Know Center Research

Publikationen

Lacic Emanuel, Reiter-Haas Markus, Duricic Tomislav, Slawicek Valentin, Lex Elisabeth
2019
In this work, we present the findings of an online study, where we explore the impact of utilizing embeddings to recommend job postings under real-time constraints. On the Austrian job platform Studo Jobs, we evaluate two popular recommendation scenarios: (i) providing similar jobs and, (ii) personalizing the job postings that are shown on the homepage. Our results show that for recommending similar jobs, we achieve the best online performance in terms of Click-Through Rate when we employ embeddings based on the most recent interaction. To personalize the job postings shown on a user's homepage, however, combining embeddings based on the frequency and recency with which a user interacts with job postings results in the best online performance.
Duricic Tomislav, Lacic Emanuel, Kowald Dominik, Lex Elisabeth
2019
User-based Collaborative Filtering (CF) is one of the most popular approaches to create recommender systems. CF, however, suffers from data sparsity and the cold-start problem since users often rate only a small fraction of available items. One solution is to incorporate additional information into the recommendation process such as explicit trust scores that are assigned by users to others or implicit trust relationships that result from social connections between users. Such relationships typically form a very sparse trust network, which can be utilized to generate recommendations for users based on people they trust. In our work, we explore the use of regular equivalence applied to a trust network to generate a similarity matrix that is used for selecting k-nearest neighbors used for item recommendation. Two vertices in a network are regularly equivalent if their neighbors are themselves equivalent and by using the iterative approach of calculating regular equivalence, we can study the impact of strong and weak ties on item recommendation. We evaluate our approach on cold start users on a dataset crawled from Epinions and find that by using weak ties in addition to strong ties, we can improve the performance of a trust-based recommender in terms of recommendation accuracy.
Wolfbauer Irmtraud
2019
Presentation of PhDUse Case: An online learning platform for apprentices.Research opportunities: Target group is under-researched1. Computer usage & ICT self-efficacy2. Communities of practice, identities as learnersReflection guidance technologies3. Rebo, the reflection guidance chatbot
Wolfbauer Irmtraud
2019
Use Case: An online learning platform for apprentices.Research opportunities: Target group is under-researched1. Computer usage & ICT self-efficacy2. Communities of practice, identities as learnersReflection guidance technologies3. Rebo, the reflection guidance chatbot
Kowald Dominik, Lex Elisabeth, Schdel Markus
2019
Iacopo Vagliano, Fessl Angela, Franziska Günther, Thomas Köhler, Vasileios Mezaris, Ahmed Saleh, Ansgar Scherp, Simic Ilija
2019
The MOVING platform enables its users to improve their information literacy by training how to exploit data and text mining methods in their daily research tasks. In this paper, we show how it can support researchers in various tasks, and we introduce its main features, such as text and video retrieval and processing, advanced visualizations, and the technologies to assist the learning process.
Fessl Angela, Apaolaza Aitor, Gledson Ann, Pammer-Schindler Viktoria, Vigo Markel
2019
Searching on the web is a key activity for working and learning purposes. In this work, we aimed to motivate users to reflect on their search behaviour, and to experiment with different search functionalities. We implemented a widget that logs user interactions within a search platform, mirrors back search behaviours to users, and prompts users to reflect about it. We carried out two studies to evaluate the impact of such widget on search behaviour: in Study 1 (N = 76), participants received screenshots of the widget including reflection prompts while in Study 2 (N = 15), a maximum of 10 search tasks were conducted by participants over a period of two weeks on a search platform that contained the widget. Study 1 shows that reflection prompts induce meaningful insights about search behaviour. Study 2 suggests that, when using a novel search platform for the first time, those participants who had the widget prioritised search behaviours over time. The incorporation of the widget into the search platform after users had become familiar with it, however, was not observed to impact search behaviour. While the potential to support un-learning of routines could not be shown, the two studies suggest the widget’s usability, perceived usefulness, potential to induce reflection and potential to impact search behaviour.
