For this to happen, both public and private actors must adopt a flexible approach to achieve the necessary transition to break data silos and create collaborative data sharing between data producers and users. In this paper, we investigate several factors influencing cooperative data usage and explore the challenges posed by the participation in cross-organizational data ecosystems by performing an interview study among stakeholders from private and public organizations in the context of the project IDE@S, which aims at fostering the cooperation in data science in the Austrian federal state of Styria. We highlight technological and organizational requirements of data infrastructure, expertise, and practises towards collaborative data usage.
Malev Olga, Babic Sanja, Cota Anja Sima, Stipaničev Draženka, Repec Siniša, Drnić Martina, Lovric Mario, Bojanić Krunoslav, Radić Brkanac Sandra, Čož-Rakovac Rozelindra, Klobučar Göran
2022
This study focused on the short-term whole organism bioassays (WOBs) on fish (Danio rerio) and crustaceans (Gammarus fossarum and Daphnia magna) to assess the negative biological effects of water from the major European River Sava and the comparison of the obtained results with in vitro toxicity data (ToxCast database) and Risk Quotient (RQ) methodology. Pollution profiles of five sampling sites along the River Sava were assessed by simultaneous chemical analysis of 562 organic contaminants (OCs) of which 476 were detected. At each sampling site, pharmaceuticals/illicit drugs category was mostly represented by their cumulative concentration, followed by categories industrial chemicals, pesticides and hormones. An exposure-activity ratio (EAR) approach based on ToxCast data highlighted steroidal anti-inflammatory drugs, antibiotics, antiepileptics/neuroleptics, industrial chemicals and hormones as compounds with the highest biological potential. Summed EAR-based prediction of toxicity showed a good correlation with the estimated toxicity of assessed sampling sites using WOBs. WOBs did not exhibit increased mortality but caused various sub-lethal biological responses that were dependant relative to the sampling site pollution intensity as well as species sensitivity. Exposure of G. fossarum and D. magna to river water-induced lower feeding rates increased GST activity and TBARS levels. Zebrafish D. rerio embryo exhibited a significant decrease in heartbeat rate, failure in pigmentation formation, as well as inhibition of ABC transporters. Nuclear receptor activation was indicated as the biological target of greatest concern based on the EAR approach. A combined approach of short-term WOBs, with a special emphasis on sub-lethal endpoints, and chemical characterization of water samples compared against in vitro toxicity data from the ToxCast database and RQs can provide a comprehensive insight into the negative effect of pollutants on aquatic organisms.
Razouk Houssam, Kern Roman
2022
Digitalization of causal domain knowledge is crucial. Especially since the inclusion of causal domain knowledge in the data analysis processes helps to avoid biased results. To extract such knowledge, the Failure Mode Effect Analysis (FMEA) documents represent a valuable data source. Originally, FMEA documents were designed to be exclusively produced and interpreted by human domain experts. As a consequence, these documents often suffer from data consistency issues. This paper argues that due to the transitive perception of the causal relations, discordant and merged information cases are likely to occur. Thus, we propose to improve the consistency of FMEA documents as a step towards more efficient use of causal domain knowledge. In contrast to other work, this paper focuses on the consistency of causal relations expressed in the FMEA documents. To this end, based on an explicit scheme of types of inconsistencies derived from the causal perspective, novel methods to enhance the data quality in FMEA documents are presented. Data quality improvement will significantly improve downstream tasks, such as root cause analysis and automatic process control.
Lovric Mario, Antunović Mario, Šunić Iva, Vuković Matej, Kecorius Simon, Kröll Mark, Bešlić Ivan, Godec Ranka, Pehnec Gordana, Geiger Bernhard, Grange Stuart K, Šimić Iva
2022
In this paper, the authors investigated changes in mass concentrations of particulate matter (PM) during the Coronavirus Disease of 2019 (COVID-19) lockdown. Daily samples of PM1, PM2.5 and PM10 fractions were measured at an urban background sampling site in Zagreb, Croatia from 2009 to late 2020. For the purpose of meteorological normalization, the mass concentrations were fed alongside meteorological and temporal data to Random Forest (RF) and LightGBM (LGB) models tuned by Bayesian optimization. The models’ predictions were subsequently de-weathered by meteorological normalization using repeated random resampling of all predictive variables except the trend variable. Three pollution periods in 2020 were examined in detail: January and February, as pre-lockdown, the month of April as the lockdown period, as well as June and July as the “new normal”. An evaluation using normalized mass concentrations of particulate matter and Analysis of variance (ANOVA) was conducted. The results showed that no significant differences were observed for PM1, PM2.5 and PM10 in April 2020—compared to the same period in 2018 and 2019. No significant changes were observed for the “new normal” as well. The results thus indicate that a reduction in mobility during COVID-19 lockdown in Zagreb, Croatia, did not significantly affect particulate matter concentration in the long-term
Sousa Samuel, Kern Roman
2022
Deep learning (DL) models for natural language processing (NLP) tasks often handle private data, demanding protection against breaches and disclosures. Data protection laws, such as the European Union’s General Data Protection Regulation (GDPR), thereby enforce the need for privacy. Although many privacy-preserving NLP methods have been proposed in recent years, no categories to organize them have been introduced yet, making it hard to follow the progress of the literature. To close this gap, this article systematically reviews over sixty DL methods for privacy-preserving NLP published between 2016 and 2020, covering theoretical foundations, privacy-enhancing technologies, and analysis of their suitability for real-world scenarios. First, we introduce a novel taxonomy for classifying the existing methods into three categories: data safeguarding methods, trusted methods, and verification methods. Second, we present an extensive summary of privacy threats, datasets for applications, and metrics for privacy evaluation. Third, throughout the review, we describe privacy issues in the NLP pipeline in a holistic view. Further, we discuss open challenges in privacy-preserving NLP regarding data traceability, computation overhead, dataset size, the prevalence of human biases in embeddings, and the privacy-utility tradeoff. Finally, this review presents future research directions to guide successive research and development of privacy-preserving NLP models.
Koutroulis Georgios, Mutlu Belgin, Kern Roman
2022
In prognostics and health management (PHM), the task of constructing comprehensive health indicators (HI)from huge amounts of condition monitoring data plays a crucial role. HIs may influence both the accuracyand reliability of remaining useful life (RUL) prediction, and ultimately the assessment of system’s degradationstatus. Most of the existing methods assume apriori an oversimplified degradation law of the investigatedmachinery, which in practice may not appropriately reflect the reality. Especially for safety–critical engineeredsystems with a high level of complexity that operate under time-varying external conditions, degradationlabels are not available, and hence, supervised approaches are not applicable. To address the above-mentionedchallenges for extrapolating HI values, we propose a novel anticausal-based framework with reduced modelcomplexity, by predicting the cause from the causal models’ effects. Two heuristic methods are presented forinferring the structural causal models. First, the causal driver is identified from complexity estimate of thetime series, and second, the set of the effect measuring parameters is inferred via Granger Causality. Once thecausal models are known, off-line anticausal learning only with few healthy cycles ensures strong generalizationcapabilities that helps obtaining robust online predictions of HIs. We validate and compare our framework onthe NASA’s N-CMAPSS dataset with real-world operating conditions as recorded on board of a commercial jet,which are utilized to further enhance the CMAPSS simulation model. The proposed framework with anticausallearning outperforms existing deep learning architectures by reducing the average root-mean-square error(RMSE) across all investigated units by nearly 65%.
Hoffer Johannes Georg, Ofner Andreas Benjamin, Rohrhofer Franz Martin, Lovric Mario, Kern Roman, Lindstaedt Stefanie , Geiger Bernhard
2022
Most engineering domains abound with models derived from first principles that have beenproven to be effective for decades. These models are not only a valuable source of knowledge, but they also form the basis of simulations. The recent trend of digitization has complemented these models with data in all forms and variants, such as process monitoring time series, measured material characteristics, and stored production parameters. Theory-inspired machine learning combines the available models and data, reaping the benefits of established knowledge and the capabilities of modern, data-driven approaches. Compared to purely physics- or purely data-driven models, the models resulting from theory-inspired machine learning are often more accurate and less complex, extrapolate better, or allow faster model training or inference. In this short survey, we introduce and discuss several prominent approaches to theory-inspired machine learning and show how they were applied in the fields of welding, joining, additive manufacturing, and metal forming.
Reichel Robert, Gursch Heimo, Kröll Mark
2022
Der Trend, im Gesundheitswesen von Aufzeichnungen in Papierform auf digitale Formen zu wechseln, legt die Basis für eine elektronische Verarbeitung von Gesundheitsdaten. Dieser Artikel beschreibt die technischen Grundlagen für die semantische Aufbereitung und Analyse von textuellen Inhalten in der medizinischen Domäne. Die speziellen Eigenschaften medizinischer Texte gestalten die Extraktion sowie Aggregation relevanter Information herausfordernder als in anderen Anwendungsgebieten. Zusätzlich gibt es Bedarf an spezialisierten Methoden gerade im Bereich der Anonymisierung bzw. Pseudonymisierung personenbezogener Daten. Der Einsatz von Methoden der Computerlinguistik in Kombination mit der fortschreitenden Digitalisierung birgt dennoch enormes Potential, das Personal im Gesundheitswesen zu unterstützen.
Gashi Milot, Gursch Heimo, Hinterbichler Hannes, Pichler Stefan, Lindstaedt Stefanie , Thalmann Stefan
2022
Predictive Maintenance (PdM) is one of the most important applications of advanced data science in Industry 4.0, aiming to facilitate manufacturing processes. To build PdM models, sufficient data, such as condition monitoring and maintenance data of the industrial application, are required. However, collecting maintenance data is complex and challenging as it requires human involvement and expertise. Due to time constrains, motivating workers to provide comprehensive labeled data is very challenging, and thus maintenance data are mostly incomplete or even completely missing. In addition to these aspects, a lot of condition monitoring data-sets exist, but only very few labeled small maintenance data-sets can be found. Hence, our proposed solution can provide additional labels and offer new research possibilities for these data-sets. To address this challenge, we introduce MEDEP, a novel maintenance event detection framework based on the Pruned Exact Linear Time (PELT) approach, promising a low false-positive (FP) rate and high accuracy results in general. MEDEP could help to automatically detect performed maintenance events from the deviations in the condition monitoring data. A heuristic method is proposed as an extension to the PELT approach consisting of the following two steps: (1) mean threshold for multivariate time series and (2) distribution threshold analysis based on the complexity-invariant metric. We validate and compare MEDEP on the Microsoft Azure Predictive Maintenance data-set and data from a real-world use case in the welding industry. The experimental outcomes of the proposed approach resulted in a superior performance with an FP rate of around 10% on average and high sensitivity and accuracy results.
Ofner Andreas Benjamin, Kefalas Achilles, Posch Stefan, Geiger Bernhard
2022
This article introduces a method for the detection of knock occurrences in an internal combustion engine (ICE) using a 1-D convolutional neural network trained on in-cylinder pressure data. The model architecture is based on expected frequency characteristics of knocking combustion. All cycles were reduced to 60° CA long windows with no further processing applied to the pressure traces. The neural networks were trained exclusively on in-cylinder pressure traces from multiple conditions, with labels provided by human experts. The best-performing model architecture achieves an accuracy of above 92% on all test sets in a tenfold cross-validation when distinguishing between knocking and non-knocking cycles. In a multiclass problem where each cycle was labeled by the number of experts who rated it as knocking, 78% of cycles were labeled perfectly, while 90% of cycles were classified at most one class from ground truth. They thus considerably outperform the broadly applied maximum amplitude of pressure oscillation (MAPO) detection method, as well as references reconstructed from previous works. Our analysis indicates that the neural network learned physically meaningful features connected to engine-characteristic resonances, thus verifying the intended theory-guided data science approach. Deeper performance investigation further shows remarkable generalization ability to unseen operating points. In addition, the model proved to classify knocking cycles in unseen engines with increased accuracy of 89% after adapting to their features via training on a small number of exclusively non-knocking cycles. The algorithm takes below 1 ms to classify individual cycles, effectively making it suitable for real-time engine control.
Hoffer Johannes Georg, Geiger Bernhard, Kern Roman
2022
The avoidance of scrap and the adherence to tolerances is an important goal in manufacturing. This requires a good engineering understanding of the underlying process. To achieve this, real physical experiments can be conducted. However, they are expensive in time and resources, and can slow down production. A promising way to overcome these drawbacks is process exploration through simulation, where the finite element method (FEM) is a well-established and robust simulation method. While FEM simulation can provide high-resolution results, it requires extensive computing resources to do so. In addition, the simulation design often depends on unknown process properties. To circumvent these drawbacks, we present a Gaussian Process surrogate model approach that accounts for real physical manufacturing process uncertainties and acts as a substitute for expensive FEM simulation, resulting in a fast and robust method that adequately depicts reality. We demonstrate that active learning can be easily applied with our surrogate model to improve computational resources. On top of that, we present a novel optimization method that treats aleatoric and epistemic uncertainties separately, allowing for greater flexibility in solving inverse problems. We evaluate our model using a typical manufacturing use case, the preforming of an Inconel 625 superalloy billet on a forging press.
Ross-Hellauer Anthony, Cole Nicki Lisa, Fessl Angela, Klebel Thomas, Pontika, Nancy, Reichmann Stefan
2022
Open Science holds the promise to make scientific endeavours more inclusive, participatory, understandable, accessible and re-usable for large audiences. However, making processes open will not per se drive wide reuse or participation unless also accompanied by the capacity (in terms of knowledge, skills, financial resources, technological readiness and motivation) to do so. These capacities vary considerably across regions, institutions and demographics. Those advantaged by such factors will remain potentially privileged, putting Open Science's agenda of inclusivity at risk of propagating conditions of ‘cumulative advantage’. With this paper, we systematically scope existing research addressing the question: ‘What evidence and discourse exists in the literature about the ways in which dynamics and structures of inequality could persist or be exacerbated in the transition to Open Science, across disciplines, regions and demographics?’ Aiming to synthesize findings, identify gaps in the literature and inform future research and policy, our results identify threats to equity associated with all aspects of Open Science, including Open Access, Open and FAIR Data, Open Methods, Open Evaluation, Citizen Science, as well as its interfaces with society, industry and policy. Key threats include: stratifications of publishing due to the exclusionary nature of the author-pays model of Open Access; potential widening of the digital divide due to the infrastructure-dependent, highly situated nature of open data practices; risks of diminishing qualitative methodologies as ‘reproducibility’ becomes synonymous with quality; new risks of bias and exclusion in means of transparent evaluation; and crucial asymmetries in the Open Science relationships with industry and the public, which privileges the former and fails to fully include the latter.
Amjad Rana Ali, Liu Kairen, Geiger Bernhard
2022
In this work, we investigate the use of three information-theoretic quantities--entropy, mutual information with the class variable, and a class selectivity measure based on Kullback-Leibler (KL) divergence--to understand and study the behavior of already trained fully connected feedforward neural networks (NNs). We analyze the connection between these information-theoretic quantities and classification performance on the test set by cumulatively ablating neurons in networks trained on MNIST, FashionMNIST, and CIFAR-10. Our results parallel those recently published by Morcos et al., indicating that class selectivity is not a good indicator for classification performance. However, looking at individual layers separately, both mutual information and class selectivity are positively correlated with classification performance, at least for networks with ReLU activation functions. We provide explanations for this phenomenon and conclude that it is ill-advised to compare the proposed information-theoretic quantities across layers. Furthermore, we show that cumulative ablation of neurons with ascending or descending information-theoretic quantities can be used to formulate hypotheses regarding the joint behavior of multiple neurons, such as redundancy and synergy, with comparably low computational cost. We also draw connections to the information bottleneck theory for NNs.
Mirzababaei Behzad, Pammer-Schindler Viktoria
2021
This article discusses the usefulness of Toulmin’s model of arguments as structuring an assessment of different types of wrongness in an argument. We discuss the usability of the model within a conversational agent that aims to support users to develop a good argument. Within the article, we present a study and the development of classifiers that identify the existence of structural components in a good argument, namely a claim, a warrant (underlying understanding), and evidence. Based on a dataset (three sub-datasets with 100, 1,026, 211 responses in each) in which users argue about the intelligence or non-intelligence of entities, we have developed classifiers for these components: The existence and direction (positive/negative) of claims can be detected a weighted average F1 score over all classes (positive/negative/unknown) of 0.91. The existence of a warrant (with warrant/without warrant) can be detected with a weighted F1 score over all classes of 0.88. The existence of evidence (with evidence/without evidence) can be detected with a weighted average F1 score of 0.80. We argue that these scores are high enough to be of use within a conditional dialogue structure based on Bloom’s taxonomy of learning; and show by argument an example conditional dialogue structure that allows us to conduct coherent learning conversations. While in our described experiments, we show how Toulmin’s model of arguments can be used to identify structural problems with argumentation, we also discuss how Toulmin’s model of arguments could be used in conjunction with content-wise assessment of the correctness especially of the evidence component to identify more complex types of wrongness in arguments, where argument components are not well aligned. Owing to having progress in argument mining and conversational agents, the next challenges could be the developing agents that support learning argumentation. These agents could identify more complex type of wrongness in arguments that result from wrong connections between argumentation components.
Mirzababaei Behzad, Pammer-Schindler Viktoria
2021
This article discusses the usefulness of Toulmin’s model of arguments as structuring an assessment of different types of wrongness in an argument. We discuss the usability of the model within a conversational agent that aims to support users to develop a good argument. Within the article, we present a study and the development of classifiers that identify the existence of structural components in a good argument, namely a claim, a warrant (underlying understanding), and evidence. Based on a dataset (three sub-datasets with 100, 1,026, 211 responses in each) in which users argue about the intelligence or non-intelligence of entities, we have developed classifiers for these components: The existence and direction (positive/negative) of claims can be detected a weighted average F1 score over all classes (positive/negative/unknown) of 0.91. The existence of a warrant (with warrant/without warrant) can be detected with a weighted F1 score over all classes of 0.88. The existence of evidence (with evidence/without evidence) can be detected with a weighted average F1 score of 0.80. We argue that these scores are high enough to be of use within a conditional dialogue structure based on Bloom’s taxonomy of learning; and show by argument an example conditional dialogue structure that allows us to conduct coherent learning conversations. While in our described experiments, we show how Toulmin’s model of arguments can be used to identify structural problems with argumentation, we also discuss how Toulmin’s model of arguments could be used in conjunction with content-wise assessment of the correctness especially of the evidence component to identify more complex types of wrongness in arguments, where argument components are not well aligned. Owing to having progress in argument mining and conversational agents, the next challenges could be the developing agents that support learning argumentation. These agents could identify more complex type of wrongness in arguments that result from wrong connections between argumentation components.
