@misc{13337, abstract = {{In manufacturing systems with a job shop organization, queues between workstations create an intermittent process flow, allowing workers to schedule tasks entering the queue based on their needs and preferences. The resulting scheduling autonomy of individual workers often leads to inefficiencies in the overall production process due to the loss of control. Companies are therefore increasingly using algorithmic scheduling systems to assign task sequences to workers, thereby drastically reducing their autonomy and negatively affecting their job performance and well-being. This paper extends the existing flexible job shop scheduling problem by sequencing preferences (FJSPSP) to incorporate a human-centered perspective by predicting workers’ task sequencing decisions using learning-to-rank (LTR) methods. By learning workers’ individual task sequencing preferences, it becomes possible to predict the processing sequence based on task characteristics. The scheduling algorithm for the FJSPSP presented in the paper incorporates workers’ learned sequencing preferences as constraints. Considering workers’ learned task sequencing decisions, the FJSPSP optimizes only task assignments to maintain workers’ autonomy over task sequences. The contributions of this paper are fourfold, namely, (1) presenting an approach to elicit sequencing decision datasets from workers, (2) demonstrating the successful prediction of humans’ and an actual worker’s task sequencing decisions with LTR, (3) formulating the FJSPSP variant that integrates workers’ sequencing preferences as constraints and proving its effectiveness in a simulation study, and (4) consolidating these steps into an explainable artificial intelligence (XAI)- and LTR-enabled sociotechnical system design framework. The paper closes with a discussion of the overall methodology and future research perspectives.}}, author = {{Herrmann, Jan-Phillip and Tackenberg, Sven and Srirajan, Tharsika Pakeerathan and Nitsch, Verena}}, booktitle = {{Journal of Manufacturing Systems}}, issn = {{0278-6125}}, keywords = {{Human-centered scheduling, Job autonomy, Learning-to-rank, Flexible job shop scheduling, Human decision-making, Explainable artificial intelligence}}, number = {{2}}, pages = {{541--560}}, publisher = {{Elsevier BV}}, title = {{{Incorporating scheduling autonomy of workers into flexible job shop scheduling: Learning and balancing decentralized task sequencing decisions with overall scheduling performance}}}, doi = {{10.1016/j.jmsy.2025.12.020}}, volume = {{84}}, year = {{2026}}, } @misc{12991, abstract = {{Introduction: This study examines the perception of presence among students using virtual reality (VR) compared to iPads. The research aimed to provide deeper insights into students' immersive experiences and identify factors influencing perceived presence. Method and results: Using a comparative approach, we show a significant difference between the two groups, with students using VR reporting a heightened sense of immersion. Additionally, participant's previous experience with immersive VR affect the presence significantly, while we report no detectable effects of age and gender. Discussion: These findings contribute to the discussion on innovative teaching methods, supporting the development of more effective and inclusive virtual learning environments.}}, author = {{Austermann, Christine and von Blanckenburg, Florin and von Blanckenburg, Korbinian and Utesch, Till}}, booktitle = {{Frontiers in Education}}, issn = {{2504-284X}}, keywords = {{virtual reality (VR), presence perception, immersion, learning environment, classroom experiment}}, publisher = {{Frontiers Media}}, title = {{{Exploring the impact of virtual reality on presence: findings from a classroom experiment}}}, doi = {{10.3389/feduc.2025.1560626}}, volume = {{10}}, year = {{2025}}, } @misc{13349, abstract = {{In weakly-structured work processes, workers are free to decide in which sequence to process their tasks. Predicting their decision-making helps plan production more accurately while preserving workers’ autonomy. The factors that influence workers’ decision-making depend on the manufacturing process and person considered, and they must be newly collected for each use case. This paper identifies the factors influencing workers when deciding in which sequence to process manufacturing tasks in a medium-sized hydraulic cylinder manufacturer. Five workers and two lead workers were observed and interviewed during several work shifts about influencing factors. The authors propose a new interview technique called indifference testing to overcome subjects’ difficulty articulating their decision-making process. Collected factors were categorized using inductive category formation and context analysis. The analyses identified 75 influencing factors comprising 37 decision attributes and 38 decision rules. The identified decision attributes indicate that worker preferences are influenced by attributes from the classical scheduling literature and attributes related to worker well-being, circadian rhythms, and ergonomics. The identified decision rules are useful constituents of more complex preference functions. The decision attributes and rules enable the construction of machine learning models to predict workers’ task sequencing decisions in job shops. Potential applications include systematically eliminating or controlling influencing factors through workplace design measures to increase worker well-being and optimality of their decisions.}}, author = {{Herrmann, Jan-Phillip and Tackenberg, Sven and Burgert, Florens and Nitsch, Verena}}, booktitle = {{Procedia Computer Science}}, issn = {{1877-0509}}, keywords = {{Task Sequencing, Manufacturing, Learning To Rank, Scheduling Human Factors, Case Study}}, pages = {{1820--1829}}, publisher = {{Elsevier BV}}, title = {{{Influencing factors on worker task sequencing decisions in a medium-sized hydraulic cylinder manufacturer}}}, doi = {{10.1016/j.procs.2025.01.244}}, volume = {{253}}, year = {{2025}}, } @misc{13350, abstract = {{In einer humanzentrierten Kleinserien- und Einzelfertigung mit Werkstattorganisation verfügen Fertigungsmitarbeitende häufig über eine hohe Autonomie und Entscheidungsfreiheit. Das Zusammenspiel individueller Planungsstrategien von Mitarbeitenden innerhalb eines Fertigungsprozesses kann sich positiv als auch negativ auf das Erreichen der produktionslogistischen Zielgrößen auswirken. In diesem Beitrag wird eine Variante des Flexible Job Shop Scheduling Problems vorgestellt, welches das Entscheidungsverhalten autonomer Arbeitspersonen bezüglich der Bearbeitungsreihenfolgebildung berücksichtigt. Weiterhin wird die Ableitung arbeitsorganisatorischer Gestaltungsempfehlungen durch die Analyse individueller Planungsstrategien von Arbeitspersonen mittels Methoden der erklärbaren künstlichen Intelligenz demonstriert. Betrachtungsgegenstand der Analyse ist die Entscheidung von Arbeitspersonen, in welcher Reihenfolge sie ihre täglichen Aufgaben abarbeiten. Der Beitrag schließt mit einer Diskussion über die Nutzung der vorgestellten Verfahren zur Ableitung von arbeitsorganisatorischen Gestaltungsempfehlungen.}}, author = {{Herrmann, Jan-Phillip and Tackenberg, Sven and Nitsch, Verena}}, booktitle = {{Arbeit 5.0: Menschzentrierte Innovationen für die Zukunft der Arbeit}}, keywords = {{Flexible Job Shop Scheduling, Learning To Rank, Erklärbare Künstliche Intelligenz, Planungsautonomie, Simulation}}, location = {{Aachen}}, pages = {{415--420}}, publisher = {{GfA-Press}}, title = {{{Analyse der Entscheidungsfindung von Fertigungsmitarbeitenden durch erklärbare künstliche Intelligenz zur Ableitung arbeitsorganisatorischer Gestaltungsempfehlungen}}}, doi = {{10.61063/FK2025}}, year = {{2025}}, } @misc{11436, abstract = {{Tailored to the students of architecture and interior architecture at the OWL University of Applied Sciences and Arts in Detmold, the project focuses on developing and integrating a digital reflection assistant called “As U know” to complement building physics education. The reflection assistant is introduced in an application-oriented module and brings together a diverse range of learning resources including sample exercises, glossaries, videos, tests, quizzes and more. Special focus is placed on interactive videos that are intended to support the development of problem-specific solutions for the complex requirements arising from the students' own designs. Many architecture and interior architecture students struggle with the challenge of harmonizing the learned principles of building physics with their individual creative design processes. As a result, face-to-face correction discussions offered are often used ineffectively or even avoided by students due to insecurity. To counteract this, "As U know" provides students individual support independent of time and location, helping them prepare effectively for correction discussions. In a survey conducted as part of the project, all users stated that the test version had supported or had rather supported them in applying the required building physics content. Forty six percent reported feeling less or tendentially less inhibited in taking advantage of the face-to-face corrections.