Publikationen

The Game Effect: Comparison of Game and Nongame Learning Environments Using the Example of “Arctic Economy” Artikel

136.

Wittrin, Ruben; Platte, Benny; Roschke, Christian; Ritter, Marc; Eibl, Maximilian; Steiner, Carolin Isabel; Tolkmitt, Volker

In: IEEE Transactions on Learning Technologies, 2024.

@article{wittrin_game_2024,

title = {The Game Effect: Comparison of Game and Nongame Learning Environments Using the Example of “Arctic Economy”},

author = {Ruben Wittrin and Benny Platte and Christian Roschke and Marc Ritter and Maximilian Eibl and Carolin Isabel Steiner and Volker Tolkmitt},

doi = {10.1109/tlt.2023.3274747},

year  = {2024},

date = {2024-01-01},

journal = {IEEE Transactions on Learning Technologies},

abstract = {Virtual environments open up far-reaching possibilities with respect to knowledge impartation. Nevertheless, they have the potential to negatively influence learning behavior. As a possible positive determinant, especially in the digital context, the moment “game” can be listed. Accordingly, previous studies prove an overall positive influence of serious games on learning success and motivation. However, the current state of research only allows for careful and few conclusions in terms of a nuanced differentiation of this influence. Thus, this study differentiates on a deeper level with regard to different parameters of learning success and motivation. The aim of the study is to quantify and evaluate a possible influence of the factor “game” with regard to these parameters. Two versions of the modular software environment Arctic Economy , a game and a nongame version, served as the basis for evaluation. Both versions were compared in a field experiment, with randomized group formation ( N = 97) and repeated measures. The data analysis showed the game group having a tendency to demonstrate better learning performance. In the differentiated analysis, a significant effect can be proven: subjects in the game group were able to remember facts more easily than subjects in the nongame group (group difference retention rate x¯¯¯= 17%). In addition, participants showed an average of 46% higher motivation and were significantly more capable of linking the application's content with reality. The identified “game effect” can therefore be classified as highly significant in the context of this study.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

135.

Schlosser, Max; Walther, Michael; Manthey, Robert; Vogel, Richard; Baumgart, Matthias; Roschke, Christian; Ritter, Marc; Vodel, Matthias

Unifying the Data Highway: A Harmonized Telemetry Format for Driver Analytics Proceedings Article

In: 2024.

A Meta Algorithm for Interpretable Ensemble Learning: The League of Experts Artikel

134.

Vogel, Richard; Schlosser, Tobias; Manthey, Robert; Ritter, Marc; Vodel, Matthias; Eibl, Maximilian; Schneider, Kristan

In: Machine Learning and Knowledge Extraction, 2024.

@article{vogel_meta_2024,

title = {A Meta Algorithm for Interpretable Ensemble Learning: The League of Experts},

author = {Richard Vogel and Tobias Schlosser and Robert Manthey and Marc Ritter and Matthias Vodel and Maximilian Eibl and Kristan Schneider},

doi = {10.3390/make6020038},

year  = {2024},

date = {2024-01-01},

journal = {Machine Learning and Knowledge Extraction},

abstract = {<jats:p>Background. The importance of explainable artificial intelligence and machine learning (XAI/XML) is increasingly being recognized, aiming to understand how information contributes to decisions, the method’s bias, or sensitivity to data pathologies. Efforts are often directed to post hoc explanations of black box models. These approaches add additional sources for errors without resolving their shortcomings. Less effort is directed into the design of intrinsically interpretable approaches. Methods. We introduce an intrinsically interpretable methodology motivated by ensemble learning: the League of Experts (LoE) model. We establish the theoretical framework first and then deduce a modular meta algorithm. In our description, we focus primarily on classification problems. However, LoE applies equally to regression problems. Specific to classification problems, we employ classical decision trees as classifier ensembles as a particular instance. This choice facilitates the derivation of human-understandable decision rules for the underlying classification problem, which results in a derived rule learning system denoted as RuleLoE. Results. In addition to 12 KEEL classification datasets, we employ two standard datasets from particularly relevant domains—medicine and finance—to illustrate the LoE algorithm. The performance of LoE with respect to its accuracy and rule coverage is comparable to common state-of-the-art classification methods. Moreover, LoE delivers a clearly understandable set of decision rules with adjustable complexity, describing the classification problem. Conclusions. LoE is a reliable method for classification and regression problems with an accuracy that seems to be appropriate for situations in which underlying causalities are in the center of interest rather than just accurate predictions or classifications.</jats:p>},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

133.