Oana Inel, Duricic Tomislav, Harmanpreet Kaur, Lex Elisabeth, Nava Tintarev
2021
Online videos have become a prevalent means for people to acquire information. Videos, however, are often polarized, misleading, or contain topics on which people have different, contradictory views. In this work, we introduce natural language explanations to stimulate more deliberate reasoning about videos and raise users’ awareness of potentially deceiving or biased information. With these explanations, we aim to support users in actively deciding and reflecting on the usefulness of the videos. We generate the explanations through an end-to-end pipeline that extracts reflection triggers so users receive additional information to the video based on its source, covered topics, communicated emotions, and sentiment. In a between-subjects user study, we examine the effect of showing the explanations for videos on three controversial topics. Besides, we assess the users’ alignment with the video’s message and how strong their belief is about the topic. Our results indicate that respondents’ alignment with the video’s message is critical to evaluate the video’s usefulness. Overall, the explanations were found to be useful and of high quality. While the explanations do not influence the perceived usefulness of the videos compared to only seeing the video, people with an extreme negative alignment with a video’s message perceived it as less useful (with or without explanations) and felt more confident in their assessment. We relate our findings to cognitive dissonance since users seem to be less receptive to explanations when the video’s message strongly challenges their beliefs. Given these findings, we provide a set of design implications for explanations grounded in theories on reducing cognitive dissonance in light of raising awareness about online deception.
Egger Jan, Pepe Antonio, Gsaxner Christina, Jin Yuan, Li Jianning, Kern Roman
2021
Deep learning belongs to the field of artificial intelligence, where machines perform tasks that typically require some kind of human intelligence. Deep learning tries to achieve this by drawing inspiration from the learning of a human brain. Similar to the basic structure of a brain, which consists of (billions of) neurons and connections between them, a deep learning algorithm consists of an artificial neural network, which resembles the biological brain structure. Mimicking the learning process of humans with their senses, deep learning networks are fed with (sensory) data, like texts, images, videos or sounds. These networks outperform the state-of-the-art methods in different tasks and, because of this, the whole field saw an exponential growth during the last years. This growth resulted in way over 10,000 publications per year in the last years. For example, the search engine PubMed alone, which covers only a sub-set of all publications in the medical field, provides already over 11,000 results in Q3 2020 for the search term ‘deep learning’, and around 90% of these results are from the last three years. Consequently, a complete overview over the field of deep learning is already impossible to obtain and, in the near future, it will potentially become difficult to obtain an overview over a subfield. However, there are several review articles about deep learning, which are focused on specific scientific fields or applications, for example deep learning advances in computer vision or in specific tasks like object detection. With these surveys as a foundation, the aim of this contribution is to provide a first high-level, categorized meta-survey of selected reviews on deep learning across different scientific disciplines and outline the research impact that they already have during a short period of time. The categories (computer vision, language processing, medical informatics and additional works) have been chosen according to the underlying data sources (image, language, medical, mixed). In addition, we review the common architectures, methods, pros, cons, evaluations, challenges and future directions for every sub-category
Pammer-Schindler Viktoria, Prilla Michael
2021
A substantial body of human-computer interaction literature investigates tools that are intended to support reflection, e.g. under the header of quantified self or in computer-mediated learning. These works describe the issues that are reflected on by users in terms of examples, such as reflecting on financial expenditures, lifestyle, professional growth, etc. A coherent concept is missing. In this paper, the reflection object is developed based on activity theory, reflection theory and related design-oriented research. The reflection object is both what is reflected on and what is changed through reflection. It constitutes the link between reflection and other activities in which the reflecting person participates. By combining these two aspects—what is reflected on and what is changed—into a coherent conceptual unit, the concept of the reflection object provides a frame to focus on how to support learning, change and transformation, which is a major challenge when designing technologies for reflection.
Lovric Mario, Duricic Tomislav, Tran Thi Ngoc Han, Hussain Hussain, Lacic Emanuel, Morten A. Rasmussen, Kern Roman
2021
Methods for dimensionality reduction are showing significant contributions to knowledge generation in high-dimensional modeling scenarios throughout many disciplines. By achieving a lower dimensional representation (also called embedding), fewer computing resources are needed in downstream machine learning tasks, thus leading to a faster training time, lower complexity, and statistical flexibility. In this work, we investigate the utility of three prominent unsupervised embedding techniques (principal component analysis—PCA, uniform manifold approximation and projection—UMAP, and variational autoencoders—VAEs) for solving classification tasks in the domain of toxicology. To this end, we compare these embedding techniques against a set of molecular fingerprint-based models that do not utilize additional pre-preprocessing of features. Inspired by the success of transfer learning in several fields, we further study the performance of embedders when trained on an external dataset of chemical compounds. To gain a better understanding of their characteristics, we evaluate the embedders with different embedding dimensionalities, and with different sizes of the external dataset. Our findings show that the recently popularized UMAP approach can be utilized alongside known techniques such as PCA and VAE as a pre-compression technique in the toxicology domain. Nevertheless, the generative model of VAE shows an advantage in pre-compressing the data with respect to classification accuracy.
Hoffer Johannes Georg, Geiger Bernhard, Ofner Patrick, Kern Roman
2021
The technical world of today fundamentally relies on structural analysis in the form of design and structural mechanic simulations.A traditional and robust simulation method is the physics-based Finite Element Method (FEM) simulation. FEM simulations in structural mechanics are known to be very accurate, however, the higher the desired resolution, the more computational effort is required. Surrogate modeling provides a robust approach to address this drawback. Nonetheless, finding the right surrogate model and its hyperparameters for a specific use case is not a straightforward process.In this paper, we discuss and compare several classes of mesh-free surrogate models based on traditional and thriving Machine Learning (ML) and Deep Learning (DL) methods.We show that relatively simple algorithms (such as $k$-nearest neighbor regression) can be competitive in applications with low geometrical complexity and extrapolation requirements. With respect to tasks exhibiting higher geometric complexity, our results show that recent DL methods at the forefront of literature (such as physics-informed neural networks), are complicated to train and to parameterize and thus require further research before they can be put to practical use. In contrast, we show that already well-researched DL methods such as the multi-layer perceptron are superior with respect to interpolation use cases and can be easily trained with available tools.With our work, we thus present a basis for selection and practical implementation of surrogate models.
Iacono Lucas, Veas Eduardo Enrique
2021
AVL RACING and the Knowledge Visualization group of Know-Center GmbH, are evaluating the performance of racing drivers using the latest wearables technologies, data analytics and vehicle dynamics simulation software from AVL. The goal is to measure human factors related with biosensors synchronized with vehicle data at a Driver-in-the-Loop (DiL) and vehicle dynamics simulation software AVL VSM™ RACE
Iacono Lucas, Veas Eduardo Enrique
2021
Know-Center is developing human-centered intelligent systems that detect cognitive, emotional and health related states by action, perception and by means of cognitive and health metrics. Models of human behavior and intention allow to be derived during different activities. The innovative set-up is reflected by linking the human telemetry (HT) system with activity monitors and by synchronizing the data. This article details our system composed of several wearable sensors, such as EEG, eye-tracker, ECG, EMG, and a data-logger, and methodology used to perform our studies
Pammer-Schindler Viktoria, Rosé Carolyn
2021
Professional and lifelong learning are a necessity for workers. This is true both for re-skilling from disappearing jobs, as well as for staying current within a professional domain. AI-enabled scaffolding and just-in-time and situated learning in the workplace offer a new frontier for future impact of AIED. The hallmark of this community’s work has been i) data-driven design of learning technology and ii) machine-learning enabled personalized interventions. In both cases, data are the foundation of AIED research and data-related ethics are thus central to AIED research. In this paper we formulate a vision how AIED research could address data-related ethics issues in informal and situated professional learning. The foundation of our vision is a secondary analysis of five research cases that offer insights related to data-driven adaptive technologies for informal professional learning. We describe the encountered data-related ethics issues. In our interpretation, we have developed three themes: Firstly, in informal and situated professional learning, relevant data about professional learning – to be used as a basis for learning analytics and reflection or as a basis for adaptive systems - is not only about learners. Instead, due to the situatedness of learning, relevant data is also about others (colleagues, customers, clients) and other objects from the learner’s context. Such data may be private, proprietary, or both. Secondly, manual tracking comes with high learner control over data. Thirdly, learning is not necessarily a shared goal in informal professional learning settings. From an ethics perspective, this is particularly problematic as much data that would be relevant for use within learning technologies hasn’t been collected for the purposes of learning. These three themes translate into challenges for AIED research that need to be addressed in order to successfully investigate and develop AIED technology for informal and situated professional learning. As an outlook of this paper, we connect these challenges to ongoing research directions within AIED – natural language processing, socio-technical design, and scenario-based data collection - that might be leveraged and aimed towards addressing data-related ethics challenges.
Smieja Marek, Wolczyk Maciej, Tabor Jacek, Geiger Bernhard
2021
We propose a semi-supervised generative model, SeGMA, which learns a joint probability distribution of data and their classes and is implemented in a typical Wasserstein autoencoder framework. We choose a mixture of Gaussians as a target distribution in latent space, which provides a natural splitting of data into clusters. To connect Gaussian components with correct classes, we use a small amount of labeled data and a Gaussian classifier induced by the target distribution. SeGMA is optimized efficiently due to the use of the Cramer-Wold distance as a maximum mean discrepancy penalty, which yields a closed-form expression for a mixture of spherical Gaussian components and, thus, obviates the need of sampling. While SeGMA preserves all properties of its semi-supervised predecessors and achieves at least as good generative performance on standard benchmark data sets, it presents additional features: 1) interpolation between any pair of points in the latent space produces realistically looking samples; 2) combining the interpolation property with disentangling of class and style information, SeGMA is able to perform continuous style transfer from one class to another; and 3) it is possible to change the intensity of class characteristics in a data point by moving the latent representation of the data point away from specific Gaussian components.
Geiger Bernhard
2021
We review the current literature concerned with information plane (IP) analyses of neural network (NN) classifiers. While the underlying information bottleneck theory and the claim that information-theoretic compression is causally linked to generalization are plausible, empirical evidence was found to be both supporting and conflicting. We review this evidence together with a detailed analysis of how the respective information quantities were estimated. Our survey suggests that compression visualized in IPs is not necessarily information-theoretic but is rather often compatible with geometric compression of the latent representations. This insight gives the IP a renewed justification. Aside from this, we shed light on the problem of estimating mutual information in deterministic NNs and its consequences. Specifically, we argue that, even in feedforward NNs, the data processing inequality needs not to hold for estimates of mutual information. Similarly, while a fitting phase, in which the mutual information is between the latent representation and the target increases, is necessary (but not sufficient) for good classification performance, depending on the specifics of mutual information estimation, such a fitting phase needs to not be visible in the IP.
Lex Elisabeth, Kowald Dominik, Seitlinger Paul, Tran Tran, Felfernig Alexander, Schedl Markus
2021
Psychology-informed Recommender Systems
Ruiz-Calleja Adolfo, Prieto Luis P., Ley Tobias, Rodrıguez-Triana Marıa Jesus, Dennerlein Sebastian
2021
Despite the ubiquity of learning in workplace and professional settings, the learning analytics (LA) community has paid significant attention to such settings only recently. This may be due to the focus on researching formal learning, as workplace learning is often informal, hard to grasp and not unequivocally defined. This paper summarizes the state of the art of Workplace Learning Analytics (WPLA), extracted from a two-iteration systematic literature review. Our in-depth analysis of 52 existing proposals not only provides a descriptive view of the field, but also reflects on researcher conceptions of learning and their influence on the design, analytics and technology choices made in this area. We also discuss the characteristics of workplace learning that make WPLA proposals different from LA in formal education contexts and the challenges resulting from this. We found that WPLA is gaining momentum, especially in some fields, like healthcare and education. The focus on theory is generally a positive feature in WPLA, but we encourage a stronger focus on assessing the impact of WPLA in realistic settings.
Basirat Mina, Geiger Bernhard, Roth Peter
2021
Information plane analysis, describing the mutual information between the input and a hidden layer and between a hidden layer and the target over time, has recently been proposed to analyze the training of neural networks. Since the activations of a hidden layer are typically continuous-valued, this mutual information cannot be computed analytically and must thus be estimated, resulting in apparently inconsistent or even contradicting results in the literature. The goal of this paper is to demonstrate how information plane analysis can still be a valuable tool for analyzing neural network training. To this end, we complement the prevailing binning estimator for mutual information with a geometric interpretation. With this geometric interpretation in mind, we evaluate the impact of regularization and interpret phenomena such as underfitting and overfitting. In addition, we investigate neural network learning in the presence of noisy data and noisy labels.
Schweimer Christoph, Geiger Bernhard, Wang Meizhu, Gogolenko Sergiy, Gogolenko Sergiy, Mahmood Imran, Jahani Alireza, Suleimenova Diana, Groen Derek
2021
Automated construction of location graphs is instrumental but challenging, particularly in logistics optimisation problems and agent-based movement simulations. Hence, we propose an algorithm for automated construction of location graphs, in which vertices correspond to geographic locations of interest and edges to direct travelling routes between them. Our approach involves two steps. In the first step, we use a routing service to compute distances between all pairs of L locations, resulting in a complete graph. In the second step, we prune this graph by removing edges corresponding to indirect routes, identified using the triangle inequality. The computational complexity of this second step is O(L3), which enables the computation of location graphs for all towns and cities on the road network of an entire continent. To illustrate the utility of our algorithm in an application, we constructed location graphs for four regions of different size and road infrastructures and compared them to manually created ground truths. Our algorithm simultaneously achieved precision and recall values around 0.9 for a wide range of the single hyperparameter, suggesting that it is a valid approach to create large location graphs for which a manual creation is infeasible.
Kowald Dominik, Müllner Peter , Zangerle Eva, Bauer Christine, Schedl Markus, Lex_KC Elisabeth
2021
Support the Underground: Characteristics of Beyond-Mainstream Music Listeners. EPJ Data Scienc
Schedl Markus, Bauer Christine, Reisinger Wolfgang, Kowald Dominik, Lex_KC Elisabeth
2021
Listener Modeling and Context-Aware Music Recommendation Based on Country Archetyp
Kefalas Achilles, Ofner Andreas Benjamin, Pirker Gerhard, Posch Stefan, Geiger Bernhard, Wimmer Andreas
2021
The phenomenon of knock is an abnormal combustion occurring in spark-ignition (SI) engines and forms a barrier that prevents an increase in thermal efficiency while simultaneously reducing CO2 emissions. Since knocking combustion is highly stochastic, a cyclic analysis of in-cylinder pressure is necessary. In this study we propose an approach for efficient and robust detection and identification of knocking combustion in three different internal combustion engines. The proposed methodology includes a signal processing technique, called continuous wavelet transformation (CWT), which provides a simultaneous analysis of the in-cylinder pressure traces in the time and frequency domains with coefficients. These coefficients serve as input for a convolutional neural network (CNN) which extracts distinctive features and performs an image recognition task in order to distinguish between non-knock and knock. The results revealed the following: (i) The CWT delivered a stable and effective feature space with the coefficients that represents the unique time-frequency pattern of each individual in-cylinder pressure cycle; (ii) the proposed approach was superior to the state-of-the-art threshold value exceeded (TVE) method with a maximum amplitude pressure oscillation (MAPO) criterion improving the overall accuracy by 6.15 percentage points (up to 92.62%); and (iii) The CWT + CNN method does not require calibrating threshold values for different engines or operating conditions as long as enough and diverse data is used to train the neural network.
Geiger Bernhard, Kubin Gernot
2020
guest editorial for a special issue
Dumouchel Suzane, Blotiere Emilie, Breitfuß Gert, Chen Yin, Di Donato Francesca, Eskevich Maria, Forbes Paula, Georgiadis Haris, Gingold Arnaud, Gorgaini Elisa, Morainville Yoann, de Paoli Stefano, Petitfils Clara, Pohle Stefanie, Toth-Czifra Erzebeth
2020
Social sciences and humanities (SSH) research is divided across a wide array of disciplines, sub-disciplines and languages. While this specialisation makes it possible to investigate the extensive variety of SSH topics, it also leads to a fragmentation that prevents SSH research from reaching its full potential. The TRIPLE project brings answers to these issues by developing an innovative discovery platform for SSH data, researchers’ projects and profiles. Having started in October 2019, the project has already three main achievements that are presented in this paper: 1) the definition of main features of the GOTRIPLE platform; 2) its interoperability; 3) its multilingual, multicultural and interdisciplinary vocation. These results have been achieved thanks to different methodologies such as a co-design process, market analysis and benchmarking, monitoring and co-building. These preliminary results highlight the need of respecting diversity of practices and communities through coordination and harmonisation.