}}, author = {{von Borstel, Ruth and Schwickert, Susanne}}, booktitle = {{International Conference The Future of Education, Edition 14}}, keywords = {{digital reflection assistant, blended learning, ndividual support, interactive video}}, location = {{Florence}}, publisher = {{Filodiritto Publisher}}, title = {{{Development and Integration of a Digital Reflection Assistant as a Complement to Building Physics Education}}}, doi = {{10.26352/I620_2384-9509}}, year = {{2024}}, } @misc{11439, abstract = {{Tailored to the students of architecture and interior architecture at the OWL University of Applied Sciences and Arts in Detmold, the project focuses on developing and integrating a digital reflection assistant called “As U know” to complement building physics education. The reflection assistant is introduced in an application-oriented module and brings together a diverse range of learning resources including sample exercises, glossaries, videos, tests, quizzes and more. Special focus is placed on interactive videos that are intended to support the development of problem-specific solutions for the complex requirements arising from the students' own designs. Many architecture and interior architecture students struggle with the challenge of harmonizing the learned principles of building physics with their individual creative design processes. As a result, face-to-face correction discussions offered are often used ineffectively or even avoided by students due to insecurity. To counteract this, "As U know" provides students individual support independent of time and location, helping them prepare effectively for correction discussions. In a survey conducted as part of the project, all users stated that the test version had supported or had rather supported them in applying the required building physics content. Forty six percent reported feeling less or tendentially less inhibited in taking advantage of the face-to-face corrections.}}, author = {{von Borstel, Ruth and Schwickert, Susanne}}, booktitle = {{Future of Education, Web of Science and Scopus}}, issn = {{2420-9732}}, keywords = {{digital reflection assistant, blended learning, individual support, interactive video}}, location = {{Florenz}}, publisher = {{Pixel}}, title = {{{Development and integration of a digital reflection assistant as a complement to building physics education}}}, year = {{2024}}, } @misc{11808, abstract = {{The application of hydrogen for energy storage and as a vehicle fuel necessitates efficient and effective storage technologies. In addition to traditional cryogenic and high-pressure tanks, an alternative approach involves utilizing porous materials such as activated carbons within the storage tank. The adsorption behaviour of hydrogen in porous structures is described using the Dubinin-Astakhov isotherm. To model the flow of hydrogen within the tank, we rely on the equations of mass conservation, the Navier-Stokes equations, and the equation of energy conservation, which are implemented in a computational fluid dynamics code and additional terms account for the amount of hydrogen involved in sorption and the corresponding heat release. While physical models are valuable, data-driven models often offer computational advantages. Based on the data from the physical adsorption model, a data-driven model is derived using various machine learning techniques. This model is then incorporated as source terms in the governing conservation equations, resulting in a novel hybrid formulation which is computationally more efficient. Consequently, a new method is presented to compute the temperature and concentration distribution during the charging and discharging of hydrogen tanks and identifying any limiting phenomena more easily.}}, author = {{Klepp, Georg Heinrich}}, booktitle = {{Energy : the international journal ; technologies, resources, reserves, demands, impact, conservation, management, policy}}, issn = {{1873-6785}}, keywords = {{Hydrogen storage, Adsorption, Activated carbon, Machine learning, Simulation, Computational fluid dynamics}}, publisher = {{Elsevier BV}}, title = {{{Modelling activated carbon hydrogen storage tanks using machine learning models}}}, doi = {{10.1016/j.energy.2024.132318}}, volume = {{306}}, year = {{2024}}, } @misc{12167, abstract = {{Deployment of Level 3 and Level 4 autonomous vehicles (AVs) in urban environments is significantly constrained by adverse weather conditions, limiting their operation to clear weather due to safety concerns. Ensuring that AVs remain within their designated Operational Design Domain (ODD) is a formidable challenge, making boundary monitoring strategies essential for safe navigation. This study explores the critical role of an ODD monitoring system (OMS) in addressing these challenges. It reviews various methodologies for designing an OMS and presents a comprehensive visualization framework incorporating trigger points for ODD exits. These trigger points serve as essential references for effective OMS design. The study also delves into a specific use case concerning ODD exits: the reduction in road friction due to adverse weather conditions. It emphasizes the importance of contactless computer vision-based methods for road condition estimation (RCE), particularly using vision sensors such as cameras. The study details a timeline of methods involving classical machine learning and deep learning feature extraction techniques, identifying contemporary challenges such as class imbalance, lack of comprehensive datasets, annotation methods, and the scarcity of generalization techniques. Furthermore, it provides a factual comparison of two state-of-the-art RCE datasets. In essence, the study aims to address and explore ODD exits due to weather-induced road conditions, decoding the practical solutions and directions for future research in the realm of AVs.}}, author = {{Subramanian, Ramakrishnan and Büker, Ulrich}}, booktitle = {{Eng : advances in engineering}}, issn = {{2673-4117}}, keywords = {{autonomous vehicles, operational design domain, computer vision, machine learning, road surface detection}}, number = {{4}}, pages = {{2778--2804}}, publisher = {{MDPI AG}}, title = {{{Study of Contactless Computer Vision-Based Road Condition Estimation Methods Within the Framework of an Operational Design Domain Monitoring System}}}, doi = {{10.3390/eng5040145}}, volume = {{5}}, year = {{2024}}, } @misc{12816, abstract = {{Medical images need annotations with high-level semantic descriptors, so that domain experts can search for the desired dataset among an enormous volume of visual media within a Medical Data Integration Center. This article introduces a processing pipeline for storing and annotating DICOM and PNG imaging data by applying Elasticsearch, S3 and Deep Learning technologies. The proposed method processes both DICOM and PNG images to generate annotations. These image annotations are indexed in Elasticsearch with the corresponding raw data paths, where they can be retrieved and analyzed.}}, author = {{Cheng, Ka Yung and Pazmino, Santiago and Bergh, Bjoern and Lange-Hegermann, Markus and Schreiweis, Bjorn}}, booktitle = {{19th World Congress on Medical and Health Informatics (MEDINFO)}}, isbn = {{978-1-64368-456-7}}, issn = {{1879-8365}}, keywords = {{Medical image retrieval, data lake, DICOM, deep learning, elasticsearch}}, location = {{Sydney, AUSTRALIA}}, pages = {{1388--1389}}, publisher = {{IOS Press, Incorporated}}, title = {{{An Image Retrieval Pipeline in a Medical Data Integration Center.}}}, doi = {{10.3233/SHTI231208}}, volume = {{310}}, year = {{2024}}, } @misc{12904, abstract = {{It is crucial to identify defective machine components in production to ensure quality. Some components generate heat when defective, so automating the inspection process with a thermal imaging camera can provide qualitative measurements. This work aims to use computer vision methods to locate these components in thermal images. Since there is currently no comparison of object detection and semantic segmentation algorithms for this use case, this study compares different architectures with the goal of localising these components for further defect inspection. Moreover, as there are currently no datasets for this use case, this study contributes a novel annotated dataset of thermal images of combine harvester components. The different algorithms are evaluated based on the quality of their predictions and their suitability for further defect inspection. As semantic segmentation and object detection cannot be directly compared with each other, custom weighted metrics are used. The architectures evaluated include RetinaNet, YOLOV8 Detector, DeepLabV3+, and SegFormer. Based on the experimental results, semantic segmentation outperforms object detection regarding the use case, and the SegFormer architecture achieves the best results with a weighted MeanIOU of 0.853. }}, author = {{Senke, Hanna and Sprute, Dennis and Büker, Ulrich and Flatt, Holger}}, booktitle = {{Forum Bildverarbeitung 2024 = Image Pocessing Forum 2024}}, editor = {{Längle, Thomas and Heizmann, Michael}}, isbn = {{978-3-7315-1386-5}}, keywords = {{industrial quality assurance, deep learning architectures, object localisation, Thermal images}}, location = {{Karlsruhe}}, pages = {{71--82}}, publisher = {{KIT Scientific Publishing}}, title = {{{Deep learning-based localisation of combine harvester components in thermal images}}}, doi = {{10.58895/ksp/1000174496-7}}, year = {{2024}}, } @misc{12993, abstract = {{In computer science and related technical fields, researchers, educators, and practitioners are continuously automating recurring tasks for high efficiency in a wide variety of fields. In higher education, such tasks that educators face are the recurring review and assessment process of students' programming coursework. Thus, various attempts exist to automate the assessment and feedback generation for course homework and practicals in higher education. Those approaches for automated programming task assessment often comprise running automated tests to check for limited functional correctness and potentially style checking for various violations (LINTing). Educators familiar with large-scale automated task assessment are likely used to seeing hard-coded solutions specifically or accidentally designed to just pass the required tests, ignoring or misinterpreting the actual task requirements. Detecting such issues in arbitrary code is non-trivial and an ongoing research topic in software engineering. Software engineering research has yielded various semantic analysis frameworks, such as GitHub's CodeQL, which can be adapted for programming task assessment. We present a work-in-progress programming task analysis framework which employs CodeQL's analysis technology to identify the actual use of task-description-mandated syntactic and semantic elements such as loop structures or the use of mandated data blocks in branching conditions. This allows extending existing course work analysis frameworks to include a semantic check of an uploaded program which exceeds the relatively simple set of input-output test cases provided by unit tests. We use a running example of entry level programming tasks and several solution attempts to introduce and explain our proposed control flow and data flow -based analysis method. We discuss the benefits of including semantic analysis as an additional method in the automated programming task assessment toolbox. Our main contribution is the adaptation of an semantic analysis code framework to analyse syntactic and semantic components in students' programming coursework.