Vogel, Richard; Manthey, Robert; Baumgart, Matthias; Roschke, Christian; Ritter, Marc; Vodel, Matthias

Tamperproof Data Transmission to Offline IoT Devices in a Zero-Trust Environment Proceedings Article

In: 2024.

132.

Manthey, Robert; Vogel, Richard; Vodel, Matthias

Decentralized Offline Smart Lock - Chainlock Proceedings Article

In: 3rd Blockchain and Cryptocurrency Conference, 2024.

131.

Lampe, Alexander; Ritter, Marc; Hentschel, Nicolas; Kaminsky, Theo; Vodel, Matthias; Sieber, Adrian; Marasas, Michelle; Beier-Grunwald, Rico; Roschke, Christian; Heinze, Isabel

Raspberry Pi Controller for Remote Laboratory Hardware Access Proceedings Article

In: The Sixteenth International Conference on Mobile, Hybrid, and On-line Learning - eLmL 2024, 2024.

130.

Manthey, Robert; Vogel, Richard; Vodel, Matthias

Offlinefähige Schließanlagen auf Blockchain-Basis Proceedings Article

In: Konferenzband zum Scientific Trackder Blockchain Autumn School 2024, 2024.

129.

Schneider, André; Baumgart, Matthias; Lindner, Caroline

CONSEQUENCES OF PSYCHOLOGICAL OWNERSHIP ON THE DEVELOPMENT OF OPEN EDUCATION RESOURCES (OER) Proceedings Article

In: INTED2023 Proceedings, 2023.

@inproceedings{schneider_consequences_2023,

title = {CONSEQUENCES OF PSYCHOLOGICAL OWNERSHIP ON THE DEVELOPMENT OF OPEN EDUCATION RESOURCES (OER)},

author = {André Schneider and Matthias Baumgart and Caroline Lindner},

doi = {10.21125/inted.2023.2175},

year  = {2023},

date = {2023-01-01},

booktitle = {INTED2023 Proceedings},

abstract = {Open Educational Resources (OER) are considered a success factor for the realisation of high-quality, inclusive and equal opportunity education. OER are all kinds of teaching and learning materials that are made available under a free licence. The essence of these materials is that anyone can legally reproduce, use, modify and distribute them free of charge. However, despite extensive scholarly discussion and financial support, their embedding in educational systems has been far less successful than originally hoped (Karapanos et al., 2019; Jung et al., 2016).<br /><br />In the search for the reasons for this development, there are numerous research projects on barriers to the use of OER at universities from the perspective of teachers or students. However, there are hardly any studies on those factors that can promote or inhibit the development of OER. Since the creation of these learning materials is a form of knowledge transfer by teachers, the question arises as to which factors positively and negatively influence the intention to share knowledge or develop OER. Among the factors discussed in the literature are the attitude towards knowledge transfer, the subjective norm, the perceived behavioural control or the personal value characteristics (Schneider et al. 2018).<br /><br />Psychological ownership can play a significant role as a further factor influencing the intention to develop OER. Pierce, Kostova and Dirks (2001, p. 299) define psychological ownership as a state in which "[...] individuals feel as though the target of ownership (material or immaterial in nature) or a piece of it is "theirs" (i.e., "It is MINE"!)". However, OER does not necessarily enable teachers to build or maintain psychological ownership, but rather encourages its loss (Hamari et al. 2016). Such losses are often perceived as a threat or diminishment of the self.<br /><br />The aim of this paper is to discuss the consequences that can be expected from the perspective of the phenomenon of psychological ownership on the successful development of OER. In addition, the first results of an ongoing qualitative study are presented, where teachers are asked about the influence of psychological property on the development of free content for use in higher education teaching.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