Ciura Krzesimir, Fedorowicz Joanna, Zuvela Petar, Lovric Mario, Kapica Hanna, Baranowski Pawel, Sawicki Wieslaw, Wong Ming Wah, Sączewski Jaroslaw
2020
Currently, rapid evaluation of the physicochemical parameters of drug candidates, such as lipophilicity, is in high demand owing to it enabling the approximation of the processes of absorption, distribution, metabolism, and elimination. Although the lipophilicity of drug candidates is determined using the shake flash method (n-octanol/water system) or reversed phase liquid chromatography (RP-LC), more biosimilar alternatives to classical lipophilicity measurement are currently available. One of the alternatives is immobilized artificial membrane (IAM) chromatography. The present study is a continuation of our research focused on physiochemical characterization of biologically active derivatives of isoxazolo[3,4-b]pyridine-3(1H)-ones. The main goal of this study was to assess the affinity of isoxazolones to phospholipids using IAM chromatography and compare it with the lipophilicity parameters established by reversed phase chromatography. Quantitative structure–retention relationship (QSRR) modeling of IAM retention using differential evolution coupled with partial least squares (DE-PLS) regression was performed. The results indicate that in the studied group of structurally related isoxazolone derivatives, discrepancies occur between the retention under IAM and RP-LC conditions. Although some correlation between these two chromatographic methods can be found, lipophilicity does not fully explain the affinities of the investigated molecules to phospholipids. QSRR analysis also shows common factors that contribute to retention under IAM and RP-LC conditions. In this context, the significant influences of WHIM and GETAWAY descriptors in all the obtained models should be highlighted
Lovric Mario, Meister Richard, Steck Thomas, Fadljevic Leon, Gerdenitsch Johann, Schuster Stefan, Schiefermüller Lukas, Lindstaedt Stefanie , Kern Roman
2020
In industrial electro galvanizing lines aged anodes deteriorate zinc coating distribution over the strip width, leading to an increase in electricity and zinc cost. We introduce a data-driven approach in predictive maintenance of anodes to replace the cost- and labor-intensive manual inspection, which is still common for this task. The approach is based on parasitic resistance as an indicator of anode condition which might be aged or mis-installed. The parasitic resistance is indirectly observable via the voltage difference between the measured and baseline (theoretical) voltage for healthy anode. Here we calculate the baseline voltage by means of two approaches: (1) a physical model based on electrical and electrochemical laws, and (2) advanced machine learning techniques including boosting and bagging regression. The data was collected on one exemplary rectifier unit equipped with two anodes being studied for a total period of two years. The dataset consists of one target variable (rectifier voltage) and nine predictive variables used in the models, observing electrical current, electrolyte, and steel strip characteristics. For predictive modelling, we used Random Forest, Partial Least Squares and AdaBoost Regression. The model training was conducted on intervals where the anodes were in good condition and validated on other segments which served as a proof of concept that bad anode conditions can be identified using the parasitic resistance predicted by our models. Our results show a RMSE of 0.24 V for baseline rectifier voltage with a mean ± standard deviation of 11.32 ± 2.53 V for the best model on the validation set. The best-performing model is a hybrid version of a Random Forest which incorporates meta-variables computed from the physical model. We found that a large predicted parasitic resistance coincides well with the results of the manual inspection. The results of this work will be implemented in online monitoring of anode conditions to reduce operational cost at a production site
Obermeier, Melanie Maria, Wicaksono, Wisnu Adi, Taffner, Julian, Bergna, Alessandro, Poehlein, Anja, Cernava, Tomislav, Lindstaedt Stefanie , Lovric Mario, Müller Bogota, Christina Andrea, Berg, Gabriele
2020
The expanding antibiotic resistance crisis calls for a more in depth understanding of the importance of antimicrobial resistance genes (ARGs) in pristine environments. We, therefore, studied the microbiome associated with Sphagnum moss forming the main vegetation in undomesticated, evolutionary old bog ecosystems. In our complementary analysis of culture collections, metagenomic data and a fosmid library from different geographic sites in Europe, we identified a low abundant but highly diverse pool of resistance determinants, which targets an unexpectedly broad range of 29 antibiotics including natural and synthetic compounds. This derives both, from the extraordinarily high abundance of efflux pumps (up to 96%), and the unexpectedly versatile set of ARGs underlying all major resistance mechanisms. Multi-resistance was frequently observed among bacterial isolates, e.g. in Serratia, Rouxiella, Pandoraea, Paraburkholderia and Pseudomonas. In a search for novel ARGs, we identified the new class A β-lactamase Mm3. The native Sphagnum resistome comprising a highly diversified and partially novel set of ARGs contributes to the bog ecosystem´s plasticity. Our results reinforce the ecological link between natural and clinically relevant resistomes and thereby shed light onto this link from the aspect of pristine plants. Moreover, they underline that diverse resistomes are an intrinsic characteristic of plant-associated microbial communities, they naturally harbour many resistances including genes with potential clinical relevance
Rauter Romana, Lerch Anita, Lederer-Hutsteiner Thomas, Klinger Sabine, Mayr Andrea, Gutounig Robert, Pammer-Schindler Viktoria
2020
Dennerlein Sebastian, Wolf-Brenner Christof, Gutounig Robert, Schweiger Stefan, Pammer-Schindler Viktoria
2020
Künstliche Intelligenz (KI) ist zum Gegenstand gesellschaftlicher Debatten geworden. Die Beratung durch KI unterstützt uns in der Schule, im Alltag beim Einkauf, bei der Urlaubsplanung und beim Medienkonsum, manipuliert uns allerdings auch gezielt bei Entscheidungen oder führt durch Filter-Bubble-Phänomene zur Realitätsverzerrung.Eine der jüngsten Aufregungen hierzulande galt der Nutzung moderner Algorithmik durch das österreichische Arbeitsmarktservice AMS. Der sogenannte "AMS-Algorithmus" soll Beratende bei der Entscheidung über Fördermaßnahmen unterstützen.Wenn KI in einem so erheblichen Ausmaß in menschliches Handeln eingreift, bedarf sie im Hinblick auf ethische Prinzipien einer sorgfältigen Bewertung. Das ist notwendig, um unethische Folgen zu vermeiden. Üblicherweise wird gefordert, KI bzw. Algorithmen sollen fair sein, was bedeutet, sie sollen nicht diskriminieren und transparent sollen sie sein, also Einblick in ihre Funktionsweise ermöglichen
Fessl Angela, Pammer-Schindler_TU Viktoria, Kai Pata, Mati Mõttus, Jörgen Janus, Tobias Ley
2020
This paper presents cooperative design as method to address the needs of SMEs to gain sufficient knowledge about new technologies in order for them to decide about adoption for knowledge management. We developed and refined a cooperative design method iteratively over nine use cases. In each use case, the goal was to match the SME’s knowledge management needs with offerings of new (to the SMEs) technologies. Where traditionally, innovation adoption and diffusion literature assume new knowledge to be transferred from knowledgeable stakeholders to less knowledgeable stakeholders, our method is built on cooperative design. In this, the relevant knowledge is constructed by the SMEs who wish to decide upon the adoption of novel technologies through the cooperative design process. The presented method is constituted of an analysis stage based on activity theory and a design stage based on paper prototyping and design workshops. In all nine cases, our method led to a good understanding a) of the domain by researchers – validated by the creation of meaningful first-version paper prototypes and b) of new technologies – validated by meaningful input to design and plausible assessment of technologies’ benefit for the respective SME. Practitioners and researchers alike are invited to use the here documented tools to cooperatively match the domain needs of practitioners with the offerings of new technologies. The value of our work lies in providing a concrete implementation of the cooperative design paradigm that is based on an established theory (activity theory) for work analysis and established tools of cooperative design (paper prototypes and design workshops as media of communication); and a discussion based on nine heterogeneous use cases.
Geiger Bernhard, Fischer Ian
2020
In this short note, we relate the variational bounds proposed in Alemi et al. (2017) and Fischer (2020) for the information bottleneck (IB) and the conditional entropy bottleneck (CEB) functional, respectively. Although the two functionals were shown to be equivalent, it was empirically observed that optimizing bounds on the CEB functional achieves better generalization performance and adversarial robustness than optimizing those on the IB functional. This work tries to shed light on this issue by showing that, in the most general setting, no ordering can be established between these variational bounds, while such an ordering can be enforced by restricting the feasible sets over which the optimizations take place. The absence of such an ordering in the general setup suggests that the variational bound on the CEB functional is either more amenable to optimization or a relevant cost function for optimization in its own regard, i.e., without justification from the IB or CEB functionals.
Tschinkel Gerwald
2020
One classic issue associated with being a researcher nowadays is the multitude and magnitude of search results for a given topic. Recommender systems can help to fix this problem by directing users to the resources most relevant to their specific research focus. However, sets of automatically generated recommendations are likely to contain irrelevant resources, making user interfaces that provide effective filtering mechanisms necessary.This problem is exacerbated when users resume a previously interrupted research task, or when different users attempt to tackle one extensive list of results, as confusion as to what resources should be consulted can be overwhelming.The presented recommendation dashboard uses micro-visualisations to display the state of multiple filters in a data type-specific manner. This paper describes the design and geometry of micro-visualisations and presents results from an evaluation of their readability and memorability in the context of exploring recommendation results. Based on that, this paper also proposes applying micro-visualisations for extending the use of a desktop-based dashboard to the needs of small-screen, mobile multi-touch devices, such as smartphones. A small-scale heuristic evaluation was conducted using a first prototype implementation.
Žuvela, Petar, Lovric Mario, Yousefian-Jazi, Ali, Liu, J. Jay
2020
Numerous industrial applications of machine learning feature critical issues that need to be addressed. This work proposes a framework to deal with these issues, such as competing objectives and class imbalance in designing a machine vision system for the in-line detection of surface defects on glass substrates of thin-film transistor liquid crystal displays (TFT-LCDs). The developed inspection system composes of (i) feature engineering: extraction of only the defect-relevant features from images using two-dimensional wavelet decomposition and (ii) training ensemble classifiers (proof of concept with a C5.0 ensemble, random forests (RF), and adaptive boosting (AdaBoost)). The focus is on cost sensitivity, increased generalization, and robustness to handle class imbalance and address multiple competing manufacturing objectives. Comprehensive performance evaluation was conducted in terms of accuracy, sensitivity, specificity, and the Matthews correlation coefficient (MCC) by calculating their 12,000 bootstrapped estimates. Results revealed significant differences (p < 0.05) between the three developed diagnostic algorithms. RFR (accuracy of 83.37%, sensitivity of 60.62%, specificity of 89.72%, and MCC of 0.51) outperformed both AdaBoost (accuracy of 81.14%, sensitivity of 69.23%, specificity of 84.48%, and MCC of 0.50) and the C5.0 ensemble (accuracy of 78.35%, sensitivity of 65.35%, specificity of 82.03%, and MCC of 0.44) in all the metrics except sensitivity. AdaBoost exhibited stronger performance in detecting defective TFT-LCD glass substrates. These promising results demonstrated that the proposed ensemble approach is a viable alternative to manual inspections when applied to an industrial case study with issues such as competing objectives and class imbalance.
Malev, Olga, Lovric Mario, Stipaničev, Draženka, Repec, Siniša, Martinović-Weigelt, Dalma, Zanella, Davor, Đuretec, Valnea Sindiči, Barišić, Josip, Li, Mei, Klobučar, Göran
2020
Chemical analysis of plasma samples of wild fish from the Sava River (Croatia) revealed the presence of 90 different pharmaceuticals/illicit drugs and their metabolites (PhACs/IDrgs). The concentrations of these PhACs/IDrgs in plasma were 10 to 1, 000 times higher than their concentrations in river water. Antibiotics, allergy/cold medications and analgesics were categories with the highest plasma concentrations. Fifty PhACs/IDrgs were identified as chemicals of concern based on the fish plasma model (FPM) effect ratios (ER) and their potential to activate evolutionary conserved biological targets. Chemicals of concern were also prioritized by calculating exposure-activity ratios (EARs) where plasma concentrations of chemicals were compared to their bioactivities in comprehensive ToxCast suite of in vitro assays. Overall, the applied prioritization methods indicated stimulants (nicotine, cotinine) and allergy/cold medications (prednisolone, dexamethasone) as having the highest potential biological impact on fish. The FPM model pointed to psychoactive substances (hallucinogens/stimulants and opioids) and psychotropic substances in the cannabinoids category (i.e. CBD and THC). EAR confirmed above and singled out additional chemicals of concern - anticholesteremic simvastatin and antiepileptic haloperidol. Present study demonstrates how the use of a combination of chemical analyses, and bio-effects based risk predictions with multiple criteria can help identify priority contaminants in freshwaters. The results reveal a widespread exposure of fish to complex mixtures of PhACs/IDrgs, which may target common molecular targets. While many of the prioritized chemicals occurred at low concentrations, their adverse effect on aquatic communities, due to continuous chronic exposure and additive effects, should not be neglected.
Havaš Auguštin, Dubravka, Šarac, Jelena, Lovric Mario, Živković, Jelena, Malev, Olga, Fuchs, Nives, Novokmet, Natalija, Turkalj, Mirjana, Missoni, Saša
2020
Maternal nutrition and lifestyle in pregnancy are important modifiable factors for both maternal and offspring’s health. Although the Mediterranean diet has beneficial effects on health, recent studies have shown low adherence in Europe. This study aimed to assess the Mediterranean diet adherence in 266 pregnant women from Dalmatia, Croatia and to investigate their lifestyle habits and regional differences. Adherence to the Mediterranean diet was assessed through two Mediterranean diet scores. Differences in maternal characteristics (diet, education, income, parity, smoking, pre-pregnancy body mass index (BMI), physical activity, contraception) with regards to location and dietary habits were analyzed using the non-parametric Mann–Whitney U test. The machine learning approach was used to reveal other potential non-linear relationships. The results showed that adherence to the Mediterranean diet was low to moderate among the pregnant women in this study, with no significant mainland–island differences. The highest adherence was observed among wealthier women with generally healthier lifestyle choices. The most significant mainland–island differences were observed for lifestyle and socioeconomic factors (income, education, physical activity). The machine learning approach confirmed the findings of the conventional statistical method. We can conclude that adverse socioeconomic and lifestyle conditions were more pronounced in the island population, which, together with the observed non-Mediterranean dietary pattern, calls for more effective intervention strategies
Lacic Emanuel, Markus Reiter-Haas, Kowald Dominik, Reddy Dareddy Mano, Cho Junghoo, Lex Elisabeth
2020
In this work, we address the problem of providing job recommendations in an online session setting, in which we do not have full user histories. We propose a recom-mendation approach, which uses different autoencoder architectures to encode ses-sions from the job domain. The inferred latent session representations are then used in a k-nearest neighbor manner to recommend jobs within a session. We evaluate our approach on three datasets, (1) a proprietary dataset we gathered from the Austrian student job portal Studo Jobs, (2) a dataset released by XING after the RecSys 2017 Challenge and (3) anonymized job applications released by CareerBuilder in 2012. Our results show that autoencoders provide relevant job recommendations as well as maintain a high coverage and, at the same time, can outperform state-of-the-art session-based recommendation techniques in terms of system-based and session-based novelty
Amjad Rana Ali, Geiger Bernhard
2020
In this theory paper, we investigate training deep neural networks (DNNs) for classification via minimizing the information bottleneck (IB) functional. We show that the resulting optimization problem suffers from two severe issues: First, for deterministic DNNs, either the IB functional is infinite for almost all values of network parameters, making the optimization problem ill-posed, or it is piecewise constant, hence not admitting gradient-based optimization methods. Second, the invariance of the IB functional under bijections prevents it from capturing properties of the learned representation that are desirable for classification, such as robustness and simplicity. We argue that these issues are partly resolved for stochastic DNNs, DNNs that include a (hard or soft) decision rule, or by replacing the IB functional with related, but more well-behaved cost functions. We conclude that recent successes reported about training DNNs using the IB framework must be attributed to such solutions. As a side effect, our results indicate limitations of the IB framework for the analysis of DNNs. We also note that rather than trying to repair the inherent problems in the IB functional, a better approach may be to design regularizers on latent representation enforcing the desired properties directly.
Amjad Rana Ali, Bloechl Clemens, Geiger Bernhard
2020
We propose an information-theoretic Markov aggregation framework that is motivated by two objectives: 1) The Markov chain observed through the aggregation mapping should be Markov. 2) The aggregated chain should retain the temporal dependence structure of the original chain. We analyze our parameterized cost function and show that it contains previous cost functions as special cases, which we critically assess. Our simple optimization heuristic for deterministic aggregations characterizes the optimization landscape for different parameter values.
Koncar Philipp, Fuchs Alexandra, Hobisch Elisabeth, Geiger Bernhard, Scholger Martina, Helic Denis
2020
Spectator periodicals contributed to spreading the ideas of the Age of Enlightenment, a turning point in human history and the foundation of our modern societies. In this work, we study the spirit and atmosphere captured in the spectator periodicals about important social issues from the 18th century by analyzing text sentiment of those periodicals. Specifically, based on a manually annotated corpus of over 3 700 issues published in five different languages and over a period of more than one hundred years, we conduct a three-fold sentiment analysis: First, we analyze the development of sentiment over time as well as the influence of topics and narrative forms on sentiment. Second, we construct sentiment networks to assess the polarity of perceptions between different entities, including periodicals, places and people. Third, we construct and analyze sentiment word networks to determine topological differences between words with positive and negative polarity allowing us to make conclusions on how sentiment was expressed in spectator periodicals.Our results depict a mildly positive tone in spectator periodicals underlining the positive attitude towards important topics of the Age of Enlightenment, but also signaling stylistic devices to disguise critique in order to avoid censorship. We also observe strong regional variation in sentiment, indicating cultural and historic differences between countries. For example, while Italy perceived other European countries as positive role models, French periodicals were frequently more critical towards other European countries. Finally, our topological analysis depicts a weak overrepresentation of positive sentiment words corroborating our findings about a general mildly positive tone in spectator periodicals.We believe that our work based on the combination of the sentiment analysis of spectator periodicals and the extensive knowledge available from literary studies sheds interesting new light on these publications. Furthermore, we demonstrate the inclusion of sentiment analysis as another useful method in the digital humanist’s distant reading toolbox.
Fruhwirth Michael, Ropposch Christiana, Pammer-Schindler Viktoria
2020
Purpose: This paper synthesizes existing research on tools and methods that support data-driven business model innovation, and maps out relevant directions for future research.Design/methodology/approach: We have carried out a structured literature review and collected and analysed a respectable but not excessively large number of 33 publications, due to the comparatively emergent nature of the field.Findings: Current literature on supporting data-driven business model innovation differs in the types of contribution (taxonomies, patterns, visual tools, methods, IT tool and processes), the types of thinking supported (divergent and convergent) and the elements of the business models that are addressed by the research (value creation, value capturing and value proposition).Research implications: Our review highlights the following as relevant directions for future research. Firstly, most research focusses on supporting divergent thinking, i.e. ideation. However, convergent thinking, i.e. evaluating, prioritizing, and deciding, is also necessary. Secondly, the complete procedure of developing data-driven business models and also the development on chains of tools related to this have been under-investigated. Thirdly, scarcely any IT tools specifically support the development of data-driven business models. These avenues also highlight the necessity to integrate between research on specifics of data in business model innovation, on innovation management, information systems and business analytics.Originality/Value: This paper is the first to synthesize the literature on how to identify and develop data-driven
Dennerlein Sebastian, Tomberg Vladimir, Treasure-Jones, Tamsin, Theiler Dieter, Lindstaedt Stefanie , Ley Tobias
2020
PurposeIntroducing technology at work presents a special challenge as learning is tightly integrated with workplace practices. Current design-based research (DBR) methods are focused on formal learning context and often questioned for a lack of yielding traceable research insights. This paper aims to propose a method that extends DBR by understanding tools as sociocultural artefacts, co-designing affordances and systematically studying their adoption in practice.Design/methodology/approachThe iterative practice-centred method allows the co-design of cognitive tools in DBR, makes assumptions and design decisions traceable and builds convergent evidence by consistently analysing how affordances are appropriated. This is demonstrated in the context of health-care professionals’ informal learning, and how they make sense of their experiences. The authors report an 18-month DBR case study of using various prototypes and testing the designs with practitioners through various data collection means.FindingsBy considering the cognitive level in the analysis of appropriation, the authors came to an understanding of how professionals cope with pressure in the health-care domain (domain insight); a prototype with concrete design decisions (design insight); and an understanding of how memory and sensemaking processes interact when cognitive tools are used to elaborate representations of informal learning needs (theory insight).Research limitations/implicationsThe method is validated in one long-term and in-depth case study. While this was necessary to gain an understanding of stakeholder concerns, build trust and apply methods over several iterations, it also potentially limits this.Originality/valueBesides generating traceable research insights, the proposed DBR method allows to design technology-enhanced learning support for working domains and practices. The method is applicable in other domains and in formal learning.