}}, author = {{Wehmeier, Leon and Eilermann, Sebastian and Niggemann, Oliver and Deuter, Andreas}}, booktitle = {{FIE 2023 : College Station, TX, USA, October 18-21, 2023 : conference proceedings / 2023 IEEE Frontiers in Education Conference (FIE)}}, isbn = {{979-8-3503-3643-6}}, keywords = {{Codes, Electronic learning, Soft sensors, Semantics, Education, Syntactics, Task analysis}}, location = {{Texas}}, publisher = {{IEEE}}, title = {{{Task-fidelity Assessment for Programming Tasks Using Semantic Code Analysis}}}, doi = {{10.1109/fie58773.2023.10342916}}, year = {{2024}}, } @misc{13576, abstract = {{Background Many young women are dissatisfied with their bodies. This study investigated the effect on current body dissatisfaction levels of a newly developed evaluative conditioning procedure that paired self-similar and self-dissimilar images of bodies with positive and neutral affective images, respectively. We hypothesized that learning the contingency that self-similar bodies predict positive affectivity is one process that could aid in explaining how these procedures function. Methods Adult women without disordered eating pathology participated in an online experiment with random assignment to an intervention or a control condition. All participants initially rated body images in self-similarity and were subsequently asked to categorize positive and neutral images by valence as quickly and accurately as possible. In the intervention condition, self-similar bodies systematically preceded positive images, and self-dissimilar images preceded neutral images, creating a similar body → positive contingency. Pairings in the control condition were unsystematic such that no contingency was present. We measured categorization latencies and accuracies to infer contingency learning as well as current body dissatisfaction immediately before and after exposure to the pairings. All participants further completed measures of trait body image concerns and disordered eating psychopathology at baseline, which we examined as moderators of an expected relation between condition assignment, contingency learning, and body dissatisfaction improvements. Results We analyzed data from N = 173 women fulfilling the inclusion criteria. Moderated mediation analyses showed that assignment to the intervention (vs. control) condition predicted increased similar body → positive contingency learning, which in turn predicted improved body dissatisfaction post-intervention, but only among women with higher pre-existing trait body image concerns or disordered eating levels. Conclusions The findings point toward the relevancy of further exploring the utility of pairing procedures. Similar body → positive contingency learning predicted improved body dissatisfaction in individuals with normatively high body image concerns, which suggests pairing procedures could help inform future research on reducing body dissatisfaction.}}, author = {{Dumstorf, Katharina and Halbeisen, Georg and Paslakis, Georgios}}, booktitle = {{Journal of Eating Disorders}}, issn = {{2050-2974}}, keywords = {{Evaluative conditioning, Body image, Eating disorders, Contingency learning, Psychotherapy, Pairing procedures}}, number = {{1}}, publisher = {{BioMed Central}}, title = {{{How evaluative pairings improve body dissatisfaction in adult women: evidence from a randomized-controlled online study}}}, doi = {{10.1186/s40337-024-00975-4}}, volume = {{12}}, year = {{2024}}, } @misc{13616, abstract = {{Objective Body dissatisfaction is an important risk factor for developing eating disorders. This study investigated whether pairing images of normatively “healthy” weight bodies of women with positive stimuli, and images of bodies outside the healthy range (e.g., underweight) with neutral stimuli, could improve body dissatisfaction. Methods We compared behavioral and rating data from 121 adult women who participated in an online study and were randomly assigned to an intervention condition (in which healthy body mass predicted positive stimuli) or a control condition (with no contingency between body mass and stimulus valence). Results Behavioral data showed that women in the intervention condition, compared to the control condition, learned to associate healthy bodies with positive valence. Having learned to associate healthy bodies with positive valence, in turn, predicted reductions in body dissatisfaction. The intervention and control conditions were not directly associated with changes in body dissatisfaction. Conclusion Learning to associate healthy bodies with any positive stimuli could be a relevant mechanism for understanding and predicting improvements in women's body dissatisfaction. Further research is required regarding the impact of contingency learning on the evaluation of other bodies, and the selection of other bodies for body-related social comparison processes.}}, author = {{Tullius, Elena M. and Halbeisen, Georg and Paslakis, Georgios}}, booktitle = {{Journal of Psychiatric Research}}, issn = {{1879-1379 }}, keywords = {{Evaluative conditioning, Body image, Eating disorders, Contingency learning, Psychotherapy}}, pages = {{340--348}}, publisher = {{Elsevier BV}}, title = {{{Can evaluative pairings of others’ bodies improve body dissatisfaction indirectly? A randomized-controlled online study with adult women}}}, doi = {{10.1016/j.jpsychires.2024.11.012}}, volume = {{180}}, year = {{2024}}, } @misc{11409, abstract = {{The current era, characterized by rapid digitalization, globalization and environmental issues, poses unique challenges and opportunities for both the educational sector and professional development. Increasingly, the research community calls for future-oriented skills as well as attitudes and values as underlying implicit concepts in order to meet the needs of today’s complex demands. These skills and implicit concepts include responsibility, inclusiveness, reflexivity, anticipation, data literacy or digital and interdisciplinary working. Some of them are based on facts and are therefore teachable, while others seem to be a matter of personal attitude and socialization and are therefore difficult to convey. In this paper we suggest educators to change their specialized knowledge-teaching settings into transdisciplinary learning contexts [1] and thus enabling transformative, situated, experiential and informal learning. We provide theoretical examples in which these didactic methodologies seem to be effective in order to impart these skills and reinforce the underlying implicit concepts. We will dive deeper into these arguments during the conference, while participants are encouraged to discuss the various elements that influence the concepts in the context of transdisciplinary learning. (DIPF/Orig.); Die heutige Zeit, die durch eine rasante Digitalisierung, Globalisierung und Umweltprobleme gekennzeichnet ist, stellt sowohl den Bildungssektor als auch die berufliche Entwicklung vor einzigartige Herausforderungen und Chancen. In der Forschung werden zunehmend zukunftsorientierte Fähigkeiten sowie Einstellungen und Werte als zugrundeliegende implizite Konzepte gefordert, um den komplexen Anforderungen von heute gerecht zu werden. Zu diesen Fähigkeiten und impliziten Konzepten gehören Verantwortungsbewusstsein, Inklusivität, Reflexivität, Antizipation, Datenkompetenz oder digitales und interdisziplinäres Arbeiten. Einige von ihnen basieren auf Fakten und sind daher lehrbar, während andere eine Frage der persönlichen Einstellung und Sozialisation zu sein scheinen und daher schwer zu vermitteln sind. In diesem Beitrag schlagen wir Pädagogen vor, ihre spezialisierten Wissenslehrsettings in transdisziplinäre Lernkontexte [1] zu verwandeln und so transformatives, situiertes, erfahrungsbasiertes und informelles Lernen zu ermöglichen. Wir stellen theoretische Beispiele vor, in denen diese didaktischen Methoden effektiv zu sein scheinen, um diese Fähigkeiten zu vermitteln und die zugrunde liegenden impliziten Konzepte zu stärken. Wir werden diese Argumente während der Konferenz vertiefen, während die Teilnehmer aufgefordert sind, die verschiedenen Elemente zu diskutieren, die die Konzepte im Kontext des transdisziplinären Lernens beeinflussen. (Autor)}}, author = {{Alavi, Marie and Schmohl, Tobias}}, booktitle = {{Conference proceedings. 13th international conference "The future of education". Hybrid edition, 29-30 June 2023}}, isbn = {{979-12-80225-59-7}}, issn = {{2384-9509}}, keywords = {{Transformation, Lernen, Methodologie, Interdisziplinarität, Informelles Lernen, Lebenslanges Lernen, Hochschulbildung, Zukunftsorientierung, Kompetenz, Learning, Methodology, Interdisciplinarity, Informal learning, Life long learning, Life-long learning, Lifelong learning, Higher education, University level of education, Future orientation, Competency}}, location = {{Bologna}}, pages = {{5 S.