@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{12009,
abstract = {{AbstractTraditional work models often need more flexibility and time autonomy for employees, especially in manufacturing. Quantitative approaches and Artificial Intelligence (AI) applications offer the potential to improve work design. However, current research does not entirely focus on human-centric criteria that enable time autonomy. This paper addresses this gap by developing a set of criteria to evaluate intelligent personnel planning approaches based on their ability to enhance time autonomy for employees. Existing quantitative approaches are not sufficient to fully integrate the developed criteria.Consequently, a novel model approach is proposed in an attempt to bridge the gap between current practices and the newly developed criteria. This two-stage planning approach fosters democratization of time autonomy on the shopfloor, moving beyond traditional top-down scheduling. The paper concludes by outlining the implementation process and discusses future developments with respect to AI for this model approach.Practical Relevance: In order to make working conditions on the shopfloor in high-wage countries more attractive, an alternative organization of shift work is needed. Intelligent planning approaches that combine traditional operations research methods with artificial intelligence approaches can democratize shift organization regarding time autonomy. Planning that takes both employee and employer preferences into account in a balanced way will strengthen the long-term competitiveness of manufacturing companies in high-wage countries and counteract the shortage of skilled labor.}},
author = {{Latos, Benedikt and Buckhorst, Armin and Kalantar, Peyman and Bentler, Dominik and Gabriel, Stefan and Dumitrescu, Roman and Minge, Michael and Steinmann, Barbara and Guhr, Nadine}},
booktitle = {{Zeitschrift für Arbeitswissenschaft}},
issn = {{2366-4681}},
keywords = {{Personnel Planning, Time Autonomy, Human-Centric Optimization, Artificial Intelligence, Manufacturing}},
number = {{3}},
pages = {{277--298}},
publisher = {{Springer-Verlag GmbH}},
title = {{{Time autonomy in personnel planning: Requirements and solution approaches in the context of intelligent scheduling from a holistic organizational perspective }}},
doi = {{10.1007/s41449-024-00432-7}},
volume = {{78}},
year = {{2024}},
}
@inbook{13169,
abstract = {{KI.BAU is a project being developed and conducted at the Detmold School of Design, part of the University of Applied Sciences and Arts Ostwestfalen-Lippe. It focuses on researching the application of artificial intelligence (AI) in architectural design, modelling, production and management processes, particularly on the communication between users, processes and the building itself in various development and life-time phases. Hence the research aims to develop new tools and AI-supported process chains for the design, production and communication of architecture. This includes the training and implementing prototypical machine learning algorithms to autonomously evolve and optimize field-specific processes and workflows.
As mentioned above, a critical question KI.BAU explores is how we, as planners, builders and users, will communicate with architecture in the future, in its phases of creation and use but also beyond. This also involves, besides virtual interfaces, examining the physical interaction with a building, its behaviour, responsiveness and adaptation to certain conditions.
The primary goal of the research at KI.BAU is to transform architecture into an intelligent, to some degree self-sustaining, self-reflective and maybe even evolving ‘ecological system’. This system should be comprehensively linked with its creators, users, devices, computers, its (biological) environment and networks. Consequently, a building must be viewed as an organism that communicates, interacts and adapts to other connected or related organisms and entities.