Open Educational Resources (OER) are considered a success factor for the realisation of high-quality, inclusive and equal opportunity education. OER are all kinds of teaching and learning materials that are made available under a free licence. The essence of these materials is that anyone can legally reproduce, use, modify and distribute them free of charge. However, despite extensive scholarly discussion and financial support, their embedding in educational systems has been far less successful than originally hoped (Karapanos et al., 2019; Jung et al., 2016). In the search for the reasons for this development, there are numerous research projects on barriers to the use of OER at universities from the perspective of teachers or students. However, there are hardly any studies on those factors that can promote or inhibit the development of OER. Since the creation of these learning materials is a form of knowledge transfer by teachers, the question arises as to which factors positively and negatively influence the intention to share knowledge or develop OER. Among the factors discussed in the literature are the attitude towards knowledge transfer, the subjective norm, the perceived behavioural control or the personal value characteristics (Schneider et al. 2018). Psychological ownership can play a significant role as a further factor influencing the intention to develop OER. Pierce, Kostova and Dirks (2001, p. 299) define psychological ownership as a state in which "[...] individuals feel as though the target of ownership (material or immaterial in nature) or a piece of it is "theirs" (i.e., "It is MINE"!)". However, OER does not necessarily enable teachers to build or maintain psychological ownership, but rather encourages its loss (Hamari et al. 2016). Such losses are often perceived as a threat or diminishment of the self. The aim of this paper is to discuss the consequences that can be expected from the perspective of the phenomenon of psychological ownership on the successful development of OER. In addition, the first results of an ongoing qualitative study are presented, where teachers are asked about the influence of psychological property on the development of free content for use in higher education teaching.

128.

Thomanek, Rico; Platte, Benny; Baumgart, Matthias; Roschke, Christian; Ritter, Marc

AI-powered real-time analysis of human activity in videos via smartphone. Proceedings Article

In: Cognitive Computing and Internet of Things. AHFE (2023), 2023.

@inproceedings{thomanek_ai-powered_2023,

title = {AI-powered real-time analysis of human activity in videos via smartphone.},

author = {Rico Thomanek and Benny Platte and Matthias Baumgart and Christian Roschke and Marc Ritter},

doi = {10.54941/ahfe1003972},

year  = {2023},

date = {2023-01-01},

booktitle = {Cognitive Computing and Internet of Things. AHFE (2023)},

abstract = {<jats:p>A major focus in computer vision research is the recognition of human activity based on visual information from audiovisual data using artificial intelligence. In this context, researchers are currently exploring image-based approaches using 3D CNNs, RNNs, or hybrid models with the intent of learning multiple levels of representation and abstraction that enable fully automated feature extraction and activity analysis based on them. Unfortunately, these architectures require powerful hardware to achieve the most real-time processing possible, making them difficult to deploy on smartphones. However, many video recordings are increasingly made with smartphones, so immediate classification of performed human activities and their tagging already during video recording would be useful for a variety of use cases. Especially in the mobile environment, a wide variety of use cases are therefore conceivable, such as the detection of correct motion sequences in the sports and health sector or the monitoring and automated alerting of security-relevant environments (e.g., demonstrations, festivals). However, this requires an efficient system architecture to perform real-time analysis despite limited hardware power. This paper addresses the approach of skeleton-based activity recognition on smartphones, where motion vectors of detected skeleton points are analyzed for their spatial and temporal expression rather than pixel-based information. In this process, the 3D-bone points of a recognized person are extracted using the AR framework integrated in the operating system and their motion data is analyzed in real time using a self-trained RNN. This purely numerical approach enables time-efficient real-time processing and activity classification. This system makes it possible to recognize a person in a live video stream recorded with a smartphone and classify the activity performed. By successfully deploying the system in several field tests, it can be shown both that the described approach works in principle and that it can be transferred to a resource-constrained mobile environment.</jats:p>},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