}}, publisher = {{Filodiritto Editore}}, title = {{{Transformative learning. Methodological and conceptual prerequisites for future-oriented skill-building}}}, doi = {{https://doi.org/10.25656/01:27907}}, year = {{2023}}, } @misc{10216, abstract = {{Wet granulation is a frequent process in the pharmaceutical industry. As a starting point for numerous dosage forms, the quality of the granulation not only affects subsequent production steps but also impacts the quality of the final product. It is thus crucial and economical to monitor this operation thoroughly. Here, we report on identifying different phases of a granulation process using a machine learning approach. The phases reflect the water content which, in turn, influences the processability and quality of the granule mass. We used two kinds of microphones and an acceleration sensor to capture acoustic emissions and vibrations. We trained convolutional neural networks (CNNs) to classify the different phases using transformed sound recordings as the input. We achieved a classification accuracy of up to 90% using vibrational data and an accuracy of up to 97% using the audible microphone data. Our results indicate the suitability of using audible sound and machine learning to monitor pharmaceutical processes. Moreover, since recording acoustic emissions is contactless, it readily complies with legal regulations and presents Good Manufacturing Practices.}}, author = {{Fulek, Ruwen and Ramm, Selina and Kiera, Christian and Pein-Hackelbusch, Miriam and Odefey, Ulrich}}, booktitle = {{Pharmaceutics}}, issn = {{1999-4923 }}, keywords = {{wet granulation, acoustic classification, machine learning, convolutional neural networks}}, number = {{8}}, publisher = {{MDPI}}, title = {{{A machine learning approach to qualitatively evaluate different granulation phases by acoustic emissions}}}, doi = {{https://doi.org/10.3390/pharmaceutics15082153}}, volume = {{15}}, year = {{2023}}, } @misc{12785, abstract = {{Due to the demographic aging of society, the demand for skilled caregiving is increasing. However, the already existing shortage of professional caregivers will exacerbate in the future. As a result, family caregivers must shoulder a heavier share of the care burden. To ease the burden and promote a better work-life balance, we developed the Digital Case Manager. This tool uses machine learning algorithms to learn the relationship between a care situation and the next care steps and helps family caregivers balance their professional and private lives so that they are able to continue caring for their family members without sacrificing their own jobs and personal ambitions. The data for the machine learning model are generated by means of a questionnaire based on professional assessment instruments. We implemented a proof-of-concept of the Digital Case Manager and initial tests show promising results. It offers a quick and easy-to-use tool for family caregivers in the early stages of a care situation.}}, author = {{Wunderlich, Paul and Wiegräbe, Frauke and Dörksen, Helene}}, booktitle = {{INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH}}, issn = {{1660-4601}}, keywords = {{machine learning, healthcare, case management, caring, multi-label classification}}, number = {{2}}, publisher = {{MDPI}}, title = {{{Digital Case Manager-A Data-Driven Tool to Support Family Caregivers with Initial Guidance}}}, doi = {{10.3390/ijerph20021215}}, volume = {{20}}, year = {{2023}}, } @misc{12806, abstract = {{Cyber-Physical Systems (CPS) play an essential role in today’s production processes, leveraging Artificial Intelligence (AI) to enhance operations such as optimization, anomaly detection, and predictive maintenance. This article reviews a cognitive architecture for Artificial Intelligence, which has been developed to establish a standard framework for integrating AI solutions into existing production processes. Given that machines in these processes continuously generate large streams of data, Online Machine Learning (OML) is identified as a crucial extension to the existing architecture. To substantiate this claim, real-world experiments using a slitting machine are conducted, to compare the performance of OML to traditional Batch Machine Learning. The assessment of contemporary OML algorithms using a real production system is a fundamental innovation in this research. The evaluations clearly indicate that OML adds significant value to CPS, and it is strongly recommended as an extension of related architectures, such as the cognitive architecture for AI discussed in this article. Additionally, surrogate-model-based optimization is employed, to determine the optimal hyperparameter settings for the corresponding OML algorithms, aiming to achieve peak performance in their respective tasks.}}, author = {{Hinterleitner, Alexander and Schulz, Richard and Hans, Lukas and Subbotin, Aleksandr and Barthel, Nils and Pütz, Noah and Rosellen, Martin and Bartz-Beielstein, Thomas and Geng, Christoph and Priss, Phillip}}, booktitle = {{ Applied Sciences : open access journal}}, issn = {{2076-3417}}, keywords = {{machine learning, online algorithms, cyber-physical production systems, surrogate-based optimization}}, number = {{20}}, publisher = {{MDPI AG}}, title = {{{Online Machine Learning and Surrogate-Model-Based Optimization for Improved Production Processes Using a Cognitive Architecture}}}, doi = {{10.3390/app132011506}}, volume = {{13}}, year = {{2023}}, } @misc{13017, abstract = {{The article presents the potentials and capacities of extracurricular activities such as student workshops for strengthening existing curricula and introducing emerging specialised areas, topics, and challenges into architectural higher education. The specific objective of this study is to enhance and test different pedagogical models for learning on the sustainable rehabilitation of mass housing neighbourhoods (MHN), as a specific type of modern heritage, through innovative extracurricular teaching practices based on interdisciplinarity, flexibility, and adaptability. This research presents three student workshops focusing on the rehabilitation of mass housing neighbourhoods (MHN), involving students, academics, and professionals from the field, organised in Germany, Serbia, and North Macedonia in 2022. Moreover, it engages a comparative analysis of the learning formats and approaches developed within this discipline-specific cross-border collaboration. The study provides (1) an insight into the comparative analysis of learning capabilities and (2) the formulation of workshop models supported by diagramming of the workshop structure. The conclusion of the article summarises the findings and highlights the essential aspects for engaging student workshops, as an instrument for generating operational knowledge in the field of mass housing rehabilitation.}}, author = {{Dragutinovic, Anica and Milovanovic, Aleksandra and Stojanovski, Mihajlo and Damjanovska, Tea and Đorđevic, Aleksandra and Nikezic, Ana and Pottgiesser, Uta and Ivanovska Deskova, Ana and Ivanovski, Jovan}}, booktitle = {{Sustainability}}, issn = {{2071-1050}}, keywords = {{extracurricular activities, extracurricular learning formats, student workshops, workshop models, pedagogical models, architectural higher education, mass housing neighbourhoods, sustainable rehabilitation}}, number = {{3}}, publisher = {{MDPI }}, title = {{{Approaching Extracurricular Activities for Teaching and Learning on Sustainable Rehabilitation of Mass Housing: Reporting from the Arena of Architectural Higher Education}}}, doi = {{10.3390/su15032476}}, volume = {{15}}, year = {{2023}}, } @misc{13019, abstract = {{The digital transformation of manufacturing companies is a huge driver of complexity in organizational structures and processes. Challenges such as an increasing number of variants, rapid changes in technology, and a multitude of interfaces between IT systems within companies require changed qualifications in the workforce. Employees lack a profound understanding of the added value that digitalization can bring to the company and themselves. To address these challenges, simulation games are a suitable approach. Simulation games are active learning methods that simulate real systems in an artificial environment. The goal is to give employees the opportunity to gain experience and make decisions without creating a pressure situation or endangering the real production system. This enables them to better understand, evaluate and design real systems. In order to make optimal use of simulation games in manufacturing companies, they should be customized to the company and its employees due to individual processes and structures. This paper presents a procedure model for designing a concept of individualized simulation games for manufacturing companies in the context of digitalization. It starts with the identification of requirements. Subsequently, the requirements of the individual elements are combined into a holistic simulation game. The piloting of the framework is presented using an example from industrial practice.}}, author = {{Machon, Fabian and Gabriel, Stefan and Latos, Benedikt and Holtkötter, Christoph and Lütkehoff, Ben and Asmar, Laban and Kühn, Dr. Arno and Dumitrescu, Prof. Dr. Roman}}, booktitle = {{Procedia CIRP}}, issn = {{2212-8271}}, keywords = {{industry 4.0, digitalization, digital transformation, simulation games, game-based learning, education, employee education, qualification}}, pages = {{1017--1022}}, publisher = {{Elsevier BV}}, title = {{{Design of individual simulation games in manufacturing companies for game-based learning}}}, doi = {{10.1016/j.procir.2023.03.145}}, volume = {{119}}, year = {{2023}}, } @misc{7578, abstract = {{In recent years considerable research efforts have been made to provide evidence for a nexus be-tween game design elements in non-game contexts. Our research presents a new approach to bridge game design elements and educational theory: defining a set of motivational “patterns” used for peda-gogical purposes in university teaching scenarios. To this end, we will build upon preliminary empirical results from a research project called EMPAMOS®. It derived a set of motivational elements frequently used in social game designs. Our hypothesis is that these elements resemble on a structural level and are directly transferable to motivational factors in online education contexts. Focused on cooperative teaching and learning, we develop a curriculum to enable educators to im-plement motivational molecules from game design in their learning settings. The paper presents basic premises and a preliminary structure of the curriculum. By examining educational settings in terms of a “broken game”, we provide a new perspective on the prerequisites for learning at the university level.