Bhat Karthik Subramanya, Bachhiesl Udo, Feichtinger Gerald, Stigler Heinz
2020
India, as a ‘developing’ country, is in the middle of a unique situation of handling its energy transition towards carbon-free energy along with its continuous economic development. With respect to the agreed COP 21 and SDG 2030 targets, India has drafted several energy strategies revolving around clean renewable energy. With multiple roadblocks for development of large hydro power capacities within the country, the long-term renewable goals of India focus highly on renewable energy technologies like solar Photo-Voltaic (PV) and wind capacities. However, with a much slower rate of development in transmission infrastructure and the given situations of the regional energy systems in the Indian subcontinent, these significant changes in India could result in severe technical and economic consequences for the complete interconnected region. The presented investigations in this paper have been conducted using ATLANTIS_India, a unique techno-economic simulation model developed at the Institute of Electricity Economics and Energy Innovation/Graz University of Technology, designed for the electricity system in the Indian subcontinent region. The model covers the electricity systems of India, Bangladesh, Bhutan, Nepal, and Sri Lanka, and is used to analyse a scenario where around 118 GW of solar PV and wind capacity expansion is planned in India until the target year 2050. This paper presents the simulation approach as well as the simulated results and conclusions. The simulation results show the positive and negative technoeconomic impacts of the discussed strategy on the overall electricity system, while suggesting possible solutions.
Lex Elisabeth, Kowald Dominik, Schedl Markus
2020
In this paper, we address the problem of modeling and predicting the music genre preferences of users. We introduce a novel user modeling approach, BLLu, which takes into account the popularity of music genres as well as temporal drifts of user listening behavior. To model these two factors, BLLu adopts a psychological model that describes how humans access information in their memory. We evaluate our approach on a standard dataset of Last.fm listening histories, which contains fine-grained music genre information. To investigate performance for different types of users, we assign each user a mainstreaminess value that corresponds to the distance between the user’s music genre preferences and the music genre preferences of the (Last.fm) mainstream. We adopt BLLu to model the listening habits and to predict the music genre preferences of three user groups: listeners of (i) niche, low-mainstream music, (ii) mainstream music, and (iii) medium-mainstream music that lies in-between. Our results show that BLLu provides the highest accuracy for predicting music genre preferences, compared to five baselines: (i) group-based modeling, (ii) user-based collaborative filtering, (iii) item-based collaborative filtering, (iv) frequency-based modeling, and (v) recency-based modeling. Besides, we achieve the most substantial accuracy improvements for the low-mainstream group. We believe that our findings provide valuable insights into the design of music recommender systems
Lovric Mario, Šimić Iva, Godec Ranka, Kröll Mark, Beslic Ivan
2020
Narrow city streets surrounded by tall buildings are favorable to inducing a general effect of a “canyon” in which pollutants strongly accumulate in a relatively small area because of weak or inexistent ventilation. In this study, levels of nitrogen-oxide (NO2), elemental carbon (EC) and organic carbon (OC) mass concentrations in PM10 particles were determined to compare between seasons and different years. Daily samples were collected at one such street canyon location in the center of Zagreb in 2011, 2012 and 2013. By applying machine learning methods we showed seasonal and yearly variations of mass concentrations for carbon species in PM10 and NO2, as well as their covariations and relationships. Furthermore, we compared the predictive capabilities of five regressors (Lasso, Random Forest, AdaBoost, Support Vector Machine and Partials Least squares) with Lasso regression being the overall best performing algorithm. By showing the feature importance for each model, we revealed true predictors per target. These measurements and application of machine learning of pollutants were done for the first time at a street canyon site in the city of Zagreb, Croatia.
Arslanovic Jasmina, Ajana Löw, Lovric Mario, Kern Roman
2020
Previous studies have suggested that artistic (synchronized) swimming athletes might showeating disorders symptoms. However, systematic research on eating disorders in artistic swimming is limited and the nature and antecedents of the development of eating disorders in this specific population of athletes is still scarce. Hence, the aim of our research was to investigate the eating disorder symptoms in artistic swimming athletes using the EAT-26 instrument, and to examine the relation of the incidence and severity of these symptoms to body mass index and body image dissatisfaction. Furthermore, we wanted to compare artistic swimmers with athletes of a non-leanness (but also an aquatic) sport, therefore we also included a group of female water-polo athletes of the same age. The sample consisted of 36 artistic swimmers and 34 female waterpolo players (both aged 13-16). To test the presence of the eating disorder symptoms the EAT-26 was used. The Mann-Whitney U Test (MWU) was used to test for the differences in EAT-26 scores. The EAT-26 total score and the Dieting subscale (one of the three subscale) showed significant differences between the two groups. The median value for EAT-26 total score was higher in the artistic swimmers’ group (C = 11) than in the waterpolo players’ group (C = 8). A decision tree classifier was used to discriminate the artistic swimmers and female water polo players based on the features from the EAT26 and calculated features. The most discriminative features were the BMI, the dieting subscale and the habit of post-meal vomiting.Our results suggest that artistic swimmers, at their typical competing age, show higher risk of developing eating disorders than female waterpoloplayers and that they are also prone to dieting weight-control behaviors to achieve a desired weight. Furthermore, results indicate that purgative behaviors, such as binge eating or self-induced vomiting, might not be a common weight-control behavior among these athletes. The results corroborate the findings that sport environment in leanness sports might contribute to the development of eating disorders. The results are also in line with evidence that leanness sports athletes are more at risk for developing restrictive than purgative eating behaviors, as the latter usually do not contribute to body weight reduction. As sport environment factors in artistic swimming include judging criteria that emphasize a specific body shape and performance, it is important to raise the awareness of mental health risks that such environment might encourage.
Stanisavljevic Darko, Cemernek David, Gursch Heimo, Urak Günter, Lechner Gernot
2019
Additive manufacturing becomes a more and more important technology for production, mainly driven by the ability to realise extremely complex structures using multiple materials but without assembly or excessive waste. Nevertheless, like any high-precision technology additive manufacturing responds to interferences during the manufacturing process. These interferences – like vibrations – might lead to deviations in product quality, becoming manifest for instance in a reduced lifetime of a product or application issues. This study targets the issue of detecting such interferences during a manufacturing process in an exemplary experimental setup. Collection of data using current sensor technology directly on a 3D-printer enables a quantitative detection of interferences. The evaluation provides insights into the effectiveness of the realised application-oriented setup, the effort required for equipping a manufacturing system with sensors, and the effort for acquisition and processing the data. These insights are of practical utility for organisations dealing with additive manufacturing: the chosen approach for detecting interferences shows promising results, reaching interference detection rates of up to 100% depending on the applied data processing configuration.
Santos Tiago, Schrunner Stefan, Geiger Bernhard, Pfeiler Olivia, Zernig Anja, Kaestner Andre, Kern Roman
2019
Semiconductor manufacturing is a highly innovative branch of industry, where a high degree of automation has already been achieved. For example, devices tested to be outside of their specifications in electrical wafer test are automatically scrapped. In this paper, we go one step further and analyze test data of devices still within the limits of the specification, by exploiting the information contained in the analog wafermaps. To that end, we propose two feature extraction approaches with the aim to detect patterns in the wafer test dataset. Such patterns might indicate the onset of critical deviations in the production process. The studied approaches are: 1) classical image processing and restoration techniques in combination with sophisticated feature engineering and 2) a data-driven deep generative model. The two approaches are evaluated on both a synthetic and a real-world dataset. The synthetic dataset has been modeled based on real-world patterns and characteristics. We found both approaches to provide similar overall evaluation metrics. Our in-depth analysis helps to choose one approach over the other depending on data availability as a major aspect, as well as on available computing power and required interpretability of the results.
Silva Nelson, Madureira, Luis
2019
Uncover hidden suppliers and their complex relationships across the entire Supply Chain is quite complex. Unexpected disruptions, e.g. earthquakes, volcanoes, bankruptcies or nuclear disasters have a huge impact on major Supply Chain strategies. It is very difficult to predict the real impact of these disruptions until it is too late. Small, unknown suppliers can hugely impact the delivery of a product. Therefore, it is crucial to constantly monitor for problems with both direct and indirect suppliers.
di Sciascio Maria Cecilia, Strohmaier David, Errecalde Marcelo Luis, Veas Eduardo Enrique
2019
Digital libraries and services enable users to access large amounts of data on demand. Yet, quality assessment of information encountered on the Internet remains an elusive open issue. For example, Wikipedia, one of the most visited platforms on the Web, hosts thousands of user-generated articles and undergoes 12 million edits/contributions per month. User-generated content is undoubtedly one of the keys to its success but also a hindrance to good quality. Although Wikipedia has established guidelines for the “perfect article,” authors find it difficult to assert whether their contributions comply with them and reviewers cannot cope with the ever-growing amount of articles pending review. Great efforts have been invested in algorithmic methods for automatic classification of Wikipedia articles (as featured or non-featured) and for quality flaw detection. Instead, our contribution is an interactive tool that combines automatic classification methods and human interaction in a toolkit, whereby experts can experiment with new quality metrics and share them with authors that need to identify weaknesses to improve a particular article. A design study shows that experts are able to effectively create complex quality metrics in a visual analytics environment. In turn, a user study evidences that regular users can identify flaws, as well as high-quality content based on the inspection of automatic quality scores.
di Sciascio Maria Cecilia, Brusilovsky Peter, Trattner Christoph, Veas Eduardo Enrique
2019
Information-seeking tasks with learning or investigative purposes are usually referred to as exploratory search. Exploratory search unfolds as a dynamic process where the user, amidst navigation, trial and error, and on-the-fly selections, gathers and organizes information (resources). A range of innovative interfaces with increased user control has been developed to support the exploratory search process. In this work, we present our attempt to increase the power of exploratory search interfaces by using ideas of social search—for instance, leveraging information left by past users of information systems. Social search technologies are highly popular today, especially for improving ranking. However, current approaches to social ranking do not allow users to decide to what extent social information should be taken into account for result ranking. This article presents an interface that integrates social search functionality into an exploratory search system in a user-controlled way that is consistent with the nature of exploratory search. The interface incorporates control features that allow the user to (i) express information needs by selecting keywords and (ii) to express preferences for incorporating social wisdom based on tag matching and user similarity. The interface promotes search transparency through color-coded stacked bars and rich tooltips. This work presents the full series of evaluations conducted to, first, assess the value of the social models in contexts independent to the user interface, in terms of objective and perceived accuracy. Then, in a study with the full-fledged system, we investigated system accuracy and subjective aspects with a structural model revealing that when users actively interacted with all of its control features, the hybrid system outperformed a baseline content-based–only tool and users were more satisfied.
Geiger Bernhard, Koch Tobias
2019
In 1959, Rényi proposed the information dimension and the d-dimensional entropy to measure the information content of general random variables. This paper proposes a generalization of information dimension to stochastic processes by defining the information dimension rate as the entropy rate of the uniformly quantized stochastic process divided by minus the logarithm of the quantizer step size 1/m in the limit as m → ∞. It is demonstrated that the information dimension rate coincides with the rate-distortion dimension, defined as twice the rate-distortion function R(D) of the stochastic process divided by - log(D) in the limit as D ↓ 0. It is further shown that among all multivariate stationary processes with a given (matrixvalued) spectral distribution function (SDF), the Gaussian process has the largest information dimension rate and the information dimension rate of multivariate stationary Gaussian processes is given by the average rank of the derivative of the SDF. The presented results reveal that the fundamental limits of almost zero-distortion recovery via compressible signal pursuit and almost lossless analog compression are different in general.
Jorge Guerra Torres, Carlos Catania, Veas Eduardo Enrique
2019
Modern Network Intrusion Detection systems depend on models trained with up-to-date labeled data. Yet, the process of labeling a network traffic dataset is specially expensive, since expert knowledge is required to perform the annotations. Visual analytics applications exist that claim to considerably reduce the labeling effort, but the expert still needs to ponder several factors before issuing a label. And, most often the effect of bad labels (noise) in the final model is not evaluated. The present article introduces a novel active learning strategy that learns to predict labels in (pseudo) real-time as the user performs the annotation. The system called RiskID, presents several innovations: i) a set of statistical methods summarize the information, which is illustrated in a visual analytics application, ii) that interfaces with the active learning strategy forbuilding a random forest model as the user issues annotations; iii) the (pseudo) real-time predictions of the model are fed back visually to scaffold the traffic annotation task. Finally, iv) an evaluation framework is introduced that represents a complete methodology for evaluating active learning solutions, including resilience against noise.
Barreiros Carla, Pammer-Schindler Viktoria, Veas Eduardo Enrique
2019
We present a visual interface for communicating the internal state of a coffee machine via a tree metaphor. Nature-inspired representations have a positive impact on human well-being. We also hypothesize that representing the coffee machine asa tree stimulates emotional connection to it, which leads to better maintenance performance.The first study assessed the understandability of the tree representation, comparing it with icon-based and chart-based representations. An online survey with 25 participants indicated no significant mean error difference between representations.A two-week field study assessed the maintenance performance of 12 participants, comparing the tree representation with the icon-based representation. Based on 240 interactions with the coffee machine, we concluded that participants understood themachine states significantly better in the tree representation. Their comments and behavior indicated that the tree representation encouraged an emotional engagement with the machine. Moreover, the participants performed significantly more optional maintenance tasks with the tree representation.
Toller Maximilian, Santos Tiago, Kern Roman
2019
Season length estimation is the task of identifying the number of observations in the dominant repeating pattern of seasonal time series data. As such, it is a common pre-processing task crucial for various downstream applications. Inferring season length from a real-world time series is often challenging due to phenomena such as slightly varying period lengths and noise. These issues may, in turn, lead practitioners to dedicate considerable effort to preprocessing of time series data since existing approaches either require dedicated parameter-tuning or their performance is heavily domain-dependent. Hence, to address these challenges, we propose SAZED: spectral and average autocorrelation zero distance density. SAZED is a versatile ensemble of multiple, specialized time series season length estimation approaches. The combination of various base methods selected with respect to domain-agnostic criteria and a novel seasonality isolation technique, allow a broad applicability to real-world time series of varied properties. Further, SAZED is theoretically grounded and parameter-free, with a computational complexity of O(𝑛log𝑛), which makes it applicable in practice. In our experiments, SAZED was statistically significantly better than every other method on at least one dataset. The datasets we used for the evaluation consist of time series data from various real-world domains, sterile synthetic test cases and synthetic data that were designed to be seasonal and yet have no finite statistical moments of any order.
Stepputat Kendra, Kienreich Wolfgang, Dick Christopher S.
2019
With this article, we present the ongoing research project “Tango Danceability of Music in European Perspective” and the transdisciplinary research design it is built upon. Three main aspects of tango argentino are in focus—the music, the dance, and the people—in order to understand what is considered danceable in tango music. The study of all three parts involves computer-aided analysis approaches, and the results are examined within ethnochoreological and ethnomusicological frameworks. Two approaches are illustrated in detail to show initial results of the research model. Network analysis based on the collection of online tango event data and quantitative evaluation of data gathered by an online survey showed significant results, corroborating the hypothesis of gatekeeping effects in the shaping of musical preferences. The experiment design includes incorporation of motion capture technology into dance research. We demonstrate certain advantages of transdisciplinary approaches in the study of Intangible Cultural Heritage, in contrast to conventional studies based on methods from just one academic discipline.
Adolfo Ruiz Calleja, Dennerlein Sebastian, Kowald Dominik, Theiler Dieter, Lex Elisabeth, Tobias Ley
2019
In this paper, we propose the Social Semantic Server (SSS) as a service-based infrastructure for workplace andprofessional Learning Analytics (LA). The design and development of the SSS has evolved over 8 years, startingwith an analysis of workplace learning inspired by knowledge creation theories and its application in differentcontexts. The SSS collects data from workplace learning tools, integrates it into a common data model based ona semantically-enriched Artifact-Actor Network and offers it back for LA applications to exploit the data. Further,the SSS design promotes its flexibility in order to be adapted to different workplace learning situations. Thispaper contributes by systematizing the derivation of requirements for the SSS according to the knowledge creationtheories, and the support offered across a number of different learning tools and LA applications integrated to it.It also shows evidence for the usefulness of the SSS extracted from four authentic workplace learning situationsinvolving 57 participants. The evaluation results indicate that the SSS satisfactorily supports decision making indiverse workplace learning situations and allow us to reflect on the importance of the knowledge creation theoriesfor such analysis.
Renner Bettina, Wesiak Gudrun, Pammer-Schindler Viktoria, Prilla Michael, Müller Lars, Morosini Dalia, Mora Simone, Faltin Nils, Cress Ulrike
2019
Fruhwirth Michael, Breitfuß Gert, Müller Christiana
2019
Die Nutzung von Daten in Unternehmen zur Analyse und Beantwortung vielfältiger Fragestellungen ist “daily business”. Es steckt aber noch viel mehr Potenzial in Daten abseits von Prozessoptimierungen und Business Intelligence Anwendungen. Der vorliegende Beitrag gibt einen Überblick über die wichtigsten Aspekte bei der Transformation von Daten in Wert bzw. bei der Entwicklung datengetriebener Geschäftsmodelle. Dabei werden die Charakteristika von datengetriebenen Geschäftsmodellen und die benötigten Kompetenzen näher beleuchtet. Vier Fallbeispiele österreichischer Unternehmen geben Einblicke in die Praxis und abschließend werden aktuelle Herausforderungen und Entwicklungen diskutiert.
Clemens Bloechl, Rana Ali Amjad, Geiger Bernhard
2019
We present an information-theoretic cost function for co-clustering, i.e., for simultaneous clustering of two sets based on similarities between their elements. By constructing a simple random walk on the corresponding bipartite graph, our cost function is derived from a recently proposed generalized framework for information-theoretic Markov chain aggregation. The goal of our cost function is to minimize relevant information loss, hence it connects to the information bottleneck formalism. Moreover, via the connection to Markov aggregation, our cost function is not ad hoc, but inherits its justification from the operational qualities associated with the corresponding Markov aggregation problem. We furthermore show that, for appropriate parameter settings, our cost function is identical to well-known approaches from the literature, such as “Information-Theoretic Co-Clustering” by Dhillon et al. Hence, understanding the influence of this parameter admits a deeper understanding of the relationship between previously proposed information-theoretic cost functions. We highlight some strengths and weaknesses of the cost function for different parameters. We also illustrate the performance of our cost function, optimized with a simple sequential heuristic, on several synthetic and real-world data sets, including the Newsgroup20 and the MovieLens100k data sets.