Kopeinik Simone, Seitlinger Paul, Lex Elisabeth
2019
Kopeinik Simone, Lex Elisabeth, Kowald Dominik, Albert Dietrich, Seitlinger Paul
2019
When people engage in Social Networking Sites, they influence one another through their contributions. Prior research suggests that the interplay between individual differences and environmental variables, such as a person’s openness to conflicting information, can give rise to either public spheres or echo chambers. In this work, we aim to unravel critical processes of this interplay in the context of learning. In particular, we observe high school students’ information behavior (search and evaluation of Web resources) to better understand a potential coupling between confirmatory search and polarization and, in further consequence, improve learning analytics and information services for individual and collective search in learning scenarios. In an empirical study, we had 91 high school students performing an information search in a social bookmarking environment. Gathered log data was used to compute indices of confirmatory search and polarisation as well as to analyze the impact of social stimulation. We find confirmatory search and polarization to correlate positively and social stimulation to mitigate, i.e., reduce the two variables’ relationship. From these findings, we derive practical implications for future work that aims to refine our formalism to compute confirmatory search and polarisation indices and to apply it for depolarizing information services
Fruhwirth Michael, Pammer-Schindler Viktoria, Thalmann Stefan
2019
Data plays a central role in many of today's business models. With the help of advanced analytics, knowledge about real-world phenomena can be discovered from data. This may lead to unintended knowledge spillover through a data-driven offering. To properly consider this risk in the design of data-driven business models, suitable decision support is needed. Prior research on approaches that support such decision-making is scarce. We frame designing business models as a set of decision problems with the lens of Behavioral Decision Theory and describe a Design Science Research project conducted in the context of an automotive company. We develop an artefact that supports identifying knowledge risks, concomitant with design decisions, during the design of data-driven business models and verify knowledge risks as a relevant problem. In further research, we explore the problem in-depth and further design and evaluate the artefact within the same company as well as in other companies.
Schlager Elke, Gursch Heimo, Feichtinger Gerald
2019
Poster to publish the finally implemented "Data Management System" @ Know-Center for the COMFORT project
Feichtinger Gerald, Gursch Heimo
2019
Poster - allgemeine Projektvorstellung
Monsberger Michael, Koppelhuber Daniela, Sabol Vedran, Gursch Heimo, Spataru Adrian, Prentner Oliver
2019
A lot of research is currently focused on studying user behavior indirectly by analyzing sensor data. However, only little attention has been given to the systematic acquisition of immediate user feedback to study user behavior in buildings. In this paper, we present a novel user feedback system which allows building users to provide feedback on the perceived sense of personal comfort in a room. To this end, a dedicated easy-to-use mobile app has been developed; it is complemented by a supporting infrastructure, including a web page for an at-a-glance overview. The obtained user feedback is compared with sensor data to assess whether building services (e.g., heating, ventilation and air-conditioning systems) are operated in accordance with user requirements. This serves as a basis to develop algorithms capable of optimizing building operation by providing recommendations to facility management staff or by automatic adjustment of operating points of building services. In this paper, we present the basic concept of the novel feedback system for building users and first results from an initial test phase. The results show that building users utilize the developed app to provide both, positive and negative feedback on room conditions. They also show that it is possible to identify rooms with non-ideal operating conditions and that reasonable measures to improve building operation can be derived from the gathered information. The results highlight the potential of the proposed system.
Fuchs Alexandra, Geiger Bernhard, Hobisch Elisabeth, Koncar Philipp, Saric Sanja, Scholger Martina
2019
with contributions from Denis Helic and Jacqueline More
Lindstaedt Stefanie , Geiger Bernhard, Pirker Gerhard
2019
Big Data and data-driven modeling are receiving more and more attention in various research disciplines, where they are often considered as universal remedies. Despite their remarkable records of success, in certain cases a purely data-driven approach has proven to be suboptimal or even insufficient.This extended abstract briefly defines the terms Big Data and data-driven modeling and characterizes scenarios in which a strong focus on data has proven to be promising. Furthermore, it explains what progress can be made by fusing concepts from data science and machine learning with current physics-based concepts to form hybrid models, and how these can be applied successfully in the field of engine pre-simulation and engine control.