}}, author = {{Bröker, Thomas and Schmulius, Nina and Schmohl, Tobias and Dulisch, Fabian and Marquardt, Sabrina and Höllen, Max and Voit, Thomas and Zinger, Benjamin}}, booktitle = {{New Perspectives in Science Education}}, keywords = {{cooperative learning, gamification, motivation, train-the-trainer, curriculum}}, location = {{Florenz}}, pages = {{22--26}}, publisher = {{Libreriauniversitaria.it}}, title = {{{What Can Educators Learn from Social Game Design in University Online Teaching?}}}, volume = {{11}}, year = {{2022}}, } @misc{7734, abstract = {{ Der Konferenzbeitrag zeigt den Forschungs- und Technikstand bezüglich des Griff-in-die-Kiste auf. Basierend auf einer Literaturrecherche werden Beispiele für regelbasierte und lernende Verfahren vorgestellt. Anschließend erfolgt eine systematische Gegenüberstellung der Verfahren. Hierfür werden die Anforderungen, die ein Griff-in-die-Kiste-System zu erfüllen hat, dargelegt. Die Kriterien resultieren aus einer Expertenbefragung des produktionstechnischen Umfelds der Weidmüller Gruppe. Neben den Anforderungen werden die Gewichtungen zur Bildung einer Rangfolge ermittelt. Die erarbeiteten Anforderungen dienen anschließend zur Bewertung der regelbasierten und lernenden Verfahren. Die Analyse mündet in einer methodischen Lücke zwischen beiden Paradigmen und stellt die Ausgangsbasis für die weitere Arbeit zur Entwicklung des industriellen Griff-in-die-Kiste dar. Abschließend werden erste Arbeitsergebnisse zur Objekterkennung von Reihenklemmen veröffentlicht. In einer Untersuchung werden die Zuverlässigkeit, die Robustheit sowie die Einrichtdauer einer Objekterkennung mithilfe von Deep Learning ermittelt. Das angestrebte Forschungsergebnis stellt einen Entwicklungsschritt von automatisierten Systemen, die in einem definierten Wirkbereich eigenständig arbeiten, zu autonomen Systemen, die selbstständig auf zeitvariante Größen reagieren, dar.}}, author = {{Stuke, Tobias and Bartsch, Thomas and Rauschenbach, Thomas}}, booktitle = {{Tagungsband AALE 2022: Wissenstransfer im Spannungsfeld von Autonomisierung und Fachkräftemangel}}, editor = {{Härle, Christian and Jäkel, Jens and Sand, Guido}}, keywords = {{Griff-in-die-Kiste, Bildverarbeitung, Robotik, Deep Learning, lernende Verfahren, regelbasierte Verfahren}}, location = {{Pforzheim}}, pages = {{145 – 154}}, publisher = {{Open Access}}, title = {{{Adaptiver Griff-in-die-Kiste – Die methodische Lücke zwischen Forschung und Industrie}}}, doi = {{https://doi.org/10.33968/2022.14}}, year = {{2022}}, } @misc{8888, abstract = {{Diese Arbeit handelt von der Frage, wie Tonaufnahmen-basierte Lernprozesse im Learning Management System der Hochschule für Musik Detmold, Moodle, erweitert werden können. Dazu werden LMS zunächst definiert und anschließend in die Bildungslandschaft eingeordnet. Daraufhin wird der Status Quo betrachtet mit der Feststellung, dass ein Bedarf an Werkzeugen besteht. Dieser Bedarf wurde durch die Programmierung zweier Anwendungen adressiert, die eine Integration im LMS ermöglichen und damit zu einer erhöhten Nutzbarkeit von Tonaufnahmen und musikalischen Inhalten führen sollen. Zum einen ist das eine Implementation des DTW Algorithmus, mittels welchem sich Synchronisationsdaten zwischen zwei verschiedenen Musikdarstellungen desselben Stückes berechnen lassen. Damit ließe sich bspw. ein Interface erstellen, auf dem die Anzeige der Musikwiedergabe mit der Anzeige einer Notenpartitur synchronisiert wird. Die zweite Anwendung fällt in den Bereich des maschinellen Lernens – es wurde ein automatischer Instrumentenklassifizierer geschrieben. Dieser eignet sich zur Erstellung von automatischen Taggings, zwecks Organisation von Daten und Gehörübungen. Die Nutzung einer CNN-Architektur hat sich dabei als effektiv erwiesen: Nach insgesamt 39 Lernepochen und knapp 7 Millionen gelernten Parametern konnte eine Genauigkeit von 95% erzielt werden. Als Datensatz diente die frei verfügbare Aufnahmensammlung des britischen Philharmonia Orchesters (vgl. Thorben Dittes). Im zweiten Kapitel soll ein Abstecken der Zwecke der einzelnen Programme die Designentscheidungen informieren, welche daraufhin erläutert werden. Im dritten Teil wird anschließend mit ScoreTube eine DTW Implementation von Berndt et al. zum Vergleich herangezogen, um die vorliegende Arbeit in den aktuellen Diskurs einzuordnen. Der Beitrag endet mit einer Evaluation der Ergebnisse und einem Ausblick auf potenzielle zukünftige Arbeiten.}}, author = {{Treiber, Dennis}}, keywords = {{learning management system, dynamic time warping, deep learning, convolutional neural network}}, pages = {{53}}, publisher = {{Technische Hochschule Ostwestfalen-Lippe}}, title = {{{Die Verwendung von Tonaufnahmen im LMS : Entwicklung spezifischer digitaler Werkzeuge an Hochschulen.}}}, year = {{2022}}, } @misc{9161, abstract = {{Employees in household-related services have so far been neglected in research and practice. The overall goal of our project is to identify work-related stress of this special target group, develop recommendations, and disseminate them using low-threshold, attractive edutainment offers. In this context, this contribution presents a learning platform design for the special target group of domestic workers, such as gardeners or cleaners. The design is based on a requirements analysis with respect to this special target group, which we as well outline in this contribution.}}, author = {{Grimm, Valentin and Geiger, Laura and Rubart, Jessica and Faller, Gudrun}}, booktitle = {{DELFI 2022 : die 20. Fachtagung Bildungstechnologien der Gesellschaft für Informatik e.V., 12.-14. September 2022, Karlsruhe}}, editor = {{Henning, Peter A. and Striewe, Michael and Wölfel, Matthias}}, isbn = {{978-3-88579-716-6}}, issn = {{1617-5468}}, keywords = {{E-Learning, Minority Group, Gameful Design, Gamification}}, location = {{Karlsruhe, DE}}, pages = {{213--214}}, publisher = {{Gesellschaft für Informatik e.V.}}, title = {{{Requirements and Design of a Training System for Domestic Workers}}}, doi = {{10.18420/delfi2022-037}}, volume = {{P-322}}, year = {{2022}}, } @misc{12817, abstract = {{Sub-optimal control policies in intersection traffic signal controllers (TSC) contribute to congestion and lead to negative effects on human health and the environment. Reinforcement learning (RL) for traffic signal control is a promising approach to design better control policies and has attracted considerable research interest in recent years. However, most work done in this area used simplified simulation environments of traffic scenarios to train RL-based TSC. To deploy RL in real-world traffic systems, the gap between simplified simulation environments and real-world applications has to be closed. Therefore, we propose LemgoRL, a benchmark tool to train RL agents as TSC in a realistic simulation environment of Lemgo, a medium-sized town in Germany. In addition to the realistic simulation model, LemgoRL encompasses a traffic signal logic unit that ensures compliance with all regulatory and safety requirements. LemgoRL offers the same interface as the well-known OpenAI gym toolkit to enable easy deployment in existing research work. To demonstrate the functionality and applicability of LemgoRL, we train a state-of-the-art Deep RL algorithm on a CPU cluster utilizing a framework for distributed and parallel RL and compare its performance with other methods. Our benchmark tool drives the development of RL algorithms towards real-world applications.}}, author = {{Müller, Arthur and Rangras, Vishal and Ferfers, Tobias and Hufen, Florian and Schreckenberg, Lukas and Jasperneite, Jürgen and Schnittker, Georg and Waldmann, Michael and Friesen, Maxim and Wiering, Marco}}, booktitle = {{20th IEEE International Conference on Machine Learning and Applications (ICMLA)}}, editor = {{Wani, M. Arif and Sethi, Ishwar and Shi, Weisong and Qu, Guangzhi and Stan Raicu, Daniela and Jin, Ruoming }}, isbn = {{978-1-6654-4337-1}}, keywords = {{deep reinforcement learning, traffic signal control, intelligent transportation system, traffic simulation}}, location = {{Online}}, pages = {{507--514}}, publisher = {{IEEE}}, title = {{{Towards Real-World Deployment of Reinforcement Learning for Traffic Signal Control}}}, doi = {{10.1109/icmla52953.2021.00085}}, year = {{2022}}, } @article{6689, abstract = {{Free amino nitrogen (FAN) concentrations in beer mash can be determined with machine learning algorithms from near-infrared (NIR) spectra. NIR spectroscopy is an alternative to a classical chemical analysis and allows for the application of inline process quality control. This study investigates the capabilities of different machine learning techniques such as Ordinary Least Squares (OLS) regression, Decision Tree Regressor (DTR), Bayesian Ridge Regression (BRR), Ridge Regression (RR), K-nearest neighbours (KNN) regression as well as Support Vector Regression (SVR) to predict the FAN content in beer mash from NIR spectra. Various pre-processing strategies such as principal component analysis (PCA) and data standardization were used to process NIR data that were used to train the machine learning algorithms. Algorithm training was conducted with NIR data obtained from 16 beer mashes with varying FAN concentrations. The trained models were then validated with 4 beer mashes that were not used for model training. Machine learning algorithms based on linear regression showed the highest prediction accuracy on unpre-processed data. BRR reached a root mean square error of calibration (RMSEC) of 2.58 mg/L (R2 = 0.96) and a prediction accuracy (RMSEP) of 2.81 mg/L (R2 = 0.96). The FAN concentration range of the investigated samples was between approx. 