Lovric Mario, Molero Perez Jose Manuel, Kern Roman
2019
The authors present an implementation of the cheminformatics toolkit RDKit in a distributed computing environment, Apache Hadoop. Together with the Apache Spark analytics engine, wrapped by PySpark, resources from commodity scalable hardware can be employed for cheminformatic calculations and query operations with basic knowledge in Python programming and understanding of the resilient distributed datasets (RDD). Three use cases of cheminfomatical computing in Spark on the Hadoop cluster are presented; querying substructures, calculating fingerprint similarity and calculating molecular descriptors. The source code for the PySpark‐RDKit implementation is provided. The use cases showed that Spark provides a reasonable scalability depending on the use case and can be a suitable choice for datasets too big to be processed with current low‐end workstations
Ross-Hellauer Anthony, Schmidt Birgit, Kramer Bianca
2018
As open access (OA) to publications continues to gather momentum, we should continuously question whether it is moving in the right direction. A novel intervention in this space is the creation of OA publishing platforms commissioned by funding organizations. Examples include those of the Wellcome Trust and the Gates Foundation, as well as recently announced initiatives from public funders like the European Commission and the Irish Health Research Board. As the number of such platforms increases, it becomes urgently necessary to assess in which ways, for better or worse, this emergent phenomenon complements or disrupts the scholarly communications landscape. This article examines ethical, organizational, and economic strengths and weaknesses of such platforms, as well as usage and uptake to date, to scope the opportunities and threats presented by funder OA platforms in the ongoing transition to OA. The article is broadly supportive of the aims and current implementations of such platforms, finding them a novel intervention which stands to help increase OA uptake, control costs of OA, lower administrative burden on researchers, and demonstrate funders’ commitment to fostering open practices. However, the article identifies key areas of concern about the potential for unintended consequences, including the appearance of conflicts of interest, difficulties of scale, potential lock-in, and issues of the branding of research. The article ends with key recommendations for future consideration which include a focus on open scholarly infrastructure.
Iacopo Vagliano, Franziska Günther, Mathias Heinz, Aitor Apaolaza, Irina Bienia, Breitfuß Gert, Till Blume, Chrysa Collyda, Fessl Angela, Sebastian Gottfried, Hasitschka Peter, Jasmin Kellermann, Thomas Köhler, Annalouise Maas, Vasileios Mezaris, Ahmed Saleh, Andrzej Skulimowski, Thalmann_TU Stefan, Markel Vigo, Wertner Alfred, Michael Wiese, Ansgar Scherp
2018
In the Big Data era, people can access vast amounts of information, but often lack the time, strategies and tools to efficiently extract the necessary knowledge from it. Research and innovation staff needs to effectively obtain an overview of publications, patents, funding opportunities, etc., to derive an innovation strategy. The MOVING platform enables its users to improve their information literacy by training how to exploit data mining methods in their daily research tasks. Through a novel integrated working and training environment, the platform supports the education of data-savvy information professionals and enables them to deal with the challenges of Big Data and open innovation.
Kowald Dominik
2018
Social tagging systems enable users to collaboratively assign freely chosen keywords (i.e.,tags) to resources (e.g., Web links). In order to support users in nding descriptive tags, tagrecommendation algorithms have been proposed. One issue of current state-of-the-art tagrecommendation algorithms is that they are often designed in a purely data-driven way andthus, lack a thorough understanding of the cognitive processes that play a role when peopleassign tags to resources. A prominent example is the activation equation of the cognitivearchitecture ACT-R, which formalizes activation processes in human memory to determineif a specic memory unit (e.g., a word or tag) will be needed in a specic context. It is theaim of this thesis to investigate if a cognitive-inspired approach, which models activationprocesses in human memory, can improve tag recommendations.For this, the relation between activation processes in human memory and usage prac-tices of tags is studied, which reveals that (i) past usage frequency, (ii) recency, and (iii)semantic context cues are important factors when people reuse tags. Based on this, acognitive-inspired tag recommendation approach termed BLLAC+MPr is developed based onthe activation equation of ACT-R. An extensive evaluation using six real-world folksonomydatasets shows that BLLAC+MPr outperforms current state-of-the-art tag recommendationalgorithms with respect to various evaluation metrics. Finally, BLLAC+MPr is utilized forhashtag recommendations in Twitter to demonstrate its generalizability in related areas oftag-based recommender systems. The ndings of this thesis demonstrate that activationprocesses in human memory can be utilized to improve not only social tag recommendationsbut also hashtag recommendations. This opens up a number of possible research strands forfuture work, such as the design of cognitive-inspired resource recommender systems
Lacic Emanuel, Traub Matthias, Duricic Tomislav, Haslauer Eva, Lex Elisabeth
2018
A challenge for importers in the automobile industry is adjusting to rapidly changing market demands. In this work, we describe a practical study of car import planning based on the monthly car registrations in Austria. We model the task as a data driven forecasting problem and we implement four different prediction approaches. One utilizes a seasonal ARIMA model, while the other is based on LSTM-RNN and both compared to a linear and seasonal baselines. In our experiments, we evaluate the 33 different brands by predicting the number of registrations for the next month and for the year to come.
Lassnig Markus, Stabauer Petra, Breitfuß Gert, Mauthner Katrin
2018
Zahlreiche Forschungsergebnisse im Bereich Geschäftsmodellinnovationenhaben gezeigt, dass über 90% aller Geschäftsmodelle der letzten50 Jahre aus einer Rekombination von bestehenden Konzepten entstanden sind.Grundsätzlich gilt das auch für digitale Geschäftsmodellinnovationen. Angesichtsder Breite potenzieller digitaler Geschäftsmodellinnovationen wollten die Autorenwissen, welche Modellmuster in der wirtschaftlichen Praxis welche Bedeutung haben.Deshalb wurde die digitale Transformation mit neuen Geschäftsmodellen ineiner empirischen Studie basierend auf qualitativen Interviews mit 68 Unternehmenuntersucht. Dabei wurden sieben geeignete Geschäftsmodellmuster identifiziert, bezüglichihres Disruptionspotenzials von evolutionär bis revolutionär klassifiziert undder Realisierungsgrad in den Unternehmen analysiert.Die stark komprimierte Conclusio lautet, dass das Thema Geschäftsmodellinnovationendurch Industrie 4.0 und digitale Transformation bei den Unternehmenangekommen ist. Es gibt jedoch sehr unterschiedliche Geschwindigkeiten in der Umsetzungund im Neuheitsgrad der Geschäftsmodellideen. Die schrittweise Weiterentwicklungvon Geschäftsmodellen (evolutionär) wird von den meisten Unternehmenbevorzugt, da hier die grundsätzliche Art und Weise des Leistungsangebots bestehenbleibt. Im Gegensatz dazu gibt es aber auch Unternehmen, die bereits radikale Änderungenvornehmen, die die gesamte Geschäftslogik betreffen. Entsprechend wird imvorliegenden Artikel ein Clustering von Geschäftsmodellinnovatoren vorgenommen – von Hesitator über Follower über Optimizer bis zu Leader in Geschäftsmodellinnovationen
Hasani-Mavriqi Ilire, Kowald Dominik, Helic Denis, Lex Elisabeth
2018
In this paper, we study the process of opinion dynamics and consensus building inonline collaboration systems, in which users interact with each other followingtheir common interests and their social proles. Specically, we are interested inhow users similarity and their social status in the community, as well as theinterplay of those two factors inuence the process of consensus dynamics. Forour study, we simulate the diusion of opinions in collaboration systems using thewell-known Naming Game model, which we extend by incorporating aninteraction mechanism based on user similarity and user social status. Weconduct our experiments on collaborative datasets extracted from the Web. Ourndings reveal that when users are guided by their similarity to other users, theprocess of consensus building in online collaboration systems is delayed. Asuitable increase of inuence of user social status on their actions can in turnfacilitate this process. In summary, our results suggest that achieving an optimalconsensus building process in collaboration systems requires an appropriatebalance between those two factors.
Lovric Mario
2018
Today's data amount is significantly increasing. A strong buzzword in research nowadays is big data.Therefore the chemistry student has to be well prepared for the upcoming age where he does not only rule the laboratories but is a modeler and data scientist as well. This tutorial covers the very basics of molecular modeling and data handling with the use of Python and Jupyter Notebook. It is the first in a series aiming to cover the relevant topics in machine learning, QSAR and molecular modeling, as well as the basics of Python programming
Rexha Andi, Kröll Mark, Ziak Hermann, Kern Roman
2018
The goal of our work is inspired by the task of associating segments of text to their real authors. In this work, we focus on analyzing the way humans judge different writing styles. This analysis can help to better understand this process and to thus simulate/ mimic such behavior accordingly. Unlike the majority of the work done in this field (i.e., authorship attribution, plagiarism detection, etc.) which uses content features, we focus only on the stylometric, i.e. content-agnostic, characteristics of authors.Therefore, we conducted two pilot studies to determine, if humans can identify authorship among documents with high content similarity. The first was a quantitative experiment involving crowd-sourcing, while the second was a qualitative one executed by the authors of this paper.Both studies confirmed that this task is quite challenging.To gain a better understanding of how humans tackle such a problem, we conducted an exploratory data analysis on the results of the studies. In the first experiment, we compared the decisions against content features and stylometric features. While in the second, the evaluators described the process and the features on which their judgment was based. The findings of our detailed analysis could (i) help to improve algorithms such as automatic authorship attribution as well as plagiarism detection, (ii) assist forensic experts or linguists to create profiles of writers, (iii) support intelligence applications to analyze aggressive and threatening messages and (iv) help editor conformity by adhering to, for instance, journal specific writing style.
Babić Sanja, Barišić Josip, Stipaničev Draženka, Repec Siniša, Lovric Mario, Malev Olga, Čož-Rakovac Rozalindra, Klobučar GIV
2018
Quantitative chemical analyses of 428 organic contaminants (OCs) confirmed the presence of 313 OCs in the sediment extracts from river Sava, Croatia. Pharmaceuticals were present in higher concentration than pesticides thus confirming their increasing threat to freshwater ecosystems. Toxicity evaluation of the sediment extracts from four locations (Jesenice, Rugvica, Galdovo and Lukavec) using zebrafish embryotoxicity test (ZET) accompanied with semi-quantitative histopathological analyses exhibited good correlation with cumulative number and concentrations of OCs at investigated sites (10,048.6, 15,222.8, 1,247.6, and 9,130.5 ng/g respectively) and proved its role as a good indicator of toxic potential of complex contaminant mixtures. Toxicity prediction of sediment extracts and sediment was assessed using Toxic unit (TU) approach and PBT (persistence, bioaccumulation and toxicity) ranking. Also, prior-knowledge informed chemical-gene interaction models were generated and graph mining approaches used to identify OCs and genes most likely to be influential in these mixtures. Predicted toxicity of sediment extracts (TUext) for sampled locations was similar to the results obtained by ZET and associated histopathology resulting in Rugvica sediment as being the most toxic, followed by Jesenice, Lukavec and Galdovo. Sediment TU (TUsed) favoured OCs with low octanol-water partition coefficient like herbicide glyphosate and antibiotics ciprofloxacin and sulfamethazine thus indicating locations containing higher concentrations of these OCs (Galdovo and Rugvica) as most toxic. Results suggest that comprehensive in silico sediment toxicity predictions advocate providing equal attention to organic contaminants with either very low or very high log Kow
Barreiros Carla, Veas Eduardo Enrique, Pammer-Schindler Viktoria
2018
This paper describes a novel visual metaphor to communicate sensor information of a connected device. The Internet of Things aims to extend every device with sensing and computing capabilities. A byproduct is that even domestic machines become increasingly complex, tedious to understand and maintain. This paper presents a prototype instrumenting a coffee machine with sensors. The machine streams the sensor data, which is picked up by an augmented reality application serving a nature metaphor. The nature metaphor, BioAR, represents the status derived from the coffee machine sensors in the features of a 3D virtual tree. The tree is meant to pass for a living proxy of the machine it represents. The metaphor, shown either with AR or a simple holographic display, reacts to the user manipulation of the machine and its workings. A first user study validates that the representation is correctly understood, and that it inspires affect for the machine. A second user study validates that the metaphor scales to a large number of machines.
Bassa Akim, Kröll Mark, Kern Roman
2018
Open Information Extraction (OIE) is the task of extracting relations fromtext without the need of domain speci c training data. Currently, most of the researchon OIE is devoted to the English language, but little or no research has been conductedon other languages including German. We tackled this problem and present GerIE, anOIE parser for the German language. Therefore we started by surveying the availableliterature on OIE with a focus on concepts, which may also apply to the Germanlanguage. Our system is built upon the output of a dependency parser, on which anumber of hand crafted rules are executed. For the evaluation we created two dedicateddatasets, one derived from news articles and one based on texts from an encyclopedia.Our system achieves F-measures of up to 0.89 for sentences that have been correctlypreprocessed.
di Sciascio Maria Cecilia, Sabol Vedran, Veas Eduardo Enrique
2017
Whenever users engage in gathering and organizing new information, searching and browsing activities emerge at the core of the exploration process. As the process unfolds and new knowledge is acquired, interest drifts occur inevitably and need to be accounted for. Despite the advances in retrieval and recommender algorithms, real-world interfaces have remained largely unchanged: results are delivered in a relevance-ranked list. However, it quickly becomes cumbersome to reorganize resources along new interests, as any new search brings new results. We introduce an interactive user-driven tool that aims at supporting users in understanding, refining, and reorganizing documents on the fly as information needs evolve. Decisions regarding visual and interactive design aspects are tightly grounded on a conceptual model for exploratory search. In other words, the different views in the user interface address stages of awareness, exploration, and explanation unfolding along the discovery process, supported by a set of text-mining methods. A formal evaluation showed that gathering items relevant to a particular topic of interest with our tool incurs in a lower cognitive load compared to a traditional ranked list. A second study reports on usage patterns and usability of the various interaction techniques within a free, unsupervised setting.
Ross-Hellauer Anthony, Deppe A., Schmidt B.
2017
Open peer review (OPR) is a cornerstone of the emergent Open Science agenda. Yet to date no large-scale survey of attitudes towards OPR amongst academic editors, authors, reviewers and publishers has been undertaken. This paper presents the findings of an online survey, conducted for the OpenAIRE2020 project during September and October 2016, that sought to bridge this information gap in order to aid the development of appropriate OPR approaches by providing evidence about attitudes towards and levels of experience with OPR. The results of this cross-disciplinary survey, which received 3,062 full responses, show the majority (60.3%) of respondents to be believe that OPR as a general concept should be mainstream scholarly practice (although attitudes to individual traits varied, and open identities peer review was not generally favoured). Respondents were also in favour of other areas of Open Science, like Open Access (88.2%) and Open Data (80.3%). Among respondents we observed high levels of experience with OPR, with three out of four (76.2%) reporting having taken part in an OPR process as author, reviewer or editor. There were also high levels of support for most of the traits of OPR, particularly open interaction, open reports and final-version commenting. Respondents were against opening reviewer identities to authors, however, with more than half believing it would make peer review worse. Overall satisfaction with the peer review system used by scholarly journals seems to strongly vary across disciplines. Taken together, these findings are very encouraging for OPR’s prospects for moving mainstream but indicate that due care must be taken to avoid a “one-size fits all” solution and to tailor such systems to differing (especially disciplinary) contexts. OPR is an evolving phenomenon and hence future studies are to be encouraged, especially to further explore differences between disciplines and monitor the evolution of attitudes.
Seifert Christin, Bailer Werner, Orgel Thomas, Gantner Louis, Kern Roman, Ziak Hermann, Petit Albin, Schlötterer Jörg, Zwicklbauer Stefan, Granitzer Michael
2017
The digitization initiatives in the past decades have led to a tremendous increase in digitized objects in the cultural heritagedomain. Although digitally available, these objects are often not easily accessible for interested users because of the distributedallocation of the content in different repositories and the variety in data structure and standards. When users search for culturalcontent, they first need to identify the specific repository and then need to know how to search within this platform (e.g., usageof specific vocabulary). The goal of the EEXCESS project is to design and implement an infrastructure that enables ubiquitousaccess to digital cultural heritage content. Cultural content should be made available in the channels that users habituallyvisit and be tailored to their current context without the need to manually search multiple portals or content repositories. Torealize this goal, open-source software components and services have been developed that can either be used as an integratedinfrastructure or as modular components suitable to be integrated in other products and services. The EEXCESS modules andcomponents comprise (i) Web-based context detection, (ii) information retrieval-based, federated content aggregation, (iii) meta-data definition and mapping, and (iv) a component responsible for privacy preservation. Various applications have been realizedbased on these components that bring cultural content to the user in content consumption and content creation scenarios. Forexample, content consumption is realized by a browser extension generating automatic search queries from the current pagecontext and the focus paragraph and presenting related results aggregated from different data providers. A Google Docs add-onallows retrieval of relevant content aggregated from multiple data providers while collaboratively writing a document. Theserelevant resources then can be included in the current document either as citation, an image, or a link (with preview) withouthaving to leave disrupt the current writing task for an explicit search in various content providers’ portals.
di Sciascio Maria Cecilia, Sabol Vedran, Veas Eduardo Enrique
2017
Whenever we gather or organize knowledge, the task of search-ing inevitably takes precedence. As exploration unfolds, it be-comes cumbersome to reorganize resources along new interests,as any new search brings new results. Despite huge advances inretrieval and recommender systems from the algorithmic point ofview, many real-world interfaces have remained largely unchanged:results appear in an infinite list ordered by relevance with respect tothe current query. We introduceuRank, a user-driven visual tool forexploration and discovery of textual document recommendations.It includes a view summarizing the content of the recommenda-tion set, combined with interactive methods for understanding, re-fining and reorganizing documents on-the-fly as information needsevolve. We provide a formal experiment showing thatuRankuserscan browse the document collection and efficiently gather items rel-evant to particular topics of interest with significantly lower cogni-tive load compared to traditional list-based representations.
Ross-Hellauer Anthony
2017
Background: “Open peer review” (OPR), despite being a major pillar of Open Science, has neither a standardized definition nor an agreed schema of its features and implementations. The literature reflects this, with numerous overlapping and contradictory definitions. While for some the term refers to peer review where the identities of both author and reviewer are disclosed to each other, for others it signifies systems where reviewer reports are published alongside articles. For others it signifies both of these conditions, and for yet others it describes systems where not only “invited experts” are able to comment. For still others, it includes a variety of combinations of these and other novel methods.Methods: Recognising the absence of a consensus view on what open peer review is, this article undertakes a systematic review of definitions of “open peer review” or “open review”, to create a corpus of 122 definitions. These definitions are systematically analysed to build a coherent typology of the various innovations in peer review signified by the term, and hence provide the precise technical definition currently lacking.Results: This quantifiable data yields rich information on the range and extent of differing definitions over time and by broad subject area. Quantifying definitions in this way allows us to accurately portray exactly how ambiguously the phrase “open peer review” has been used thus far, for the literature offers 22 distinct configurations of seven traits, effectively meaning that there are 22 different definitions of OPR in the literature reviewed.Conclusions: I propose a pragmatic definition of open peer review as an umbrella term for a number of overlapping ways that peer review models can be adapted in line with the aims of Open Science, including making reviewer and author identities open, publishing review reports and enabling greater participation in the peer review process.