Gursch Heimo, Cemernek David, Wuttei Andreas, Kern Roman
2019
The increasing potential of Information and Communications Technology (ICT) drives higher degrees of digitisation in the manufacturing industry. Such catchphrases as “Industry 4.0” and “smart manufacturing” reflect this tendency. The implementation of these paradigms is not merely an end to itself, but a new way of collaboration across existing department and process boundaries. Converting the process input, internal and output data into digital twins offers the possibility to test and validate the parameter changes via simulations, whose results can be used to update guidelines for shop-floor workers. The result is a Cyber-Physical System (CPS) that brings together the physical shop-floor, the digital data created in the manufacturing process, the simulations, and the human workers. The CPS offers new ways of collaboration on a shared data basis: the workers can annotate manufacturing problems directly in the data, obtain updated process guidelines, and use knowledge from other experts to address issues. Although the CPS cannot replace manufacturing management since it is formalised through various approaches, e. g., Six-Sigma or Advanced Process Control (APC), it is a new tool for validating decisions in simulation before they are implemented, allowing to continuously improve the guidelines.
Schweimer Christoph, Geiger Bernhard, Suleimenova Diana, Groen Derek, Gfrerer Christine, Pape David, Elsaesser Robert, Kocsis Albert Tihamér, Liszkai B., Horváth Zoltan
2019
Jorge Guerra Torres, Veas Eduardo Enrique, Carlos Catania
2019
Labeling a real network dataset is specially expensive in computer security, as an expert has to ponder several factors before assigning each label. This paper describes an interactive intelligent system to support the task of identifying hostile behavior in network logs. The RiskID application uses visualizations to graphically encode features of network connections and promote visual comparison. In the background, two algorithms are used to actively organize connections and predict potential labels: a recommendation algorithm and a semi-supervised learning strategy. These algorithms together with interactive adaptions to the user interface constitute a behavior recommendation. A study is carried out to analyze how the algo-rithms for recommendation and prediction influence the workflow of labeling a dataset. The results of a study with 16 participants indicate that the behaviour recommendation significantly improves the quality of labels. Analyzing interaction patterns, we identify a more intuitive workflow used when behaviour recommendation isavailable.
Luzhnica Granit, Veas Eduardo Enrique
2019
Proficiency in any form of reading requires a considerable amount of practice. With exposure, people get better at recognising words, because they develop strategies that enable them to read faster. This paper describes a study investigating recognition of words encoded with a 6-channel vibrotactile display. We train 22 users to recognise ten letters of the English alphabet. Additionally, we repeatedly expose users to 12 words in the form of training and reinforcement testing.Then, we test participants on exposed and unexposed words to observe the effects of exposure to words. Our study shows that, with exposure to words, participants did significantly improve on recognition of exposed words. The findings suggest that such a word exposure technique could be used during the training of novice users in order to boost the word recognition of a particular dictionary of words.
Remonda Adrian, Krebs Sarah, Luzhnica Granit, Kern Roman, Veas Eduardo Enrique
2019
This paper explores the use of reinforcement learning (RL) models for autonomous racing. In contrast to passenger cars, where safety is the top priority, a racing car aims to minimize the lap-time. We frame the problem as a reinforcement learning task witha multidimensional input consisting of the vehicle telemetry, and a continuous action space. To findout which RL methods better solve the problem and whether the obtained models generalize to drivingon unknown tracks, we put 10 variants of deep deterministic policy gradient (DDPG) to race in two experiments: i) studying how RL methods learn to drive a racing car and ii) studying how the learning scenario influences the capability of the models to generalize. Our studies show that models trained with RL are not only able to drive faster than the baseline open source handcrafted bots but also generalize to unknown tracks.