180 and 220 mg/L. Machine learning based NIR spectra analysis is an alternative to classical chemical FAN level determination methods and can also be used as inline sensor system.}}, author = {{Wefing, Patrick and Conradi, Florian and Rämisch, Johannes and Neubauer, Peter and Schneider, Jan}}, issn = {{0723-1520}}, journal = {{Brewing science }}, keywords = {{mashing, NIR, machine learning, FAN}}, number = {{9/10}}, pages = {{107 -- 121}}, publisher = {{Carl}}, title = {{{Determination of free amino nitrogen in beer mash with an inline NIR transflectance probe and data evaluation by machine learning algorithms}}}, doi = {{https://doi.org/10.23763/BrSc21-10wefing}}, volume = {{74}}, year = {{2021}}, } @misc{7519, abstract = {{Increasing consumer engagement is a cornerstone of companies' social media efforts. However, how social media brand engagement behavior affects brand performance remains largely unexplored. We capture engagement along two dimensions - volume and variety - and measure brand performance using consumers' brand attachment, attitudes, and purchase intentions. Based on the power law of practice and combining survey measures with social media data, our analyses reveal a diminishing marginal utility of engagement volume, as the positive impact of engagement behavior on brand outcomes declines at higher engagement levels. However, the variation across performed activities attenuates these diminishing returns on engagement volume. We find consistent evidence for these effects across two studies with 1347 consumers who interacted with different brands. The results question companies' often unidimensional focus on increasing engagement volume. Instead, our findings suggest that to maximize brand performance on social media platforms, companies should also encourage engagement variety.}}, author = {{Schäfers, Tobias and Falk, Tomas and Kumar, Ashish and Schamari, Julia}}, booktitle = {{Journal of Business Research}}, issn = {{1873-7978}}, keywords = {{Social media, Brand engagement, Diminishing marginal utility, Learning curve}}, pages = {{282--294}}, publisher = {{Elsevier}}, title = {{{More of the same? Effects of volume and variety of social media brand engagement behavior}}}, doi = {{10.1016/j.jbusres.2021.06.033}}, volume = {{135}}, year = {{2021}}, } @misc{11803, abstract = {{Sub-optimal control policies in intersection traffic signal controllers (TSC) contribute to congestion and lead to negative effects on human health and the environment. Reinforcement learning (RL) for traffic signal control is a promising approach to design better control policies and has attracted considerable research interest in recent years. However, most work done in this area used simplified simulation environments of traffic scenarios to train RL-based TSC. To deploy RL in real-world traffic systems, the gap between simplified simulation environments and real-world applications has to be closed. Therefore, we propose LemgoRL, a benchmark tool to train RL agents as TSC in a realistic simulation environment of Lemgo, a medium-sized town in Germany. In addition to the realistic simulation model, LemgoRL encompasses a traffic signal logic unit that ensures compliance with all regulatory and safety requirements. LemgoRL offers the same interface as the well-known OpenAI gym toolkit to enable easy deployment in existing research work. To demonstrate the functionality and applicability of LemgoRL, we train a state-of-the-art Deep RL algorithm on a CPU cluster utilizing a framework for distributed and parallel RL and compare its performance with other methods. Our benchmark tool drives the development of RL algorithms towards real-world applications.}}, author = {{Müller, Arthur and Rangras, Vishal and Schnittker, Georg and Waldmann, Michael and Friesen, Maxim and Ferfers, Tobias and Schreckenberg, Lukas and Hufen, Florian and Jasperneite, Jürgen and Wiering, Marco}}, booktitle = {{20th IEEE International Conference on Machine Learning and Applications (ICMLA)}}, editor = {{Wani, M. Arif}}, keywords = {{deep reinforcement learning, traffic signal control, intelligent transportation system, traffic simulation}}, location = {{Pasadena, CA, USA }}, publisher = {{IEEE}}, title = {{{Towards Real-World Deployment of Reinforcement Learning for Traffic Signal Control}}}, doi = {{10.1109/ICMLA52953.2021.00085}}, year = {{2021}}, } @misc{12800, abstract = {{his paper presents the cognitive module of the Cognitive Architecture for Artificial Intelligence (CAAI) in cyber-physical production systems (CPPS). The goal of this architecture is to reduce the implementation effort of artificial intelligence (AI) algorithms in CPPS. Declarative user goals and the provided algorithm-knowledge base allow the dynamic pipeline orchestration and configuration. A big data platform (BDP) instantiates the pipelines and monitors the CPPS performance for further evaluation through the cognitive module. Thus, the cognitive module is able to select feasible and robust configurations for process pipelines in varying use cases. Furthermore, it automatically adapts the models and algorithms based on model quality and resource consumption. The cognitive module also instantiates additional pipelines to evaluate algorithms from different classes on test functions. CAAI relies on well-defined interfaces to enable the integration of additional modules and reduce implementation effort. Finally, an implementation based on Docker, Kubernetes, and Kafka for the virtualization and orchestration of the individual modules and as messaging technology for module communication is used to evaluate a real-world use case.}}, author = {{Strohschein, Jan and Fischbach, Andreas and Bunte, Andreas and Faeskorn-Woyke, Heide and Moriz, Natalia and Bartz-Beielstein, Thomas}}, booktitle = {{The International Journal of Advanced Manufacturing Technology}}, issn = {{1433-3015}}, keywords = {{Cognition, Industry 40, Big data platform, Machine learning, CPPS, Optimization, Algorithm selection, Simulation}}, number = {{11-12}}, pages = {{3513--3532}}, publisher = {{Springer }}, title = {{{Cognitive capabilities for the CAAI in cyber-physical production systems}}}, doi = {{10.1007/s00170-021-07248-3}}, volume = {{115}}, year = {{2021}}, } @inproceedings{4097, abstract = {{The capabilities of object detection are well known, but many projects don’t use them, despite potential benefit. Even though the use of object detection algorithms is facilitated through frameworks and publications, a big issue is the creation of the necessary training data. To tackle this issue, this work shows the design and evaluation of a prototype, which allows users to create synthetic datasets for object detection in images. The prototype is evaluated using YOLOv3 as the underlying detector and shows that the generated datasets are equally good in quality as manually created data. This encourages a wide adoption of object detection algorithms in different areas, since image creation and labeling is often the most time consuming step.}}, author = {{Besginow, Andreas and Büttner, Sebastian and Röcker, Carsten}}, booktitle = {{22nd International Conference on Human-Computer Interaction}}, isbn = {{978-3-030-50343-7}}, keywords = {{Object detection, Synthetic datasets, Machine learning, Deep learning}}, location = {{Copenhagen, Denmark}}, pages = {{178--192}}, publisher = {{Springer}}, title = {{{Making Object Detection Available to Everyone - A Hardware Prototype for Semi-automatic Synthetic Data Generation}}}, doi = {{https://doi.org/10.1007/978-3-030-50344-4_14}}, volume = {{12203}}, year = {{2020}}, } @misc{4100, author = {{Schmohl, Tobias and Schwickert, Susanne and Glahn, Oliver}}, booktitle = {{The Future of Education}}, keywords = {{Artificial Intelligence, intelligent tutoring system, reflection, project-based learning, online-learning, interactive video}}, location = {{Florenz}}, pages = {{309--313}}, publisher = {{Libreriauniversitaria.it}}, title = {{{Conceptual Design of an AI-Based Learning Assistant }}}, doi = {{10.26352/E618_2384-9509}}, year = {{2020}}, } @misc{12807, abstract = {{Writing chorales in the style of Bach has been a music theory exercise for generations of music students. As such it is not surprising that automatic Bach chorale harmonization has been a topic in music technology for decades. We suggest several improvements to current neural network solutions based on musicological insights into human choral composition practices. Evaluations with expert listeners show that the generated chorales closely resemble Bach's harmonization style.}}, author = {{Leemhuis, Alexander and Waloschek, Simon and Hadjakos, Aristotelis}}, booktitle = {{Machine Learning and Knowledge Discovery in Databases : International Workshops of ECML PKDD 2019}}, editor = {{Cellier, Peggy and Driessens, Kurt}}, isbn = {{978-3-030-43886-9}}, issn = {{1865-0937}}, keywords = {{Bach chorale harmonization, Deep learning, Beam search}}, location = {{Würzburg}}, pages = {{462–469}}, publisher = {{Springer International Publishing}}, title = {{{Bacher than Bach? On Musicologically Informed AI-Based Bach Chorale Harmonization}}}, doi = {{10.1007/978-3-030-43887-6_39}}, volume = {{1168}}, year = {{2020}}, } @misc{12812, abstract = {{Discerning unexpected from expected data patterns is the key challenge of anomaly detection. Although a multitude of solutions has been applied to this modern Industry 4.0 problem, it remains an open research issue to identify the key characteristics subjacent to an anomaly, sc. generate hypothesis as to why they appear. In recent years, machine learning models have been regarded as universal solution for a wide range of problems. While most of them suffer from non-self-explanatory representations, Gaussian Processes (GPs) deliver interpretable and robust statistical data models, which are able to cope with unreliable, noisy, or partially missing data. Thus, we regard them as a suitable solution for detecting and appropriately representing anomalies and their respective characteristics. In this position paper, we discuss the problem of automatic and interpretable anomaly detection by means of GPs. That is, we elaborate on why GPs are well suited for anomaly detection and what the current challenges are when applying these probabilistic models to large-scale production data.