Dragoni Mauro, Federici Marco, Rexha Andi
2017
One of the most important opinion mining research directions falls in the extraction ofpolarities referring to specific entities (aspects) contained in the analyzed texts. The detectionof such aspects may be very critical especially when documents come from unknowndomains. Indeed, while in some contexts it is possible to train domain-specificmodels for improving the effectiveness of aspects extraction algorithms, in others themost suitable solution is to apply unsupervised techniques by making such algorithmsdomain-independent. Moreover, an emerging need is to exploit the results of aspectbasedanalysis for triggering actions based on these data. This led to the necessityof providing solutions supporting both an effective analysis of user-generated contentand an efficient and intuitive way of visualizing collected data. In this work, we implementedan opinion monitoring service implementing (i) a set of unsupervised strategiesfor aspect-based opinion mining together with (ii) a monitoring tool supporting usersin visualizing analyzed data. The aspect extraction strategies are based on the use of semanticresources for performing the extraction of aspects from texts. The effectivenessof the platform has been tested on benchmarks provided by the SemEval campaign and have been compared with the results obtained by domain-adapted techniques.
Seitlinger Paul, Ley Tobias, Kowald Dominik, Theiler Dieter, Hasani-Mavriqi Ilire, Dennerlein Sebastian, Lex Elisabeth, Albert D.
2017
Creative group work can be supported by collaborative search and annotation of Web resources. In this setting, it is important to help individuals both stay fluent in generating ideas of what to search next (i.e., maintain ideational fluency) and stay consistent in annotating resources (i.e., maintain organization). Based on a model of human memory, we hypothesize that sharing search results with other users, such as through bookmarks and social tags, prompts search processes in memory, which increase ideational fluency, but decrease the consistency of annotations, e.g., the reuse of tags for topically similar resources. To balance this tradeoff, we suggest the tag recommender SoMe, which is designed to simulate search of memory from user-specific tag-topic associations. An experimental field study (N = 18) in a workplace context finds evidence of the expected tradeoff and an advantage of SoMe over a conventional recommender in the collaborative setting. We conclude that sharing search results supports group creativity by increasing the ideational fluency, and that SoMe helps balancing the evidenced fluency-consistency tradeoff.
Kaiser Rene_DB, Meixner Britta, Jäger Joscha
2017
Enabling interactive access to multimedia content and evaluating content-consumption behaviors and experiences involve several different research areas, which are covered at many different conferences. For four years, the Workshop on Interactive Content Consumption (WSICC) series offered a forum for combining interdisciplinary, comprehensive views, inspiring new discussions related to interactive multimedia. Here, the authors reflect on the outcome of the series.
Thalmann Stefan, Pammer-Schindler Viktoria
2017
Aktuelle Untersuchungen zeigen einerseits auf, dass der Mensch weiterhin eine zentrale Rolle in der Industrie spielt. Andererseits ist aber auch klar, dass die Zahl der direkt in der Produktion beschäftigten Mitarbeter sinken wird. Die Veränderung wird dahin gehen, dass der Mensch weniger gleichförmige Prozese bearbeitet, stattdessen aber in der Lage sein muss, sich schnell ändernden Arbeitstätigkeiten azupassen und individualisierte Fertigungsprozesse zu steuern. Die Reduktion der Mitarbeiter hat jedoch auch eine Reduktion von Redunanzen zur Folge. Dies führt dazu, dass dem Einzelnen mehr Verantwortung übertragen wird. Als Folge haben Fehlentscheidungen eine görßere Tragweite und bedeuten somit auch ein höheres Risikio. Der Erfolg einer Industrie 4.0 Kampagne wird daher im Wesentlichen von den Anpassungsfähigkeiten der Mitarbeiter abhängen.
Pammer-Schindler Viktoria, Fessl Angela, Weghofer Franz, Thalmann Stefan
2017
Die Digitalisierung der Industrie wird aktuell sehr stark aus technoogischer Sicht betrachtet. Aber auch für den Menschen ergebn sich vielfältige Herausforderungen in dieser veränderten Arbeitsumgebung. Sie betreffen hautsächlich das Lernen von benötigtem Wissen.
Pammer-Schindler Viktoria, Fessl Angela, Wesiak Gudrun, Feyertag Sandra, Rivera-Pelayo Verónica
2017
This paper presents a concept for in-app reflection guidance and its evaluation in four work-related field trials. By synthesizing across four field trials, we can show that computer-based reflection guidance can function in the workplace, in the sense of being accepted as technology, being perceived as useful and leading to reflective learning. This is encouraging for all endeavours aiming to transfer existing knowledge on reflection supportive technology from educational settings to the workplace. However,reflective learning in our studies was mostly visible to limited depth in textual entries made in the applications themselves; and proactive reflection guidance technology like prompts were often found to be disruptive. We offer these two issues as highly relevant questions for future research.
Pammer-Schindler Viktoria, Rivera-Pelayo Verónica, Fessl Angela, Müller Lars
2017
The benefits of self-tracking have been thoroughly investigated in private areas of life, like health or sustainable living, but less attention has been given to the impact and benefits of self-tracking in work-related settings. Through two field studies, we introduced and evaluated a mood self-tracking application in two call centers to investigate the role of mood self-tracking at work, as well as its impact on individuals and teams. Our studies indicate that mood self-tracking is accepted and can improve performance if the application is well integrated into the work processes and matches the management style. The results show that (i) capturing moods and explicitly relating them to work tasks facilitated reflection, (ii) mood self-tracking increased emotional awareness and this improved cohesion within teams, and (iii) proactive reactions by managers to trends and changes in team members’ mood were key for acceptance of reflection and correlated with measured improvements in work performance. These findings help to better understand the role and potential of self-tracking in work settings and further provide insights that guide future researchers and practitioners to design and introduce these tools in a workplace setting.
Topps David, Dennerlein Sebastian, Treasure-Jones Tamsin
2017
There is increasing interest in Barcamps and Unconferences as an educational approach during traditional medical education conferences. Ourgroup has now accumulated extensive experience in these formats over a number of years in different educational venues. We present asummary of observations and lessons learned about what works and what doesn’t.
Wilsdon James , Bar-Ilan Judit, Frodemann Robert, Lex Elisabeth, Peters Isabella , Wouters Paul
2017
Dennerlein Sebastian, Treasure-Jones Tamsin, Lex Elisabeth, Ley Tobias
2016
Background: Teamworking, within and acrosshealthcare organisations, is essential to deliverexcellent integrated care. Drawing upon an alternationof collaborative and cooperative phases, we exploredthis teamworking and respective technologicalsupport within UK Primary Care. Participants usedBits&Pieces (B&P), a sensemaking tool for tracedexperiences that allows sharing results and mutuallyelaborating them: i.e. cooperating and/orcollaborating.Summary of Work: We conducted a two month-longcase study involving six healthcare professionals. InB&P, they reviewed organizational processes, whichrequired the involvement of different professions ineither collaborative and/or cooperative manner. Weused system-usage data, interviews and qualitativeanalysis to understand the interplay of teamworkingpracticeand technology.Summary of Results: Within our analysis we mainlyidentified cooperation phases. In a f2f-meeting,professionals collaboratively identified subtasks andassigned individuals leading collaboration on them.However, these subtasks were undertaken asindividual sensemaking efforts and finally combined(i.e. cooperation). We found few examples ofreciprocal interpretation processes (i.e. collaboration):e.g. discussing problems during sensemaking ormonitoring other’s sensemaking-outcomes to makesuggestions.Discussion: These patterns suggest that collaborationin healthcare often helps to construct a minimalshared understanding (SU) of subtasks to engage incooperation, where individuals trust in other’scompetencies and autonomous completion. However,we also found that professionals with positivecollaboration history and deepened SU were willing toundertake subtasks collaboratively. It seems thatacquiring such deepened SU of concepts andmethods, leads to benefits that motivate professionalsto collaborate more.Conclusion: Healthcare is a challenging environmentrequiring interprofessional work across organisations.For effective teamwork, a deepened SU is crucial andboth cooperation and collaboration are required.However, we found a tendency of staff to rely mainlyon cooperation when working in teams and not fullyexplore benefits of collaboration.Take Home Messages: To maximise benefits ofinterprofessional working, tools for teamworkingshould support both cooperation and collaborationprocesses and scaffold the move between them
Silva Nelson, Caldera Christian, Krispel Ulrich, Eggeling Eva, Sunk Alexander, Reisinger Gerhard, Sihn Wilfried, Fellner Dieter W.
2016
Value stream mapping is a lean management method for analyzing and optimizing a series of events for production or services. Even today the first step in value stream analysis – the acquisition of the current state map – is still created using pen & paper by physically visiting the production line. We capture a digital representation of how manufacturing processes look like in reality. The manufacturing processes can be represented and efficiently analyzed for future production planning as a future state map by using a meta description together with a dependency graph. With VASCO we present a tool, which contributes to all parts of value stream analysis - from data acquisition, over analyzing, planning, comparison up to simulation of alternative future state maps.We call this a holistic approach for Value stream mapping including detailed analysis of lead time, productivity, space, distance, material disposal, energy and carbon dioxide equivalents – depending in a change of calculated direct product costs.
Hasani-Mavriqi Ilire, Geigl Florian, Pujari Suhbash Chandra, Lex Elisabeth, Helic Denis
2016
In this paper, we study the process of opinion dynamics and consensus building in online collaboration systems, in which users interact with each other following their common interests and their social profiles. Specifically, we are interested in how users similarity and their social status in the community, as well as the interplay of those two factors influence the process of consensus dynamics. For our study, we simulate the diffusion of opinions in collaboration systems using the well-known Naming Game model, which we extend by incorporating an interaction mechanism based on user similarity and user social status. We conduct our experiments on collaborative datasets extracted from the Web. Our findings reveal that when users are guided by their similarity to other users, the process of consensus building in online collaboration systems is delayed. A suitable increase of influence of user social status on their actions can in turn facilitate this process. In summary, our results suggest that achieving an optimal consensus building process in collaboration systems requires an appropriate balance between those two factors.
Fessl Angela, Pammer-Schindler Viktoria, Blunk Oliver, Prilla Michael
2016
Reflective learning has been established as a process that deepenslearning in both educational and work-related settings. We present a literaturereview on various approaches and tools (e.g., prompts, journals, visuals)providing guidance for facilitating reflective learning. Research consideredin this review coincides common understanding of reflective learning, hasapplied and evaluated a tool supporting reflection and presents correspondingresults. Literature was analysed with respect to timing of reflection, reflectionparticipants, type of reflection guidance, and results achieved regardingreflection. From this analysis, we were able to derive insights, guidelinesand recommendations for the design of reflection guidance functionality incomputing systems: (i) ensure that learners understand the purpose of reflectivelearning, (ii) combine reflective learning tools with reflective questions either inform of prompts or with peer-to-peer or group discussions, (iii) for work-relatedsettings consider the time with regard to when and how to motivate to reflect.
Trattner Christoph, Kuśmierczyk Tomasz, Nørvåg Kjetil
2016
Kopeinik Simone, Kowald Dominik, Hasani-Mavriqi Ilire, Lex Elisabeth
2016
Classic resource recommenders like Collaborative Filteringtreat users as just another entity, thereby neglecting non-linear user-resource dynamics that shape attention and in-terpretation. SUSTAIN, as an unsupervised human cate-gory learning model, captures these dynamics. It aims tomimic a learner’s categorization behavior. In this paper, weuse three social bookmarking datasets gathered from Bib-Sonomy, CiteULike and Delicious to investigate SUSTAINas a user modeling approach to re-rank and enrich Collab-orative Filtering following a hybrid recommender strategy.Evaluations against baseline algorithms in terms of recom-mender accuracy and computational complexity reveal en-couraging results. Our approach substantially improves Col-laborative Filtering and, depending on the dataset, success-fully competes with a computationally much more expen-sive Matrix Factorization variant. In a further step, we ex-plore SUSTAIN’s dynamics in our specific learning task andshow that both memorization of a user’s history and clus-tering, contribute to the algorithm’s performance. Finally,we observe that the users’ attentional foci determined bySUSTAIN correlate with the users’ level of curiosity, iden-tified by the SPEAR algorithm. Overall, the results ofour study show that SUSTAIN can be used to efficientlymodel attention-interpretation dynamics of users and canhelp improve Collaborative Filtering for resource recommen-dations.
Kraker Peter, Kittel Christopher, Enkhbayar Asuraa
2016
The goal of Open Knowledge Maps is to create a visual interface to the world’s scientific knowledge. The base for this visual interface consists of so-called knowledge maps, which enable the exploration of existing knowledge and the discovery of new knowledge. Our open source knowledge mapping software applies a mixture of summarization techniques and similarity measures on article metadata, which are iteratively chained together. After processing, the representation is saved in a database for use in a web visualization. In the future, we want to create a space for collective knowledge mapping that brings together individuals and communities involved in exploration and discovery. We want to enable people to guide each other in their discovery by collaboratively annotating and modifying the automatically created maps.
Kraker Peter, Dennerlein Sebastian, Dörler, D, Ferus, A, Gutounig Robert, Heigl, F., Kaier, C., Rieck Katharina, Šimukovic, E., Vignoli Michela
2016
Between April 2015 and June 2016, members of the Open Access Network Aus- tria (OANA) working group “Open Access and Scholarly Communication” met in Vienna to discuss a fundamental reform of the scholarly communication system.By scholarly communication we mean the processes of producing, reviewing, organising, disseminating and preserving scholarly knowledge1. Scholarly communication does not only concern researchers, but also society at large, especially students, educators, policy makers, public administrators, funders, librarians, journalists, practitioners, publishers, public and private organisations, and interested citizens.
Trattner Christoph, Kowald Dominik, Seitlinger Paul, Ley Tobias
2016
Several successful tag recommendation mechanisms have been developed, including algorithms built upon Collaborative Filtering, Tensor Factorization, graph-based and simple "most popular tags" approaches. From an economic perspective, the latter approach has been convincing since calculating frequencies is computationally efficient and effective with respect to different recommender evaluation metrics. In this paper, we introduce a tag recommendation algorithm that mimics the way humans draw on items in their long-term memory in order to extend these conventional "most popular tags" approaches. Based on a theory of human memory, the approach estimates a tag's reuse probability as a function of usage frequency and recency in the user's past (base-level activation) as well as of the current semantic context (associative component).Using four real-world folksonomies gathered from bookmarks in BibSonomy, CiteULike, Delicious and Flickr, we show how refining frequency-based estimates by considering recency and semantic context outperforms conventional "most popular tags" approaches and another existing and very effective but less theory-driven, time-dependent recommendation mechanism. By combining our approach with a simple resource-specific frequency analysis, our algorithm outperforms other well-established algorithms, such as Collaborative Filtering, FolkRank and Pairwise Interaction Tensor Factorization with respect to recommender accuracy and runtime. We conclude that our approach provides an accurate and computationally efficient model of a user's temporal tagging behavior. Moreover, we demonstrate how effective principles of recommender systems can be designed and implemented if human memory processes are taken into account.
Simon Jörg Peter, Schmidt Peter, Pammer-Schindler Viktoria
2016
Synchronisation algorithms are central to collaborative editing software. As collaboration is increasingly mediated by mobile devices, the energy efficiency for such algorithms is interest to a wide community of application developers. In this paper we explore the differential synchronisation (diffsync) algorithm with respect to energy consumption on mobile devices. Discussions within this paper are based on real usage data of PDF annotations via the Mendeley iOS app, which requires realtime synchronisation. We identify three areas for optimising diffsync: a.) Empty cycles in which no changes need to be processed b.) tail energy by adapting cycle intervals and c.) computational complexity. Following these considerations, we propose a push-based diffsync strategy in which synchronisation cycles are triggered when a device connects to the network or when a device is notified of changes.
Kraker Peter, Peters Isabella, Lex Elisabeth, Gumpenberger Christian , Gorraiz Juan
2016
In this study, we explore the citedness of research data, its distribution overtime and its relation to the availability of a digital object identifier (DOI) in the ThomsonReuters database Data Citation Index (DCI). We investigate if cited research data ‘‘im-pacts’’ the (social) web, reflected by altmetrics scores, and if there is any relationshipbetween the number of citations and the sum of altmetrics scores from various social mediaplatforms. Three tools are used to collect altmetrics scores, namely PlumX, ImpactStory,and Altmetric.com, and the corresponding results are compared. We found that out of thethree altmetrics tools, PlumX has the best coverage. Our experiments revealed thatresearch data remain mostly uncited (about 85 %), although there has been an increase inciting data sets published since 2008. The percentage of the number of cited research datawith a DOI in DCI has decreased in the last years. Only nine repositories are responsible for research data with DOIs and two or more citations. The number of cited research datawith altmetrics ‘‘foot-prints’’ is even lower (4–9 %) but shows a higher coverage ofresearch data from the last decade. In our study, we also found no correlation between thenumber of citations and the total number of altmetrics scores. Yet, certain data types (i.e.survey, aggregate data, and sequence data) are more often cited and also receive higheraltmetrics scores. Additionally, we performed citation and altmetric analyses of allresearch data published between 2011 and 2013 in four different disciplines covered by theDCI. In general, these results correspond very well with the ones obtained for research datacited at least twice and also show low numbers in citations and in altmetrics. Finally, weobserved that there are disciplinary differences in the availability and extent of altmetricsscores.
Santos Patricia, Dennerlein Sebastian, Theiler Dieter, Cook John, Treasure-Jones Tamsin, Holley Debbie, Kerr Micky , Atwell Graham, Kowald Dominik, Lex Elisabeth
2016
Social learning networks enable the sharing, transfer and enhancement of knowledge in the workplace that builds the ground to exchange informal learning practices. In this work, three healthcare networks are studied in order to understand how to enable the building, maintaining and activation of new contacts at work and the exchange of knowledge between them. By paying close attention to the needs of the practitioners, we aimed to understand how personal and social learning could be supported by technological services exploiting social networks and the respective traces reflected in the semantics. This paper presents a case study reporting on the results of two co-design sessions and elicits requirements showing the importance of scaffolding strategies in personal and shared learning networks. Besides, the significance of these strategies to aggregate trust among peers when sharing resources and decision-support when exchanging questions and answers. The outcome is a set of design criteria to be used for further technical development for a social tool. We conclude with the lessons learned and future work.