A major focus in computer vision research is the recognition of human activity based on visual information from audiovisual data using artificial intelligence. In this context, researchers are currently exploring image-based approaches using 3D CNNs, RNNs, or hybrid models with the intent of learning multiple levels of representation and abstraction that enable fully automated feature extraction and activity analysis based on them. Unfortunately, these architectures require powerful hardware to achieve the most real-time processing possible, making them difficult to deploy on smartphones. However, many video recordings are increasingly made with smartphones, so immediate classification of performed human activities and their tagging already during video recording would be useful for a variety of use cases. Especially in the mobile environment, a wide variety of use cases are therefore conceivable, such as the detection of correct motion sequences in the sports and health sector or the monitoring and automated alerting of security-relevant environments (e.g., demonstrations, festivals). However, this requires an efficient system architecture to perform real-time analysis despite limited hardware power. This paper addresses the approach of skeleton-based activity recognition on smartphones, where motion vectors of detected skeleton points are analyzed for their spatial and temporal expression rather than pixel-based information. In this process, the 3D-bone points of a recognized person are extracted using the AR framework integrated in the operating system and their motion data is analyzed in real time using a self-trained RNN. This purely numerical approach enables time-efficient real-time processing and activity classification. This system makes it possible to recognize a person in a live video stream recorded with a smartphone and classify the activity performed. By successfully deploying the system in several field tests, it can be shown both that the described approach works in principle and that it can be transferred to a resource-constrained mobile environment.

127.

Hösel, Claudia; Baumgart, Matthias; Platte, Benny; Roschke, Christian; Ritter, Marc

Exploratory Analysis of the News in Easy Language (NiEL) Corpus to Identify Characteristic Patterns for Natural Language Processing Proceedings Article

In: Communications in Computer and Information Science, 2023.

@inproceedings{hosel_exploratory_2023,

title = {Exploratory Analysis of the News in Easy Language (NiEL) Corpus to Identify Characteristic Patterns for Natural Language Processing},

author = {Claudia Hösel and Matthias Baumgart and Benny Platte and Christian Roschke and Marc Ritter},

doi = {10.1007/978-3-031-36004-6_57},

year  = {2023},

date = {2023-01-01},

booktitle = {Communications in Computer and Information Science},

abstract = {While comprehensive corpora are available for resource-rich languages such as English in different domains, which can be made usable for natural language processing (NLP) applications, this is not the case for resource-poor languages. Parallel or monolingual corpora must first be created and adequately processed in order to make them usable for later NLP applications. In the past, selected variants of a standard language were increasingly identified as resource-poor languages and corresponding resources were created. The German Easy Language, as a highly simplified variant of the Standard German language, can be defined as a resource-poor language, since here, too, hardly any NLP-suitable corpora are available. In this paper, we present the News in Easy Language (NiEL) corpus, a monolingual text resource for German Easy Language. By means of exploratory analysis using selected NLP tools, characteristic patterns for Easy Language can be derived at both word and sentence level. The identified patterns of Easy Language can be compared in perspective with patterns from standard language texts. Our results show that multiple tools from the NLP domain are suitable for German Easy Language as well as for German Standard Language. Features like word variance, sentence depth but also average word and sentence length can be distinguished. The features extracted in this way are suitable for the development of models, whereby initial implications for the natural language processing of Easy Language can be derived. The results form an important basis for further research in the domain of Easy Language. As a low-resource language that has been primarily analyzed intellectually, another added value of our work also lies in the implications for natural processing of plain language derived from the exploratory analysis of the corpus.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

126.