}}, author = {{Berns, Fabian and Lange-Hegermann, Markus and Beecks, Christian}}, booktitle = {{ Proceedings of the International Conference on Innovative Intelligent Industrial Production and Logistics IN4PL - Volume 1}}, editor = {{Panetto, H. and Madani, K. and Smirnov, A.}}, isbn = {{978-989-758-476-3}}, keywords = {{Anomaly Detection, Gaussian Processes, Explainable Machine Learning, Industry 4.0}}, location = {{Budapest, HUNGARY}}, pages = {{87--92}}, publisher = {{SCITEPRESS - Science and Technology Publications}}, title = {{{Towards Gaussian Processes for Automatic and Interpretable Anomaly Detection in Industry 4.0}}}, doi = {{10.5220/0010130300870092}}, year = {{2020}}, } @misc{13641, abstract = {{The neuro-physiological response to stress has far-reaching implications for learning and memory processes. Here, we examined whether and how the stress-induced release of cortisol, following the socially-evaluated cold pressor test, influenced the acquisition of preferences in an evaluative conditioning (EC) procedure. We found that when the stressor preceded the evaluation phase, cortisol responders showed decreased evaluative conditioning effects. By contrast, impairing effects of a stressor-induced cortisol release before encoding were not found. Moreover, explicit memory was not found to be affected by the stressor or its timing. Implications of the timing-dependent effects of stress-induced cortisol release on EC and the relation between stress and associative memory are discussed.}}, author = {{Halbeisen, Georg and Buttlar, Benjamin and Kamp, Siri-Maria and Walther, Eva}}, booktitle = {{International Journal of Psychophysiology}}, issn = {{1872-7697}}, keywords = {{Affective learning, Socially-evaluated cold pressor test, Free salivary cortisol, Hypothalamus-pituitary-adrenal axis, Evaluative conditioning}}, pages = {{44--52}}, publisher = {{Elsevier BV}}, title = {{{The timing-dependent effects of stress-induced cortisol release on evaluative conditioning}}}, doi = {{10.1016/j.ijpsycho.2020.04.007}}, volume = {{152}}, year = {{2020}}, } @inbook{6850, abstract = {{Dieser Beitrag betrachtet die Konzeption und den Einsatz von eTutorien im Rahmen der Hochschullehre. Dabei wird deutlich, dass eTutorien eine E-Learning-Maßnahme darstellen, die in einem bestimmten Kontext eingesetzt werden kann. Dozenten von digitalen Tutorien müssen sich dabei aber neuen Herausforderungen stellen. Das Fehlen von visueller oder akustischer Rückmeldung der Zuhörerschaft ist gewöhnungsbedürftig und muss über ein gut ausgewogenes akustisches Format mit visuellen Elementen kompensiert werden. eTutorien stellen damit eine sinnvolle Ergänzung des klassischen Tutoriums dar. Der Bedarf von nicht-digitalen Ergänzungsveranstaltungen wie z. B. Übungsgruppen und Präsenztutorien ist aber weiterhin gegeben. }}, author = {{von Blanckenburg, Korbinian and Knost, Eike}}, booktitle = {{Lehrexperimente der Hochschulbildung- Didaktische Innovationen aus den Fachdisziplinen}}, editor = {{Schmohl, Tobias and Schäffer, Dennis}}, isbn = {{978-3-7639-6114-6}}, keywords = {{E-Learning, Hochschule, Hochschullehre, Virtuelle Hochschule, Visuelles Medium, Lehrveranstaltung, Tutorium, Online-Angebot, Online-Kurs, Virtuelle Lehre, Digitale Medien, Interaktive Medien, Elektronische Medien, Ostwestfalen-Lippe, Deutschland}}, pages = {{41--46}}, publisher = {{wbv }}, title = {{{Einsatz von eTutorien als komplementäre Lehr- und Lernform}}}, doi = {{ 10.25656/01:18561}}, volume = {{2}}, year = {{2019}}, } @inproceedings{4102, abstract = {{Complexity is a fundamental part of product design and manufacturing today, owing to increased demands for customization and advances in digital design techniques. Assembling and repairing such an enormous variety of components means that workers are cognitively challenged, take longer to search for the relevant information and are prone to making mistakes. Although in recent years deep learning approaches to object recognition have seen rapid advances, the combined potential of deep learning and augmented reality in the industrial domain remains relatively under explored. In this paper we introduce AR-ProMO, a combined hardware/software solution that provides a generalizable assistance system for identifying mistakes during product assembly and repair.}}, author = {{Dhiman, Hitesh and Büttner, Sebastian and Röcker, Carsten and Reisch, Raphael}}, booktitle = {{Proceedings of the 31st Australian Conference on Human-Computer-Interaction (OzCHI'19) : 2nd Dec.-5th Dec. 2019, Perth/Fremantle, WA, Australia}}, isbn = {{978-1-4503-7696-9}}, keywords = {{Augmented Reality, Deep Learning}}, location = {{Perth/Fremantle, WA, Australia}}, pages = {{ 518–522}}, publisher = {{ACM}}, title = {{{Handling Work Complexity with AR/Deep Learning}}}, doi = {{10.1145/3369457.3370919}}, year = {{2019}}, } @inbook{4312, abstract = {{Computer-aided assistance systems are entering the world of work and production. Such systems utilize augmented- and virtual-reality for operator training and live guidance as well as mobile maintenance and support. This is particularly important in the modern production reality of ever-changing products and `lot size one' customization of production.This paper focuses on the application of machine learning approach to extend the functionality of assistance systems. Machine learning provides tools to analyse large amounts of data and extract meaningful information. The goal here is to recognize the movement of an operator which would enable automatic display of instructions relevant to them.We present the challenges facing machine learning applications in human-centered assistance systems and a framework to assess machine learning approaches feasible for this scenario. The approach is assessed on a historical data set and then deployed in a work station for live testing. The post-hoc, or historical, analysis yields promising results. The ad-hoc, or live, analysis is a complex task and the results are affected by multiple factors, most of which are introduced by the human influence.The contribution of this paper is an approach to adapt state- of-the-art machine learning to operator movement recognition with a special focus on approaches to spatial time series data pre-processing. Presented experiment results validate the approach and show that it performs well in a real-world scenario.}}, author = {{Fullen, Marta and Maier, Alexander and Nazarenko, Arthur and Jenderny, Sascha and Röcker, Carsten}}, booktitle = {{2019 IEEE 17th International Conference on Industrial Informatics (INDIN)}}, isbn = {{978-1-7281-2927-3}}, issn = {{2378-363X}}, keywords = {{augmented reality, computer based training, data handling, industrial training, learning (artificial intelligence), time series}}, location = {{Helsinki, Finland,}}, pages = {{296 -- 302}}, publisher = {{IEEE}}, title = {{{Machine Learning for Assistance Systems: Pattern-Based Approach to Online Step Recognition}}}, doi = {{10.1109/INDIN41052.2019.8972122}}, year = {{2019}}, } @inproceedings{4327, abstract = {{In ever changing world, the industrial systems become more and more complex. Machine feedback in the form of alarms and notifications, due to its growing volume, becomes overwhelming for the operator. In addition, expectations in relation to system availability are growing as well. Therefore, there exists strong need for new solutions guaranteeing fast troubleshooting of problems that arise during system operation. The approach proposed in this study uses advantages of the Asset Administration Shell, machine learning, and human-machine interaction in order to create the assistance system which holistically addresses the issue of troubleshooting complex industrial systems.