Yusuke Fukazawa, Kröll Mark, Strohmaier M., Ota Jun
2016
Task-models concretize general requests to support users in real-world scenarios. In this paper, we present an IR based algorithm (IRTML) to automate the construction of hierarchically structured task-models. In contrast to other approaches, our algorithm is capable of assigning general tasks closer to the top and specific tasks closer to the bottom. Connections between tasks are established by extending Turney’s PMI-IR measure. To evaluate our algorithm, we manually created a ground truth in the health-care domain consisting of 14 domains. We compared the IRTML algorithm to three state-of-the-art algorithms to generate hierarchical structures, i.e. BiSection K-means, Formal Concept Analysis and Bottom-Up Clustering. Our results show that IRTML achieves a 25.9% taxonomic overlap with the ground truth, a 32.0% improvement over the compared algorithms.
2015
Fall detection is a classical use case for mobile phone sensing.Nonetheless, no open dataset exists that could be used totrain, test and compare fall detection algorithms.We present a dataset for mobile phone sensing-based fall detection.The dataset contains both accelerometer and gyroscopedata. Data were labelled with four types of falls(e.g., “stumbling”) and ten types of non-fall activities (e.g.,“sit down”). The dataset was collected with martial artistswho simulated falls. We used five different state-of-the-artAndroid smartphone models worn on the hip in a small bag.Due to the datasets properties of using multiple devices andbeing labelled with multiple fall- and non-fall categories, weargue that it is suitable to serve as benchmark dataset.
2015
Recent research has unveiled the importance of online social networks for improving the quality of recommender systems and encouraged the research community to investigate better ways of exploiting the social information for recommendations. To contribute to this sparse field of research, in this paper we exploit users’ interactions along three data sources (marketplace, social network and location-based) to assess their performance in a barely studied domain: recommending products and domains of interests (i.e., product categories) to people in an online marketplace environment. To that end we defined sets of content- and network-based user similarity features for each data source and studied them isolated using an user-based Collaborative Filtering (CF) approach and in combination via a hybrid recommender algorithm, to assess which one provides the best recommendation performance. Interestingly, in our experiments conducted on a rich dataset collected from SecondLife, a popular online virtual world, we found that recommenders relying on user similarity features obtained from the social network data clearly yielded the best results in terms of accuracy in case of predicting products, whereas the features obtained from the marketplace and location-based data sources also obtained very good results in case of predicting categories. This finding indicates that all three types of data sources are important and should be taken into account depending on the level of specialization of the recommendation task.
2015
We assume that recommender systems are more successful, when they are based on a thorough understanding of how people process information. In the current paper we test this assumption in the context of social tagging systems. Cognitive research on how people assign tags has shown that they draw on two interconnected levels of knowledge in their memory: on a conceptual level of semantic fields or LDA topics, and on a lexical level that turns patterns on the semantic level into words. Another strand of tagging research reveals a strong impact of time-dependent forgetting on users' tag choices, such that recently used tags have a higher probability being reused than "older" tags. In this paper, we align both strands by implementing a computational theory of human memory that integrates the two-level conception and the process of forgetting in form of a tag recommender. Furthermore, we test the approach in three large-scale social tagging datasets that are drawn from BibSonomy, CiteULike and Flickr. As expected, our results reveal a selective effect of time: forgetting is much more pronounced on the lexical level of tags. Second, an extensive evaluation based on this observation shows that a tag recommender interconnecting the semantic and lexical level based on a theory of human categorization and integrating time-dependent forgetting on the lexical level results in high accuracy predictions and outperforms other wellestablished algorithms, such as Collaborative Filtering, Pairwise Interaction Tensor Factorization, FolkRank and two alternative time-dependent approaches. We conclude that tag recommenders will benefit from going beyond the manifest level of word co-occurrences, and from including forgetting processes on the lexical level.
2015
In this paper, we introduce a tag recommendation algorithm that mimics the way humans draw on items in their long-term memory. Based on a theory of human memory, the approach estimates a tag's probability being applied by a particular user as a function of usage frequency and recency of the tag in the user's past. This probability is further refined by considering the in uence of the current semantic context of the user's tagging situation. Using three real-world folksonomies gathered from bookmarks in BibSonomy, CiteULike and Flickr, we show how refining frequency-based estimates by considering usage recency and contextual in uence outperforms conventional "most popular tags" approaches and another existing and very effective but less theory-driven, time-dependent recommendation mechanism. By combining our approach with a simple resource-specific frequency analysis, our algorithm outperforms other well-established algorithms, such as FolkRank, Pairwise Interaction Tensor Factorization and Collaborative Filtering. We conclude that our approach provides an accurate and computationally efficient model of a user's temporal tagging behavior. We demonstrate how effective principles of recommender systems can be designed and implemented if human memory processes are taken into account.
Tatzgern Markus, Grasset Raphael, Veas Eduardo Enrique, Schmalstieg Dieter
2015
Augmented reality (AR) enables users to retrieve additional information about real world objects and locations. Exploring such location-based information in AR requires physical movement to different viewpoints, which may be tiring and even infeasible when viewpoints are out of reach. In this paper, we present object-centric exploration techniques for handheld AR that allow users to access information freely using a virtual copy metaphor. We focus on the design of techniques that allow the exploration of large real world objects. We evaluated our interfaces in a series of studies in controlled conditions and compared them to a 3D map interface, which is a more common method for accessing location-based information. Based on our findings, we put forward design recommendations that should be considered by future generations of location-based AR browsers, 3D tourist guides or situated urban planning.
Parra Denis, Gomez M., Hutardo D., Wen X., Lin Yu-Ru, Trattner Christoph
2015
Twitter is often referred to as a backchannel for conferences. While the main conference takes place in a physicalsetting, on-site and off-site attendees socialize, introduce new ideas or broadcast information by microblogging on Twitter.In this paper we analyze scholars’ Twitter usage in 16 Computer Science conferences over a timespan of five years. Ourprimary finding is that over the years there are differences with respect to the uses of Twitter, with an increase ofinformational activity (retweets and URLs), and a decrease of conversational usage (replies and mentions), which alsoimpacts the network structure – meaning the amount of connected components – of the informational and conversationalnetworks. We also applied topic modeling over the tweets’ content and found that when clustering conferences accordingto their topics the resulting dendrogram clearly reveals the similarities and differences of the actual research interests ofthose events. Furthermore, we also analyzed the sentiment of tweets and found persistent differences among conferences.It also shows that some communities consistently express messages with higher levels of emotions while others do it in amore neutral manner. Finally, we investigated some features that can help predict future user participation in the onlineTwitter conference activity. By casting the problem as a classification task, we created a model that identifies factors thatcontribute to the continuing user participation. Our results have implications for research communities to implementstrategies for continuous and active participation among members. Moreover, our work reveals the potential for the useof information shared on Twitter in order to facilitate communication and cooperation among research communities, byproviding visibility to new resources or researchers from relevant but often little known research communities.
Kraker Peter
2015
In this paper, I present the evaluation of a novel knowledge domain visualization of educational technology. The interactive visualization is based on readership patterns in the online reference management system Mendeley. It comprises of 13 topic areas, spanning psychological, pedagogical, and methodological foundations, learning methods and technologies, and social and technological developments. The visualization was evaluated with (1) a qualitative comparison to knowledge domain visualizations based on citations, and (2) expert interviews. The results show that the co-readership visualization is a recent representation of pedagogical and psychological research in educational technology. Furthermore, the co-readership analysis covers more areas than comparable visualizations based on co-citation patterns. Areas related to computer science, however, are missing from the co-readership visualization and more research is needed to explore the interpretations of size and placement of research areas on the map.
Trattner Christoph, Steurer Michael
2015
Existing approaches to identify the tie strength between users involve typically only one type of network. To date, no studies exist that investigate the intensity of social relations and in particular partnership between users across social networks. To fill this gap in the literature, we studied over 50 social proximity features to detect the tie strength of users defined as partnership in two different types of networks: location-based and online social networks. We compared user pairs in terms of partners and non-partners and found significant differences between those users. Following these observations, we evaluated the social proximity of users via supervised and unsupervised learning approaches and establish that location-based social networks have a great potential for the identification of a partner relationship. In particular, we established that location-based social networks and correspondingly induced features based on events attended by users could identify partnership with 0.922 AUC, while online social network data had a classification power of 0.892 AUC. When utilizing data from both types of networks, a partnership could be identified to a great extent with 0.946 AUC. This article is relevant for engineers, researchers and teachers who are interested in social network analysis and mining.
Lin Yi-ling, Trattner Christoph, Brusilovsky Peter , He Daqing
2015
Crowdsourcing has been emerging to harvest social wisdom from thousands of volunteers to perform series of tasks online. However, little research has been devoted to exploring the impact of various factors such as the content of a resource or crowdsourcing interface design to user tagging behavior. While images’ titles and descriptions are frequently available in image digital libraries, it is not clear whether they should be displayed to crowdworkers engaged in tagging. This paper focuses on offering an insight to the curators of digital image libraries who face this dilemma by examining (i) how descriptions influence the user in his/her tagging behavior and (ii) how this relates to the (a) nature of the tags, (b) the emergent folksonomy, and (c) the findability of the images in the tagging system. We compared two different methods for collecting image tags from Amazon’s Mechanical Turk’s crowdworkers – with and without image descriptions. Several properties of generated tags were examined from different perspectives: diversity, specificity, reusability, quality, similarity, descriptiveness, etc. In addition, the study was carried out to examine the impact of image description on supporting users’ information seeking with a tag cloud interface. The results showed that the properties of tags are affected by the crowdsourcing approach. Tags from the “with description” condition are more diverse and more specific than tags from the “without description” condition, while the latter has a higher tag reuse rate. A user study also revealed that different tag sets provided different support for search. Tags produced “with description” shortened the path to the target results, while tags produced without description increased user success in the search task
Lex Elisabeth, Dennerlein Sebastian
2015
Today's complex scientific problems often require interdisciplinary, team-oriented approaches: the expertise of researchers from different disciplines is needed to collaboratively reach a solution. Interdisciplinary teams yet face many challenges such as differences in research practice, terminology, communication , and in the usage of tools. In this paper, we therefore study concrete mechanisms and tools of two real-world scientific projects with the aim to examine their efficacy and influence on interdisciplinary teamwork. For our study, we draw upon Bronstein's model of interdisciplinary collaboration. We found that it is key to use suitable environments for communication and collaboration, especially when teams are geographically distributed. Plus, the willingness to share (domain) knowledge is not a given and requires strong common goals and incentives. Besides, structural barriers such as financial aspects can hinder interdisciplinary work, especially in applied, industry funded research. Furthermore, we observed a kind of cold-start problem in interdisciplinary collaboration, when there is no work history and when the disciplines are rather different, e.g. in terms of wording. HowTo: Scientific Work in Interdisciplinary and Distributed Teams (PDF Download Available). Available from: https://www.researchgate.net/publication/282813815_HowTo_Scientific_Work_in_Interdisciplinary_and_Distributed_Teams [accessed Jul 13, 2017].
Kraker Peter, Schlögl C. , Jack K., Lindstaedt Stefanie
2015
Given the enormous amount of scientific knowledgethat is produced each and every day, the need for better waysof gaining – and keeping – an overview of research fields isbecoming more and more apparent. In a recent paper publishedin the Journal of Informetrics [1], we analyze the adequacy andapplicability of readership statistics recorded in social referencemanagement systems for creating such overviews. First, weinvestigated the distribution of subject areas in user librariesof educational technology researchers on Mendeley. The resultsshow that around 69% of the publications in an average userlibrary can be attributed to a single subject area. Then, we usedco-readership patterns to map the field of educational technology.The resulting knowledge domain visualization, based on the mostread publications in this field on Mendeley, reveals 13 topicareas of educational technology research. The visualization isa recent representation of the field: 80% of the publicationsincluded were published within ten years of data collection. Thecharacteristics of the readers, however, introduce certain biasesto the visualization. Knowledge domain visualizations based onreadership statistics are therefore multifaceted and timely, but itis important that the characteristics of the underlying sample aremade transparent.
Buschmann Katrin, Kasberger Stefan, Mayer Katja, Reckling Falk, Rieck Katharina, Vignoli Michela, Kraker Peter
2015
Insbesondere in den letzten zwei Jahren hat Österreichim Bereich Open Science, vor allem was Open Accessund Open Data betrifft, nennenswerte Fortschritte gemacht.Die Gründung des Open Access Networks Austria(OANA) und das Anfang 2014 gestartete Projekt e-InfrastructuresAustria können als wichtige Grundsteine fürden Ausbau einer österreichischen Open-Science-Landschaftgesehen werden. Auch das österreichische Kapitelder Open Knowledge Foundation leistet in den BereichenOpen Science Praxis- und Bewusstseinsbildung grundlegendeArbeit. Unter anderem bilden diese Initiativendie Grundlage für den Aufbau einer nationalen Open-Access-Strategie sowie einer ganz Österreich abdeckendenInfrastruktur für Open Access und Open (Research) Data.Dieser Beitrag gibt einen Überblick über diese und ähnlichenationale sowie lokale Open-Science-Projekte und-Initiativen und einen Ausblick in die mögliche Zukunftvon Open Science in Österreich.
Kraker Peter, Lindstaedt Stefanie , Schlögl C., Jack K.
2015
In this paper, we analyze the adequacy and applicability of readership statistics recorded in social reference management systems for creating knowledge domain visualizations. First, we investigate the distribution of subject areas in user libraries of educational technology researchers on Mendeley. The results show that around 69% of the publications in an average user library can be attributed to a single subject area. Then, we use co-readership patterns to map the field of educational technology. The resulting visualization prototype, based on the most read publications in this field on Mendeley, reveals 13 topic areas of educational technology research. The visualization is a recent representation of the field: 80% of the publications included were published within ten years of data collection. The characteristics of the readers, however, introduce certain biases to the visualization. Knowledge domain visualizations based on readership statistics are therefore multifaceted and timely, but it is important that the characteristics of the underlying sample are made transparent.
Mutlu Belgin, Veas Eduardo Enrique, Trattner Christoph
2015
Visualizations have a distinctive advantage when dealing with the information overload problem: since theyare grounded in basic visual cognition, many people understand them. However, creating the appropriaterepresentation requires specific expertise of the domain and underlying data. Our quest in this paper is tostudy methods to suggest appropriate visualizations autonomously. To be appropriate, a visualization hasto follow studied guidelines to find and distinguish patterns visually, and encode data therein. Thus, a visu-alization tells a story of the underlying data; yet, to be appropriate, it has to clearly represent those aspectsof the data the viewer is interested in. Which aspects of a visualization are important to the viewer? Canwe capture and use those aspects to recommend visualizations? This paper investigates strategies to recom-mend visualizations considering different aspects of user preferences. A multi-dimensional scale is used toestimate aspects of quality for charts for collaborative filtering. Alternatively, tag vectors describing chartsare used to recommend potentially interesting charts based on content. Finally, a hybrid approach combinesinformation on what a chart is about (tags) and how good it is (ratings). We present the design principlesbehindVizRec, our visual recommender. We describe its architecture, the data acquisition approach with acrowd sourced study, and the analysis of strategies for visualization recommendation
Fessl Angela, Bratic Marina, Pammer-Schindler Viktoria
2014
A continuous learning solution was sought which allows strokenurses to keep the vast body of theoretical knowledge fresh, stay up-to-datewith new knowledge, and relate theoretical knowledge to practical experience.Based on the theoretical background of learning in the medical domain,reflective and game-based learning, we carried out a user-oriented designprocess that involved a focus group and a design workshop. In this process, aquiz that includes both content-based and reflection questions was identified asa viable means of transportation for theoretical knowledge. In this paper wepresent the result of trialling a quiz with both content-based and metacognitive(reflective) questions in two settings: In one trial the quiz was used by nursesas part of a qualification programme for stroke nurses, in the second trial bynurses outside such a formal continuous learning setting. Both trials weresuccessful in terms of user acceptance, user satisfaction and learning. Beyondthis success report, we discuss barriers to integrating a quiz into work processeswithin an emergency ward such as a stroke unit.
Breitweiser Christian, Terbu Oliver, Holzinger Andreas, Brunner Clemens, Lindstaedt Stefanie , Müller-Putz Gernot
2013
We developed an iOS based application called iScope to monitor biosignals online. iScope is able to receive different signal types via a wireless network connection and is able to present them in the time or the frequency domain. Thus it is possible to inspect recorded data immediately during the recording process and detect potential artifacts early without the need to carry around heavy equipment like laptops or complete PC workstations. The iScope app has been tested during various measurements on the iPhone 3GS as well as on the iPad 1 and is fully functional.
Drachsler Hendrik, Verbert Katrien, Manouselis Nikos, Vuorikari Riina, Wolpers Martin, Lindstaedt Stefanie
2012
Technology Enhanced Learning is undergoing a significant shift in paradigm towards more data driven systems that will make educational systems more transparent and predictable. Data science and data-driven tools will change the evaluation of educational practice and didactical interventions for individual learners and educational institutions. We summarise these developments and new challenges in the preface of this Special Issue under the keyword dataTEL that stands for ‘Data-Supported Technology-Enhanced Learning’.
Pammer-Schindler Viktoria, Kump Barbara, Lindstaedt Stefanie
2012
Collaborative tagging platforms allow users to describe resources with freely chosen keywords, so called tags. The meaning of a tag as well as the precise relation between a tag and the tagged resource are left open for interpretation to the user. Although human users mostly have a fair chance at interpreting this relation, machines do not. In this paper we study the characteristics of the problem to identify descriptive tags, i.e. tags that relate to visible objects in a picture. We investigate the feasibility of using a tag-based algorithm, i.e. an algorithm that ignores actual picture content, to tackle the problem. Given the theoretical feasibility of a well-performing tag-based algorithm, which we show via an optimal algorithm, we describe the implementation and evaluation of a WordNet-based algorithm as proof-of-concept. These two investigations lead to the conclusion that even relatively simple and fast tag-based algorithms can yet predict human ratings of which objects a picture shows. Finally, we discuss the inherent difficulty both humans and machines have when deciding whether a tag is descriptive or not. Based on a qualitative analysis, we distinguish between definitional disagreement, difference in knowledge, disambiguation and difference in perception as reasons for disagreement between raters.
Lindstaedt Stefanie , Kump Barbara, Rath Andreas S.