Kowald Dominik, Traub Matthias, Theiler Dieter, Gursch Heimo, Lacic Emanuel, Lindstaedt Stefanie , Kern Roman, Lex Elisabeth
2019
Kowald Dominik, Lacic Emanuel, Theiler Dieter, Traub Matthias, Kuffer Lucky, Lindstaedt Stefanie , Lex Elisabeth
2019
Kowald Dominik, Lex Elisabeth, Schedl Markus
2019
Lex Elisabeth, Kowald Dominik
2019
Toller Maximilian, Geiger Bernhard, Kern Roman
2019
Distance-based classification is among the most competitive classification methods for time series data. The most critical componentof distance-based classification is the selected distance function.Past research has proposed various different distance metrics ormeasures dedicated to particular aspects of real-world time seriesdata, yet there is an important aspect that has not been considered so far: Robustness against arbitrary data contamination. In thiswork, we propose a novel distance metric that is robust against arbitrarily “bad” contamination and has a worst-case computationalcomplexity of O(n logn). We formally argue why our proposedmetric is robust, and demonstrate in an empirical evaluation thatthe metric yields competitive classification accuracy when appliedin k-Nearest Neighbor time series classification.
Breitfuß Gert, Berger Martin, Doerrzapf Linda
2019
The Austrian Federal Ministry for Transport, Innovation and Technology created an initiative to fund the setup and operation of Living Labs to provide a vital innovation ecosystem for mobility and transport. Five Urban Mobility Labs (UML) located in four urban areas have been selected for funding (duration 4 years) and started operation in 2017. In order to cover the risk of a high dependency of public funding (which is mostly limited in time), the lab management teams face the challenge to develop a viable and future-proof UML Business Model. The overall research goal of this paper is to get empirical insights on how a UML Business Model evolves on a long-term perspective and which success factors play a role. To answer the research question, a method mix of desk research and qualitative methods have been selected. In order to get an insight into the UML Business Model, two circles of 10 semi-structured interviews (two responsible persons of each UML) are planned. The first circle of the interviews took place between July 2018 and January 2019. The second circle of interviews is planned for 2020. Between the two rounds of the survey, a Business Model workshop is planned to share and create ideas for future Business Model developments. Based on the gained research insights a comprehensive list of success factors and hands-on recommendations will be derived. This should help UML organizations in developing a viable Business Model in order to support sustainable innovations in transport and mobility.
Geiger Bernhard
2019
joint work with Tobias Koch, Universidad Carlos III de Madrid
Silva Nelson, Blascheck Tanja, Jianu Radu, Rodrigues Nils, Weiskopf Daniel, Raubal Martin, Schreck Tobias
2019
Visual analytics (VA) research provides helpful solutions for interactive visual data analysis when exploring large and complexdatasets. Due to recent advances in eye tracking technology, promising opportunities arise to extend these traditional VA approaches.Therefore, we discuss foundations for eye tracking support in VAsystems. We first review and discuss the structure and range oftypical VA systems. Based on a widely used VA model, we presentfive comprehensive examples that cover a wide range of usage scenarios. Then, we demonstrate that the VA model can be used tosystematically explore how concrete VA systems could be extendedwith eye tracking, to create supportive and adaptive analytics systems. This allows us to identify general research and applicationopportunities, and classify them into research themes. In a call foraction, we map the road for future research to broaden the use ofeye tracking and advance visual analytics.
Kaiser Rene_DB
2019
This paper gives a comprehensive overview of the Virtual Director concept. A Virtual Director is a software component automating the key decision making tasks of a TV broadcast director. It decides how to mix and present the available content streams on a particular playout device, most essentially deciding which camera view to show and when to switch to another. A Virtual Director allows to take decisions respecting individual user preferences and playout device characteristics. In order to take meaningful decisions, a Virtual Director must be continuously informed by real-time sensors which emit information about what is happening in the scene. From such (low-level) 'cues', the Virtual Director infers higher-level events, actions, facts and states which in turn trigger the real-time processes deciding on the presentation of the content. The behaviour of a Virtual Director, the 'production grammar', defines how decisions are taken, generally encompassing two main aspects: selecting what is most relevant, and deciding how to show it, applying cinematographic principles.
Thalmann Stefan, Gursch Heimo, Suschnigg Josef, Gashi Milot, Ennsbrunner Helmut, Fuchs Anna Katharina, Schreck Tobias, Mutlu Belgin, Mangler Jürgen, Huemer Christian, Lindstaedt Stefanie
2019
Current trends in manufacturing lead to more intelligent products, produced in global supply chains in shorter cycles, taking more and complex requirements into account. To manage this increasing complexity, cognitive decision support systems, building on data analytic approaches and focusing on the product life cycle, stages seem a promising approach. With two high-tech companies (world market leader in their domains) from Austria, we are approaching this challenge and jointly develop cognitive decision support systems for three real world industrial use cases. Within this position paper, we introduce our understanding of cognitive decision support and we introduce three industrial use cases, focusing on the requirements for cognitive decision support. Finally, we describe our preliminary solution approach for each use case and our next steps.