}},
author = {{Sachs, Hans}},
booktitle = {{Synthetic realities: New Frontiers in AI-driven Design, Fabrication and Materiality}},
editor = {{Kretzer, Manuel}},
isbn = {{978-3887781088}},
keywords = {{AI, Artificial Intelligence, Architecture, Build Environment, Building Construction, Ecology of Architecture}},
pages = {{14}},
publisher = {{AADR – Art Architecture Design Research}},
title = {{{KI.BAU Artificial Intelligence in Architecture}}},
year = {{2024}},
}
@inbook{11402,
abstract = {{In diesem Artikel geht es um die Bedeutung von Selbstbildung im Hochschulstudium und wie Studierende ihre Fähigkeit zur Selbstbildung verbessern können. Der Artikel diskutiert verschiedene Lehrmethoden und Initiativen, die dazu beitragen können, die Selbstkompetenzförderung strukturell zu verankern. Es werden auch adaptive, lernzielorientierte Kurse vorgestellt, die den Einsatz von Algorithmen der künstlichen Intelligenz nutzen, um Studierenden hochgradig individualisierte Bildungswege zu ermöglichen. Der Artikel schließt mit einer Diskussion darüber, wie die Hochschuldidaktik dazu beitragen kann, die Selbstbildungskompetenz der Studierenden zu fördern. (Autor); This article is about the importance of self-education in higher education and how students can improve their ability to self-educate. The article discusses various teaching methods and initiatives that can help to structurally embed self-education. It also presents adaptive learning goal-oriented courses that leverage the use of artificial intelligence algorithms to provide students with highly individualized educational pathways. The article concludes with a discussion of how higher education didactics can help promote students’ self-education skills.}},
author = {{Schmohl, Tobias and Go, Stefanie}},
booktitle = {{(Selbst-)Lernkompetenzen Studierender stärken: Unterstützungsangebote – Beratung – Lernräume. Sammelband zur Fachtagung "(Selbst-)Lernunterstützung an Hochschulen – wieso noch mal?" am 15. und 16.10.2020 an der Technischen Universität Kaiserslautern}},
editor = {{Haberer, Monika and Günther, Dorit and Köhler , Janina }},
keywords = {{Selbstbildung, Studium, Selbstkompetenz, Lehrmethode, Adaptiver Unterricht, Künstliche Intelligenz, Hochschuldidaktik, Lerngegenstand, Wissen, Bildungsbiografie, Hochschule, Student, Self-education, Academic studies, Teaching method, Artificial intelligence, University didactics, Knowledge, School career, Higher education institute, Male student}},
pages = {{35--45}},
publisher = {{Rheinland-Pfälzische Technische Universität Kaiserslautern-Landau, Zentrum für Innovation und Digitalisierung in Studium und Lehre (ZIDiS) }},
title = {{{Selbstbildung als Proprium akademischer Didaktik? Ein kritischer Zwischenruf}}},
doi = {{https://doi.org/10.25656/01:27948}},
year = {{2023}},
}
@misc{11445,
abstract = {{Predicting human decisions is a central challenge for planning and controlling production with weakly structured processes. Thus, workers’ decisions regarding the processing strategies and the temporal sequence of tasks to be processed are to be determined prospectively. Accordingly, there is a need to review methods for preference elicitation to develop individual predictive decision models. This paper presents a systematic literature review and discussion of 42 publications on predictive decision models and decision attributes. Methods for eliciting decision-making knowledge from manufacturing workers as part of the modeling process and decision model validation methods are reviewed and discussed in light of their predictive validity for individual task selection. The article synthesizes the recent literature for predicting human decision-making in manufacturing using artificial intelligence methods. Along with the review results, a future research agenda is proposed for modeling and simulating human decision-making in manufacturing. Knowledge about human preferences and the successful prediction of workers’ decision-making in manufacturing helps companies predict manufacturing objectives and derive organizational and work design measures.}},
author = {{Herrmann, Jan-Phillip and Tackenberg, Sven and Nitsch, Verena}},
booktitle = {{IEEE Access}},
issn = {{2169-3536}},
keywords = {{Artificial intelligence, assistance system, human decision-making, manufacturing}},
pages = {{141172--141191}},
publisher = {{IEEE}},
title = {{{Predicting Human Decision-Making for Task Selection in Manufacturing: A Systematic Literature Review}}},
doi = {{10.1109/access.2023.3340626}},
volume = {{11}},
year = {{2023}},
}
@misc{13010,
