@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{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}}, } @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{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{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}}, } @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}}, } @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}}, } @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}}, } @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}}, } @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}}, } @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}}, }