Pammer-Schindler Viktoria
2019
This is a commentary of mine, created in the context of an open review process, selected for publication alongside the accepted original paper in a juried process, and published alongside the paper at the given DOI,
Xie Benjamin, Harpstead Erik, DiSalvo Betsy, Slovak Petr, Kharuffa Ahmed, Lee Michael J., Pammer-Schindler Viktoria, Ogan Amy, Williams Joseph Jay
2019
Winter Kevin, Kern Roman
2019
This paper presents the Know-Center system submitted for task 5 of the SemEval-2019workshop. Given a Twitter message in either English or Spanish, the task is to first detect whether it contains hateful speech and second,to determine the target and level of aggression used. For this purpose our system utilizes word embeddings and a neural network architecture, consisting of both dilated and traditional convolution layers. We achieved aver-age F1-scores of 0.57 and 0.74 for English and Spanish respectively.
Maritsch Martin, Diana Suleimenova, Geiger Bernhard, Derek Groen
2019
Geiger Bernhard, Schrunner Stefan, Kern Roman
2019
Schrunner and Geiger have contributed equally to this work.
Fessl Angela, Simic Ilija, Barthold Sabine, Pammer-Schindler Viktoria
2019
Information literacy, the access to knowledge and use of it are becoming a precondition for individuals to actively take part in social,economic, cultural and political life. Information literacy must be considered as a fundamental competency like the ability to read, write and calculate. Therefore, we are working on automatic learning guidance with respect to three modules of the information literacy curriculum developed by the EU (DigComp 2.1 Framework). In prior work, we havelaid out the essential research questions from a technical side. In this work, we follow-up by specifying the concept to micro learning, and micro learning content units. This means, that the overall intervention that we design is concretized to: The widget is initialized by assessing the learners competence with the help of a knowledge test. This is the basis for recommending suitable micro learning content, adapted to the identified competence level. After the learner has read/worked through the content, the widget asks a reflective question to the learner. The goal of the reflective question is to deepen the learning. In this paper we present the concept of the widget and its integration in a search platform.
Luzhnica Granit, Veas Eduardo Enrique
2019
Luzhnica Granit, Veas Eduardo Enrique
2019
This paper proposes methods of optimising alphabet encoding for skin reading in order to avoid perception errors. First, a user study with 16 participants using two body locations serves to identify issues in recognition of both individual letters and words. To avoid such issues, a two-step optimisation method of the symbol encoding is proposed and validated in a second user study with eight participants using the optimised encoding with a seven vibromotor wearable layout on the back of the hand. The results show significant improvements in the recognition accuracy of letters (97%) and words (97%) when compared to the non-optimised encoding.
Breitfuß Gert, Fruhwirth Michael, Pammer-Schindler Viktoria, Stern Hermann, Dennerlein Sebastian
2019
Increasing digitization is generating more and more data in all areas ofbusiness. Modern analytical methods open up these large amounts of data forbusiness value creation. Expected business value ranges from process optimizationsuch as reduction of maintenance work and strategic decision support to businessmodel innovation. In the development of a data-driven business model, it is usefulto conceptualise elements of data-driven business models in order to differentiateand compare between examples of a data-driven business model and to think ofopportunities for using data to innovate an existing or design a new businessmodel. The goal of this paper is to identify a conceptual tool that supports datadrivenbusiness model innovation in a similar manner: We applied three existingclassification schemes to differentiate between data-driven business models basedon 30 examples for data-driven business model innovations. Subsequently, wepresent the strength and weaknesses of every scheme to identify possible blindspots for gaining business value out of data-driven activities. Following thisdiscussion, we outline a new classification scheme. The newly developed schemecombines all positive aspects from the three analysed classification models andresolves the identified weaknesses.