}}, author = {{Lang, Dorota and Wunderlich, Paul and Heinz, Mario and Wisniewski, Lukasz and Jasperneite, Jürgen and Niggemann, Oliver and Röcker, Carsten}}, booktitle = {{14th IEEE International Workshop on Factory Communication Systems (WFCS)}}, keywords = {{Maintenance engineering, Adaptation models, Machine learning, Data models, Standards, Software, Bayes methods}}, location = {{Imperia, Italy }}, publisher = {{IEEE}}, title = {{{Assistance System to Support Troubleshooting of Complex Industrial Systems}}}, doi = {{10.1109/WFCS.2018.8402380}}, year = {{2018}}, } @misc{9650, abstract = {{In Germany, there is much academic discourse on and scientific inquiry into pedagogical issues of science teaching and learning at the school level. Concepts like ‘Bildung’ (inquiry-based self-formation) or ‘Didaktik’ (instruction-based reflections on teaching) are almost directly associated with institutions or actors rooted in pedagogical departments. Unfortunately, those departments rarely focus on issues of science teaching and learning at the University level – and if they do so, they most often try to apply conceptions and models borrowed from upper or post-secondary education. The few research-based institutions that address specific issues of higher education are commonly fitted out so that they are nowhere near the impacts of research institutions covering teaching methodology in primary or secondary education, for example. Yet from an international perspective, the university as an institution does hold a great potential to improve educational practice in a systematic, cross-disciplinary and research-based way. Around the globe, more and more institutions rely on the notion of scholarship in this context: ‘The improvement of learning and teaching is dependent upon the development of scholarship and research in teaching’ (Prosser & Trigwell, 1999, p. 8). If incorporated at the heart of tertiary education, scholarship could contribute to develop new faculty in the German higher-educational sector. }}, author = {{Schmohl, Tobias}}, booktitle = {{ International Conference New Perspectives in Science Education }}, keywords = {{Scholarship of Teaching and Learning, Scholarship of Academic Development, Higher Education, community building}}, location = {{Florence, Italy}}, publisher = {{libreriauniversitaria.it edizioni}}, title = {{{Towards a New Scholarship of German Science Education}}}, year = {{2018}}, } @misc{7592, author = {{Schmohl, Tobias}}, booktitle = {{The Future of Education}}, isbn = {{ ‎ 978-8862928687}}, keywords = {{Scholarship of Academic Development, Scholarship of Teaching and Learning}}, location = {{Florenz}}, pages = {{317--321}}, publisher = {{Libreriauniversitaria.it}}, title = {{{The research—education nexus: Basic premises and practical application of the "Scholarship" movement}}}, volume = {{7}}, year = {{2017}}, } @inproceedings{4254, abstract = {{The current trend of integrating machines and factories into cyber-physical systems (CPS) creates an enormous complexity for operators of such systems. Especially the search for the root cause of cascading failures becomes highly time-consuming. Within this paper, we address the question on how to help human users to better and faster understand root causes of such situations. We propose a concept of interactive alarm flood reduction and present the implementation of a first vertical prototype for such a system. We consider this prototype as a first artifact to be discussed by the research community and aim towards an incremental further development of the system in order to support humans in complex error situations.}}, author = {{Büttner, Sebastian and Wunderlich, Paul and Heinz, Mario and Niggemann, Oliver and Röcker, Carsten}}, booktitle = {{ Machine Learning and Knowledge Extraction : First IFIP TC 5, WG 8.4, 8.9, 12.9 International Cross-Domain Conference, CD-MAKE 2017, Reggio, Italy, August 29 – September 1, 2017, Proceedings}}, editor = {{Holzinger, Andreas}}, isbn = {{978-3-319-66807-9}}, keywords = {{Alarm flood reduction, Machine learning, Assistive system}}, location = {{Reggio, Italy}}, pages = {{69--82}}, publisher = {{Springer}}, title = {{{Managing Complexity: Towards Intelligent Error-Handling Assistance Trough Interactive Alarm Flood Reduction}}}, volume = {{10410}}, year = {{2017}}, } @misc{811, author = {{Böhl, Freda}}, keywords = {{E-Learning, eLearning}}, pages = {{60}}, publisher = {{Hochschule Ostwestfalen-Lippe}}, title = {{{eLearning in der Hochschullehre: Entwicklung eines Leitfadens für den Studiengang Medienproduktion}}}, year = {{2017}}, } @inbook{4298, abstract = {{In this paper, we present the current state-of-the-art of decision making (DM) and machine learning (ML) and bridge the two research domains to create an integrated approach of complex problem solving based on human and computational agents. We present a novel classification of ML, emphasizing the human-in-the-loop in interactive ML (iML) and more specific on collaborative interactive ML (ciML), which we understand as a deep integrated version of iML, where humans and algorithms work hand in hand to solve complex problems. Both humans and computers have specific strengths and weaknesses and integrating humans into machine learning processes might be a very efficient way for tackling problems. This approach bears immense research potential for various domains, e.g., in health informatics or in industrial applications. We outline open questions and name future challenges that have to be addressed by the research community to enable the use of collaborative interactive machine learning for problem solving in a large scale.}}, author = {{Robert, Sebastian and Büttner, Sebastian and Röcker, Carsten and Holzinger, Andreas}}, booktitle = {{Machine Learning for Health Informatics : State-of-the-Art and Future Challenges }}, editor = {{Holzinger, Andreas}}, isbn = {{978-3-319-50477-3 }}, keywords = {{Decision making, Reasoning, Interactive machine learning, Collaborative interactive machine learning}}, pages = {{357--376}}, publisher = {{Springer}}, title = {{{Reasoning Under Uncertainty: Towards Collaborative Interactive Machine Learning}}}, doi = {{10.1007/978-3-319-50478-0_18}}, volume = {{9605}}, year = {{2016}}, } @inproceedings{2167, abstract = {{Cyber-Physical Production Systems (CPPSs) are in the focus of research, industry and politics: By applying new IT and new computer science solutions, production systems will become more adaptable, more resource ef- ficient and more user friendly. The analysis and diagnosis of such systems is a major part of this trend: Plants should detect automatically wear, faults and suboptimal configurations. This paper reflects the current state-of- the-art in diagnosis against the requirements of CPPSs, identifies three main gaps and gives application scenarios to outline first ideas for potential solutions to close these gaps. }}, author = {{Niggemann, Oliver and Lohweg, Volker}}, booktitle = {{Twenty-Ninth Conference on Artificial Intelligence (AAAI-15)}}, keywords = {{Cyber-Physical Systems, Machine Learning, Diagnosis, Anomaly Detection}}, title = {{{On the Diagnosis of Cyber-Physical Production Systems - State-of-the-Art and Research Agenda}}}, year = {{2015}}, } @book{4336, abstract = {{Prolonged life expectancy along with the increasing complexity of medicine and health services raises health costs worldwide dramatically. Whilst the smart health concept has much potential to support the concept of the emerging P4-medicine (preventive, participatory, predictive, and personalized), such high-tech medicine produces large amounts of high-dimensional, weakly-structured data sets and massive amounts of unstructured information. All these technological approaches along with “big data” are turning the medical sciences into a data-intensive science. To keep pace with the growing amounts of complex data, smart hospital approaches are a commandment of the future, necessitating context aware computing along with advanced interaction paradigms in new physical-digital ecosystems. The very successful synergistic combination of methodologies and approaches from Human-Computer Interaction (HCI) and Knowledge Discovery and Data Mining (KDD) offers ideal conditions for the vision to support human intelligence with machine learning. The papers selected for this volume focus on hot topics in smart health; they discuss open problems and future challenges in order to provide a research agenda to stimulate further research and progress.}}, editor = {{Holzinger, Andreas and Röcker, Carsten and Ziefle, Martina}}, isbn = {{978-3-319-16225-6}}, issn = {{1611-3349}}, keywords = {{HCI, ambient assisted living, big data, computational intelligence, context awareness, data centric medicine, decision support, interactive data mining, keyword detection, knoweldge bases, knoweldge discovery, machine learning, medical decision support, medical informatics, natural language processing, pervasive health, smart home, ubiquitous computing, visualization, wearable sensors}}, pages = {{275}}, publisher = {{Springer}}, title = {{{Smart Health: Open Problems and Future Challenges}}}, doi = {{10.1007/978-3-319-16226-3}}, volume = {{8700}}, year = {{2015}}, } @misc{9856, abstract = {{According to the Bologna Accord in 2006 the study courses for architecture, urban planning and landscape planning at Kassel university were reformed to a bachelor and master education programme. New courses – so called “modules” were found. One of them “Wahrnehmung und Analyse von Räumen” – “landscape perception and analysis” – is an interdisciplinary course teaching and comparing three different perspectives – those of ecology, social science and landscape planning – on landscape. To manage a high number of students the e-learning platform “Moodle” is used. Also giving an introduction into GIS is a major part of the course. This article – after “landscape perception and analysis” started four years ago – gives an overview of the recent and future development of the course from a teachers perspective.}}, author = {{Leiner, Claas and Stemmer, Boris}}, booktitle = {{gis.Science}}, issn = {{2698-4571}}, keywords = {{Universitarian teaching, GIS, e-learning, bologna process}}, number = {{4}}, pages = {{105–110}}, publisher = {{Wichmann}}, title = {{{Teaching Landscape Planning - Landscape Perception and Analysis}}}, year = {{2011}}, } @inproceedings{2087, abstract = {{It is likely in real-world applications that only little data isavailable for training a knowledge-based system. We present a method forautomatically training the knowledge-representing membership functionsof a Fuzzy-Pattern-Classification system that works also when only littledata is available and the universal set is described insufficiently. Actually,this paper presents how the Modified-Fuzzy-Pattern-Classifier’s member-ship functions are trained using probability distribution functions.}}, author = {{Mönks, Uwe and Lohweg, Volker and Petker, Denis}}, booktitle = {{IPMU 2010 - International Conference on Information Processing and Management of Uncertainty in Knowledge Based Systems}}, keywords = {{Fuzzy Logic, Probability Theory, Fuzzy-Pattern-Classification, Machine Learning, Artificial Intelligence, Pattern Recognition}}, publisher = {{28 Jun 2010 - 02 July 2010, Dortmund, Germany}}, title = {{{Fuzzy-Pattern-Classifier Training with Small Data Sets}}}, year = {{2010}}, }