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.
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.
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.
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.
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
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.
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.
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.
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
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.
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.
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.
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
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.
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.
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.
Lindstaedt Stefanie , Farmer J.
2004
Lindstaedt Stefanie
2002
Lindstaedt Stefanie , Scheir Peter, Sarka W.
2002
Lindstaedt Stefanie
2001
Pammer-Schindler Viktoria, Lindstaedt Stefanie