2011
Within this chapter we first outline the important role learning plays within knowledge work and its impact on productivity. As a theoretical background we introduce the paradigm of Work-Integrated Learning (WIL) which conceptualizes informal learning at the workplace and takes place tightly intertwined with the execution of work tasks. Based on a variety of in-depth knowledge work studies we identify key requirements for the design of work-integrated learning support. Our focus is on providing learning support during the execution of work tasks (instead of beforehand), within the work environment of the user (instead of within a separate learning system), and by repurposing content for learning which was not originally intended for learning (instead of relying on the expensive manual creation of learning material). In order to satisfy these requirements we developed a number of context-aware knowledge services. These services integrate semantic technologies with statistical approaches which perform well in the face of uncertainty. These hybrid knowledge services include the automatic detection of a user’s work task, the ‘inference’ of the user’s competencies based on her past activities, context-aware recommendation of content and colleagues, learning opportunities, etc. A summary of a 3 month in-depth summative workplace evaluation at three testbed sites concludes the chapter.
Erdmann Michael, Hansch Daniel, Pammer-Schindler Viktoria, Rospocher Marco, Ghidini Chiara, Lindstaedt Stefanie , Serafini Luciano
2011
This chapter describes some extensions to and applications of the Semantic MediaWiki. It complements the discussion of the SMW in Chap. 3. Semantic enterprise wikis combine the strengths of traditional content management systems, databases, semantic knowledge management systems and collaborative Web 2.0 platforms. Section 12.1 presents SMW+, a product for developing semantic enterprise applications. The section describes a number of real-world applications that are realized with SMW+. These include content management, project management and semantic data integration. Section 12.2 presents MoKi, a semantic wiki for modeling enterprise processes and application domains. Example applications of MoKi include modeling tasks and topics for work-integrated learning, collaboratively building an ontology and modeling clinical protocols. The chapter illustrates the wealth of activities which semantic wikis support.
Granitzer Michael, Lindstaedt Stefanie
2011
Granitzer Michael, Sabol Vedran, Onn K., Lukose D.
2010
Stern Hermann, Kaiser Rene_DB, Hofmair P., Lindstaedt Stefanie , Scheir Peter, Kraker Peter
2010
One of the success factors of Work Integrated Learning (WIL) is to provide theappropriate content to the users, both suitable for the topics they are currently working on, andtheir experience level in these topics. Our main contributions in this paper are (i) overcomingthe problem of sparse content annotation by using a network based recommendation approachcalled Associative Network, which exploits the user context as input; (ii) using snippets for notonly highlighting relevant parts of documents, but also serving as a basic concept enabling theWIL system to handle text-based and audiovisual content the same way; and (iii) using the WebTool for Ontology Evaluation (WTE) toolkit for finding the best default semantic similaritymeasure of the Associative Network for new domains. The approach presented is employed inthe software platform APOSDLE, which is designed to enable knowledge workers to learn atwork.
Beham Günter, Lindstaedt Stefanie , Ley Tobias, Kump Barbara, Seifert C.
2010
When inferring a user’s knowledge state from naturally occurringinteractions in adaptive learning systems, one has to makes complexassumptions that may be hard to understand for users. We suggestMyExperiences, an open learner model designed for these specificrequirements. MyExperiences is based on some of the key design principles ofinformation visualization to help users understand the complex information inthe learner model. It further allows users to edit their learner models in order toimprove the accuracy of the information represented there.
Stocker A., Mueller J.
2010
Ley Tobias, Kump Barbara, Albert D.
2010
Granitzer Michael, Rath Andreas S., Kröll Mark, Ipsmiller D., Devaurs Didier, Weber Nicolas, Lindstaedt Stefanie , Seifert C.
2009
Increasing the productivity of a knowledgeworker via intelligent applications requires the identification ofa user’s current work task, i.e. the current work context a userresides in. In this work we present and evaluate machine learningbased work task detection methods. By viewing a work taskas sequence of digital interaction patterns of mouse clicks andkey strokes, we present (i) a methodology for recording thoseuser interactions and (ii) an in-depth analysis of supervised classificationmodels for classifying work tasks in two different scenarios:a task centric scenario and a user centric scenario. Weanalyze different supervised classification models, feature typesand feature selection methods on a laboratory as well as a realworld data set. Results show satisfiable accuracy and high useracceptance by using relatively simple types of features.
Gras R., Devaurs Didier, Wozniak A., Aspinall A.
2009
We present an individual-based predator-prey model with, for the first time, each agent behavior being modeled by a fuzzy cognitive map (FCM), allowing the evolution of the agent behavior through the epochs of the simulation. The FCM enables the agent to evaluate its environment (e.g., distance to predator or prey, distance to potential breeding partner, distance to food, energy level) and its internal states (e.g., fear, hunger, curiosity), and to choose several possible actions such as evasion, eating, or breeding. The FCM of each individual is unique and is the result of the evolutionary process. The notion of species is also implemented in such a way that species emerge from the evolving population of agents. To our knowledge, our system is the only one that allows the modeling of links between behavior patterns and speciation. The simulation produces a lot of data, including number of individuals, level of energy by individual, choice of action, age of the individuals, and average FCM associated with each species. This study investigates patterns of macroevolutionary processes, such as the emergence of species in a simulated ecosystem, and proposes a general framework for the study of specific ecological problems such as invasive species and species diversity patterns. We present promising results showing coherent behaviors of the whole simulation with the emergence of strong correlation patterns also observed in existing ecosystems.
Thurner-Scheuerer Claudia
2009
Schachner W., Koubek A.
2009
Lindstaedt Stefanie , Hambach S., Müsebeck P., de Hoog R., Kooken J., Musielak M.
2009
Computational support for work-integrated learning will gain more and moreattention. We understand informal self-directed work-integrated learning of knowledgeworkers as a by-product of their knowledge work activities and propose a conceptual as wellas a technical approach for supporting learning from documents and learning in interactionwith fellow knowledge workers. The paper focuses on contextualization and scripting as twomeans to specifically address the latter interaction type.
Neidhart T., Granitzer Michael, Kern Roman, Weichselbraun A., Wohlgenannt G., Scharl A., Juffinger A.
2009
Lindstaedt Stefanie , Moerzinger R., Sorschag R. , Pammer-Schindler Viktoria, Thallinger G.
2009
Automatic image annotation is an important and challenging task, andbecomes increasingly necessary when managing large image collections. This paperdescribes techniques for automatic image annotation that take advantage of collaborativelyannotated image databases, so called visual folksonomies. Our approachapplies two techniques based on image analysis: First, classification annotates imageswith a controlled vocabulary and second tag propagation along visually similar images.The latter propagates user generated, folksonomic annotations and is thereforecapable of dealing with an unlimited vocabulary. Experiments with a pool of Flickrimages demonstrate the high accuracy and efficiency of the proposed methods in thetask of automatic image annotation. Both techniques were applied in the prototypicaltag recommender “tagr”.
Ley Tobias, Ulbrich Armin, Lindstaedt Stefanie , Scheir Peter, Kump Barbara, Albert Dietrich
2008
Purpose – The purpose of this paper is to suggest a way to support work-integrated learning forknowledge work, which poses a great challenge for current research and practice.Design/methodology/approach – The authors first suggest a workplace learning context model, whichhas been derived by analyzing knowledge work and the knowledge sources used by knowledgeworkers. The authors then focus on the part of the context that specifies competencies by applying thecompetence performance approach, a formal framework developed in cognitive psychology. From theformal framework, a methodology is then derived of how to model competence and performance in theworkplace. The methodology is tested in a case study for the learning domain of requirementsengineering.Findings – The Workplace Learning Context Model specifies an integrative view on knowledge workers’work environment by connecting learning, work and knowledge spaces. The competence performanceapproach suggests that human competencies be formalized with a strong connection to workplaceperformance (i.e. the tasks performed by the knowledge worker). As a result, competency diagnosisand competency gap analysis can be embedded into the normal working tasks and learninginterventions can be offered accordingly. The results of the case study indicate that experts weregenerally in moderate to high agreement when assigning competencies to tasks.Research limitations/implications – The model needs to be evaluated with regard to the learningoutcomes in order to test whether the learning interventions offered benefit the user. Also, the validityand efficiency of competency diagnosis need to be compared to other standard practices incompetency management.Practical implications – Use of competence performance structures within organizational settings hasthe potential to more closely relate the diagnosis of competency needs to actual work tasks, and toembed it into work processes.Originality/value – The paper connects the latest research in cognitive psychology and in thebehavioural sciences with a formal approach that makes it appropriate for integration intotechnology-enhanced learning environments.Keywords Competences, Learning, Workplace learning, Knowledge managementPaper type Research paper
Lex Elisabeth, Kienreich Wolfgang, Granitzer Michael, Seifert C.
2008
Granitzer Gisela, Höfler Patrick
2008
Even though it was only about three years ago that Social Software became a trend, it has become a common practice to utilize Social Software in learning institutions. It brought about a lot of advantages, but also challenges. Amounts of distributed and often unstructured user generated content make it difficult to meaningfully process and find relevant information. According to the estimate of the authors, the solution lies in underpinning Social Software with structure resulting in Social Semantic Software. In this contribution we introduce the central concepts Social Software, Semantic Web and Social Semantic Web and show how Social Semantic Technologies might be utilized in the higher education context.
Lindstaedt Stefanie , Ley Tobias, Scheir Peter, Ulbrich Armin
2008
This contribution introduces the concept of work-integrated learning which distinguishes itself from traditional e-Learning in that it provides learning support (i) during work task execution and tightly contextualized to the work context,(ii) within the work environment, and (iii) utilizes knowledge artefacts available within the organizational memory for learning. We argue that in order to achieve this highly flexible learning support we need to turn to" scruffy" methods (such as associative retrieval, genetic algorithms, Bayesian and other probabilistic methods) which can provide good results in the presence of uncertainty and the absence of fine-granular models. Hybrid approaches to user context determination, user profile management, and learning material identification are discussed and first results are reported.
Lux M.
2007
Is Web 2.0 just hype or just a buzzword, which might disappear in the near future? One way to find answers to these questions is to investigate the actual benefit of the Web 2.0 for real use cases. Within this contribution we study a very special aspect of the Web 2.0 ? the folksonomy ? and its use within self-directed learning. Guided by conceptual principles of emergent computing we point out methods, which might be able to let semantics emerge from folksonomies and discuss the effect of the results in self-directed learning.
Strohmaier M., Lindstaedt Stefanie
2007
Purpose: The purpose of this contribution is to motivate a new, rapid approachto modeling knowledge work in organizational settings and to introducea software tool that demonstrates the viability of the envisioned concept.Approach: Based on existing modeling structures, the KnowFlowr Toolsetthat aids knowledge analysts in rapidly conducting interviews and in conductingmulti-perspective analysis of organizational knowledge work is introduced.Findings: It is demonstrated how rapid knowledge work visualization can beconducted largely without human modelers by developing an interview structurethat allows for self-service interviews. Two application scenarios illustrate thepressing need for and the potentials of rapid knowledge work visualizations inorganizational settings.Research Implications: The efforts necessary for traditional modeling approachesin the area of knowledge management are often prohibitive. Thiscontribution argues that future research needs to take economical constraintsof organizational settings into account in order to be able to realize the fullpotential of knowledge work management.Practical Implications: This work picks up a problem identified in practiceand proposes the novel concept of rapid knowledge work visualization for makingknowledge work modeling in organizations more feasible.Value: This work develops a vision of rapid knowledge work visualization andintroduces a tool-supported approach that addresses some of the identified challenges.
Rollett H., Lux M., Strohmaier M., Dösinger G.
2007
While there is a lot of hype around various concepts associated with the term Web 2.0 in industry, little academic research has so far been conducted on the implications of this new approach for the domain of education. Much of what goes by the name of Web 2.0 can, in fact, be regarded as new kinds of learning technologies, and can be utilised as such. This paper explains the background of Web 2.0, investigates the implications for knowledge transfer in general, and then discusses its particular use in eLearning contexts with the help of short scenarios. The main challenge in the future will be to maintain essential Web 2.0 attributes, such as trust, openness, voluntariness and self-organisation, when applying Web 2.0 tools in institutional contexts.
Burgsteiner H., Kröll Mark, Leopold A., Steinbauer G.
2007
The prediction of time series is an important task in finance, economy, object tracking, state estimation and robotics. Prediction is in general either based on a well-known mathematical description of the system behind the time series or learned from previously collected time series. In this work we introduce a novel approach to learn predictions of real world time series like object trajectories in robotics. In a sequence of experiments we evaluate whether a liquid state machine in combination with a supervised learning algorithm can be used to predict ball trajectories with input data coming from a video camera mounted on a robot participating in the RoboCup. The pre-processed video data is fed into a recurrent spiking neural network. Connections to some output neurons are trained by linear regression to predict the position of a ball in various time steps ahead. The main advantages of this approach are that due to the nonlinear projection of the input data to a high-dimensional space simple learning algorithms can be used, that the liquid state machine provides temporal memory capabilities and that this kind of computation appears biologically more plausible than conventional methods for prediction. Our results support the idea that learning with a liquid state machine is a generic powerful tool for prediction.
Kooken J., Ley Tobias, de Hoog R.
2007
Any software development project is based on assumptions about the state of the world that probably will hold when it is fielded. Investigating whether they are true can be seen as an important task. This paper describes how an empirical investigation was designed and conducted for the EU funded APOSDLE project. This project aims at supporting informal learning during work. Four basic assumptions are derived from the project plan and subsequently investigated in a two-phase study using several methods, including workplace observations and a survey. The results show that most of the assumptions are valid in the current work context of knowledge workers. In addition more specific suggestions for the design of the prospective APOSDLE application could be derived. Though requiring a substantial effort, carrying out studies like this can be seen as important for longer term software development projects.
Lokaiczyk R., Godehardt E., Faatz A., Goertz M., Kienle A., Wessner M., Ulbrich Armin
2007
Strohmaier M.
2005
Timbrell G., Koller S., Schefe N., Lindstaedt Stefanie
2005
This paper explores a process view of call-centres and the knowledge infrastructuresthat support these processes. As call-centres grow and become more complex in their functionand organisation so do the knowledge infrastructures required to support their size andcomplexity. This study suggests a knowledge-based hierarchy of ‘advice-type’ call-centres anddiscusses associated knowledge management strategies for different sized centres. It introducesa Knowledge Infrastructure Hierarchy model, with which it is possible to analyze and classifycall-centre knowledge infrastructures. The model also demonstrates different types ofinterventions supporting knowledge management in call-centres. Finally the paper discusses thepossibilities of applying traditional maturity model approaches in this context.
Maurer H.
2004
Dösinger G.
2004
Dösinger G., Gissing B.
2004
Maurer H.
2004
Lindstaedt Stefanie , Farmer J.
2004
Kienreich Wolfgang, Sabol Vedran, Granitzer Michael, Becker J.
2003
Ley Tobias, Albert D.
2003
Ley Tobias, Albert D.
2003
Ley Tobias, Albert D.
2003
We present a formalisation for employee competencies which is based on a psychological framework separating the overt behavioural level from the underlying competence level. On the competence level, employees draw on action potentials (knowledge, skills and abilities) which in a given situation produce performance outcomes on the behavioural level. Our conception is based on the competence performance approach by [Korossy 1997] and [Korossy 1999] which uses mathematical structures to establish prerequisite relations on the competence and the performance level. From this framework, a methodology for assessing competencies in dynamic work domains is developed which utilises documents employees have created to assess the competencies they have been acquiring. By means of a case study, we show how the methodology and the resulting structures can be validated in an organisational setting. From the resulting structures, employee competency profiles can be derived and development planning can be supported. The structures also provide the means for making inferences within the competency assessment process which in turn facilitates continuous updating of competency profiles and maintenance of the structures.
Clancy J.M. , Elliott G., Ley Tobias, Odomei M.M., Wearing A.J., McLennan J., Thorsteinsson E.B.
2003
Lux M., Klieber Hans-Werner, Becker J., Mayer H., Neuschmied H., Haas W.
2002
Lux M., Klieber Hans-Werner, Becker J., Mayer H., Neuschmied H., Haas W.
2002
The evolution of the Web is not only accompanied by an increasing diversity of multimedia but by new requirements towards intelligent research capabilities, user specific assistance, intuitive user interfaces and platform independent information presentation. To reach these and further upcoming requirements new standardized Web technologies and XML based description languages are used. The Web Information Space has transformed into a Knowledge marketplace where worldwide located participants take part into the creation, annotation and consumption of knowledge. This paper points out the design of semantic retrieval frameworks and a prototype implementation for audio and video annotation, storage and retrieval using the MPEG-7 standard and semantic web reference implementations. MPEG-7 plays an important role towards the standardized enrichment of multimedia with semantics on higher abstraction levels and a related improvement of query results.
Dösinger G., Ley Tobias
2002
Becker J., Granitzer Michael, Kienreich Wolfgang, Sabol Vedran
2002
Andrews K., Kienreich Wolfgang, Sabol Vedran, Becker J., Kappe F., Droschl G., Granitzer Michael, Auer P.
2002
Maurer H.
2002
Maurer H.
2002
Becker J., Lux M., Klieber Hans-Werner, Sabol Vedran, Kienreich Wolfgang
2002
Becker J., Lux M., Klieber Hans-Werner
2002
Lindstaedt Stefanie
2002
Lindstaedt Stefanie , Scheir Peter, Sarka W.
2002
2002
2002
2002
Lindstaedt Stefanie
2001
Ulbrich Armin, Ausserhofer A., Dietinger T., Raback W., Hoitsch P.
2001
Pammer-Schindler Viktoria, Lindstaedt Stefanie
Cicchinelli Analia, Pammer-Schindler Viktoria
Purpose – The goal of this study is to understand what drives people (i.e., their motivations, autonomous learning attitudes and learning interests) to volunteer as mentors for a program that helps families to ideate technological solutions to community problems.Design/methodology/approach – A three-phase method was used to i) create volunteer mentor profiles; ii) elicit topics of interest; and iii) establish relationships between those. The mentor profiles were based on self-assessments of motivation, attitudes towards lifelong learning and self-regulated learning strategies. The topics of interests were defined by analyzing answers to reflection questions. Statistical methods were applied to analyze the relationships between the interests and the mentor profiles.Findings –Three mentor groups (G1 “low,” G2 “high” and G3 “medium”) were identified based on pre-survey data via bottom-up clustering. Content analysis was used to define the topics of interest: communication skills; learning AI; mentoring; prototype development; problem solving skills; and working with families. Examining relationships between the mentor profile and the topics of interest showed that group G3 “medium” with strong intrinsic motivation had significantly more interest in working with families. The group with overall highest scores (G2 “high”) expressed substantial interest in learning about AI. However, there was a high variability between members of this group. Originality/value –The study established different types of learning interests of volunteer mentors and related them to the mentor profiles based on motivation, self-regulated learning strategies and attitudes towards lifelong learning. Such knowledge can help organizations shape volunteering experience, offering more value to volunteers. Furthermore, the reflection questions can be used by: i) volunteers as an instrument of reflection; and ii) organizations for eliciting learning interests of volunteers.