abstract = {{Especially in highly interdisciplinary fields such as automation engineering, contemporary programming education with tailored assignments and individual feedback is a major challenge for educational institutions due to the increasing number of students per teacher and the ever-increasing demand for computer science professionals. To address this gap, we present ”KIAAA” an AI Assistant for Automation Engineering Teaching, a work-in-progress approach for an integrated, customized, and AI-based learning support system for automation and programming courses based on instructor-defined course objectives. Thereby in the KIAAA system, the individual knowledge level of the students is determined and individually tailored virtual learning scenarios are generated based on the knowledge and learning profile of the students. These are iteratively adapted based on the answers given. To achieve this, KIAAA uses several AI components, a hybrid rule-based scenario generation component, a Help-DKT-based cognitive model, and a solution assessor that uses a combination of traditional code analysis methods and AI-based analyses methods for automated programming task assessment. These components are the main parts of KIAAA to generate customized programming scenarios as well as visualization and simulation based on a modern game and physics engine.}},
author = {{Eilermann, Sebastian and Wehmeier, Leon and Niggemann, Oliver and Deuter, Andreas}},
booktitle = {{2023 IEEE 21st International Conference on Industrial Informatics (INDIN)}},
editor = {{Jasperneite, Jürgen}},
isbn = {{978-1-6654-9314-7}},
keywords = {{Visualization, Automation, Education, Games, Hybrid power systems, Task analysis, Artificial intelligence}},
location = {{Lemgo}},
publisher = {{IEEE}},
title = {{{KIAAA: An AI Assistant for Teaching Programming in the Field of Automation}}},
doi = {{10.1109/indin51400.2023.10218157}},
year = {{2023}},
}
@misc{12796,
abstract = {{This Design-Based Research (DBR) project aims to develop an intelligent tutoring system (ITS) for higher education. The system will collect teaching and learning materials in audio and video formats (e.g., podcasts, lecture recordings, screencasts, and explainer videos), and store them on a learning experience platform (LXP). Then, the ITS will process them with the help of speech recognition to gain data which, in turn, will be used to power further applications: Using artificial intelligence (AI), the platform will allow users to search the materials, automatically compiling them according to criteria like lesson subject, language, medium, or required prior knowledge. By the end of the last DBR cycle, the ITS will also provide a more active form of support: It will automatically generate exercises based on predefined patterns and teaching materials, thus allowing learners to check up on their learning progress autonomously. In order to closely match the ITS's features to the needs and learning habits of students in higher education, the development of this AI-based tutoring system is accompanied by an interdisciplinary team which will continuously re-evaluate and adapt the concept over the course of several DBR cycles. Our goal is to derive implications for the system's technical development by collecting and evaluating educational research data (mixed methods design; primary and secondary research methods).}},
author = {{Schmohl, Tobias and Schelling, Kathrin and Go, Stefanie and Thaler, Katrin Jana and Watanabe, Alice}},
booktitle = {{Proceedings of the 14th International Conference on Computer Supported Education - Vol. 2}},
editor = {{Cukurova, Mutlu and Rummel, Nikol and Gillet, Denis and McLaren, Bruce and Uhomoibhi, James }},
keywords = {{Artificial Intelligence in Higher Education, Design-based Research, Intelligent Tutoring System, Participatory Technology Design, Scoping Review}},
location = {{Online}},
pages = {{179--186}},
publisher = {{SCITEPRESS - Science and Technology Publications}},
title = {{{Development, Implementation and Acceptance of an AI-based Tutoring System: A Research-Led Methodology}}},
doi = {{10.5220/0011068500003182}},
year = {{2022}},
}
@inbook{6908,
abstract = {{Es liegt auf der Hand, dass eine digitale Unterstützung von Planungs- und Beteiligungsverfahren in vielfacher Hinsicht enorme Vorteile bietet. So können mittels moderner, digitaler Partizpationsplattformen Prozessbeteiligte orts- und zeitunabhängig an städtebaulichen Ideenfindungs- und Bewertungsverfahren teilnehmen und ihre Gedanken, Meinungen und Vorschläge mit anderen teilen und diskutieren. Seit einigen Jahren stehen hierfür eine Reihe adaptierbarer Softwareprodukte zur Verfügung, z. B. Consul, ein community-basiertes Opensource-Projekt der Consul Democracy Foundation auf GitHub, die proprietäre Software citizenLab des gleichnamigen belgischen Unternehmens, oder dem neuseeländischen Pendant Loomio der Loomio Cooperative Ltd. und viele weitere. Der webbasierte Zugang ermöglicht dabei nicht nur eine potenzielle Reichweitensteigerung an Teilnehmenden und die schnelle Verlinkung zu anderen digitalen Inhalten