Becher, Michelle; Friedrich, Anna; Welscher, Xavier; Clausnitzer, Serena; Hubert, Ronja; Laura, Leske; Beger, Paula; Rendtel, Catriona; Hoffmann, Benjamin; Heinzig, Manuel; Schmidt, Anke; Andrä, Kristina; Roschke, Christian; Ritter, Marc

Eine explorative Studie zur Gesundheitsbewertung und -tracking mit multimodaler Sensorik Proceedings Article

In: Tagungsband zur 23. Nachwuchswissenschaftler*innenkonferenz, 2023.

Abstract | BibTeX

@inproceedings{becher_explorative_2023,

title = {Eine explorative Studie zur Gesundheitsbewertung und -tracking mit multimodaler Sensorik},

author = {Michelle Becher and Anna Friedrich and Xavier Welscher and Serena Clausnitzer and Ronja Hubert and Leske Laura and Paula Beger and Catriona Rendtel and Benjamin Hoffmann and Manuel Heinzig and Anke Schmidt and Kristina Andrä and Christian Roschke and Marc Ritter},

year  = {2023},

date = {2023-01-01},

booktitle = {Tagungsband zur 23. Nachwuchswissenschaftler*innenkonferenz},

abstract = {Besonders im Bereich E-Health trägt die technische Entwicklung zur schnelleren<br />Erkennung von Problemen bei und eröffnet neue digitale Therapiemöglichkeiten (Chen<br />& Yang, 2020). Im Rahmen des Lehrformats "Digital Skills and Products" (Ritter et al.,<br />2019) wurde ein entsprechendes Projekt an der Hochschule Mittweida über drei<br />Semester umgesetzt. Das Ziel bestand in der Entwicklung einer iOS-Applikation, die<br />Informationen zur Körperhaltung eines Menschen erfasst und zu Kontroll- und<br />Verbesserungszwecken verständlich visualisiert. Das entstandene Analyseframework<br />xPose extrahiert dazu Skelettdaten aus Bildern und fusioniert sie mit weiteren<br />Vitaldaten. Vor der eigentlichen Evaluation fand ein Vortest statt, um die Wirksamkeit<br />aller beteiligten Geräte zu überprüfen. Anschließend befasste sich eine erste Evaluation<br />mit der Einschätzung des User Interface mittels AttrakDiff. Eine zweite Evaluation diente<br />zur Prüfung der Genauigkeit der automatisch gemessenen Daten im Vergleich mit<br />manuellen Messungen. Die Ergebnisse zeigen, dass die zum Training eingesetzte<br />provibes-Schwingungsplattform tendenziell entspannend wirkt, eine Normalisierung<br />der Gelenkbeweglichkeit erfolgt und die professionell erhobenen Messwerte anteilig mit<br />den semi-automatisierten Messungen von Apples ARKit vergleichbar sind.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

125.

Schlosser, Max; Urban, Mona; Tran, Duc; Nobre, Carolina Rocha; Kreißig, Peter; Labude, Susan; Breck, Dominik; Roschke, Christian; Ritter, Marc; Vodel, Matthias

Evaluation of a Learning Application Designed to Improve Motivation and Engagement of Students in Higher Education Proceedings Article

In: International Journal of Intelligent Computing Research, 2023.

124.

Welk, Josefine

Stress or No Stress? This is the Question: Life-like Stress Detection in Different Domains using Different Hardware Solutions Proceedings Article

In: 2023.

123.

Weidner, Fanny; Bischoff, Laurenz; Bätz, Johannes; Schöppach, Robin; Belov, Gleb; Meineke, Gleb; Belov, Peter; Meineke, Peter; Kambach, Kevin; Mitsch, Jannick; Motuzov, Andreas; Mieth, Martin; Schulz, Andreas; Weidlich-Rau, Melissa; Roschke, Christian; Vodel, Matthias; Kühn, Alexander Thomas; Czauderna, Tobias; Müssig, Daniel; Heinzig, Manuel; Lässig, Jörg; Ritter, Marc

A VR Office Applying Modern Search and Filter Concepts for Knowledge Workers Proceedings Article

In: Lecture Notes in Computer Science, 2023.