bzw. Medien, sondern erleichtert auch die statistische Informationsauswertung und die mediale wie inhaltliche Dokumentation des Gesamtprozesses. Aktuelle Softwarelösungen sind dabei als anwenderfreundliches Baukastensystem konzipiert, das je nach Anwendungsfall individuell, modular und ohne Programmierkenntnisse zusammengesetzt werden kann. Die zuschaltbaren Module reichen von einfachen Formularmasken über interaktive Karten-Tools, MindMaps und Umfragen bis hin zu integrierten Video-Chat-Funktionen und kollaborativen Whiteboards. Zukünftig ist davon auszugehen, dass die modulare Struktur und die enorm vielfältigen Einsatzgebiete dieser Softwarelösungen zunehmend auch KI-gestützte Funktionen als neue Features enthalten werden bzw. im Baukasten bestehende Module optimieren oder ablösen werden. Die Gründe hierfür liegen größtenteils im disruptiven Fortschritt der Softwarentwicklung. Andererseits darf aber auch erwogen werden, ob nicht doch häufig beobachtete Hemmnisse oder Probleme bisheriger Partizipationsverfahren ggf. durch den unterstützenden Einsatz von KI auch abgebaut oder verringert werden könnten. Beide Perspektiven stellen für sich genommen schon sehr breite Grundlagenforschungsfelder dar, die insbesondere durch die noch hinzukommenden Aspekte der Technologieakzeptanz enorm komplex werden können. Da aber die technologische Hürde zur Umsetzung einfacher Software-Prototypen durch die Vielzahl zur Verfügung stehender Opensource-Tools sehr niedrig ist, entwickelte der Forschungsschwerpunkt nextPlace der Technischen Hochschule Ostwestfalen-Lippe zunächst eine allererste, prototypische Hardware-Software-Applikation, um - im Sinne eines Proof-of-Concept – die Relevanz und Aufwände tiefergehender Forschungs- und Entwicklungsarbeiten abschätzen zu können. Folglich stellen die nachfolgenden Ausführungen einen technischen Erfahrungsbericht der ersten Entwicklungsschritte dar, um einen einfachen, kostengünstigen und experimentellen Zugang in dieses noch recht junge Forschungsfeld nachvollziehbar zu machen.}},
author = {{Oldenburg, Carsten and Häusler, Axel}},
booktitle = {{ REAL CORP 2021: Cities 20.50, creating habitats for the 3rd millennium, smart - sustainable - climate neutral : proceedings of 26th International Conference on Urban Planning, Regional Development and Information Society}},
editor = {{Schrenk, Mnafred and Popovich, Vasily V. and Zeile, Peter and Elisei, Pietro and Beyer, Clemens and Ryser, Judith and Stöglehner, Gernot}},
isbn = {{978-3-9504945-0-1}},
keywords = {{Data Visualisation, Participation, Speech Recognition, Artificial Intelligence, Internet of Things}},
location = {{Wien}},
pages = {{481--487}},
title = {{{KI-gestützter Wordcloud-Generator für Beteiligungsprozesse}}},
doi = {{10.48494/REALCORP2021.1116}},
year = {{2021}},
}
@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}},
}
@article{4518,
abstract = {{This paper introduces CAAI, a novel cognitive architecture for artificial intelligence in cyber-physical production systems. The goal of the architecture is to reduce the implementation effort for the usage of artificial intelligence algorithms. The core of the CAAI is a cognitive module that processes the user's declarative goals, selects suitable models and algorithms, and creates a configuration for the execution of a processing pipeline on a big data platform. Constant observation and evaluation against performance criteria assess the performance of pipelines for many and different use cases. Based on these evaluations, the pipelines are automatically adapted if necessary. The modular design with well-defined interfaces enables the reusability and extensibility of pipeline components. A big data platform implements this modular design supported by technologies such as Docker, Kubernetes, and Kafka for virtualization and orchestration of the individual components and their communication. The implementation of the architecture is evaluated using a real-world use case. The prototypic implementation is accessible on GitHub and contains a demonstration.}},
author = {{Fischbach, Andreas and Strohschein, Jan and Bunte, Andreas and Stork, Jörg and Faeskorn-Woyke, Heide and Moriz, Natalia and Bartz-Beielstein, Thomas}},
issn = {{1433-3015}},
journal = {{The International Journal of Advanced Manufacturing Technology}},
keywords = {{CPPS, Artificial intelligence, Industry 40, Reference architecture, Optimization, SMBO, Cognition, Big data platform, Modularization, AutoML}},
number = {{1/2}},
pages = {{609--626}},
publisher = {{Springer}},
title = {{{CAAI -- A Cognitive Architecture to Introduce Artificial Intelligence in Cyber-Physical Production Systems}}},
doi = {{10.1007/s00170-020-06094-z}},
volume = {{111}},
year = {{2020}},
}
@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{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}},
}