@inproceedings{WeegerStiehlvonKistowskietal.2025, author = {Weeger, Nicolas and Stiehl, Annika and von Kistowski, J{\´o}akim and Geißels{\"o}der, Stefan and Uhl, Christian}, title = {Towards Practicable Machine Learning Development Using AI Engineering Blueprints}, series = {2025 IEEE 22nd International Conference on Software Architecture Companion (ICSA-C)}, booktitle = {2025 IEEE 22nd International Conference on Software Architecture Companion (ICSA-C)}, publisher = {IEEE}, doi = {10.1109/ICSA-C65153.2025.00078}, pages = {525 -- 528}, year = {2025}, abstract = {The implementation of artificial intelligence (AI) in business applications holds considerable promise for significant improvements. The development of AI systems is becoming increasingly complex, thereby underscoring the growing importance of AI engineering and MLOps techniques. Small and medium-sized enterprises (SMEs) face considerable challenges when implementing AI in their products or processes. These enterprises often lack the necessary resources and expertise to develop, deploy, and operate AI systems that are tailored to address their specific problems. Given the lack of studies on the application of AI engineering practices, particularly in the context of SMEs, this paper proposes a research plan designed to develop blueprints for the creation of proprietary machine learning (ML) models using AI engineering and MLOps practices. These blueprints enable SMEs to develop, deploy, and operate AI systems by providing reference architectures and suitable automation approaches for different types of ML. The efficacy of the blueprints is assessed through their application to a series of field projects. This process gives rise to further requirements and additional development loops for the purpose of generalization. The benefits of using the blueprints for organizations are demonstrated by observing the process of developing ML models and by conducting interviews with the developers.}, subject = {Maschinelles Lernen}, language = {en} } @incollection{Hubert2024, author = {Hubert, Andreas}, title = {Scene Understanding at Manual Assembly Cells}, series = {Organic Computing}, volume = {2023}, booktitle = {Organic Computing}, publisher = {Kassel University Press}, address = {Kassel}, pages = {109 -- 120}, year = {2024}, subject = {Maschinelles Lernen}, language = {en} } @article{CibaPetzoldAlvesetal.2025, author = {Ciba, Manuel and Petzold, Marc and Alves, Caroline L. and Rodrigues, Francisco A. and Jimbo, Yasuhiko and Thielemann, Christiane}, title = {Machine learning and complex network analysis of drug effects on neuronal microelectrode biosensor data}, series = {Scientific Reports}, volume = {15}, journal = {Scientific Reports}, number = {1}, publisher = {Springer Science and Business Media LLC}, issn = {2045-2322}, doi = {https://doi.org/10.1038/s41598-025-99479-7}, year = {2025}, abstract = {Biosensors, such as microelectrode arrays that record in vitro neuronal activity, provide powerful platforms for studying neuroactive substances. This study presents a machine learning workflow to analyze drug-induced changes in neuronal biosensor data using complex network measures from graph theory. Microelectrode array recordings of neuronal networks exposed to bicuculline, a GABA \$\$_A\$\$ receptor antagonist known to induce hypersynchrony, demonstrated the workflow's ability to detect and characterize pharmacological effects. The workflow integrates network-based features with synchrony, optimizing preprocessing parameters, including spike train bin sizes, segmentation window sizes, and correlation methods. It achieved high classification accuracy (AUC up to 90\%) and used Shapley Additive Explanations to interpret feature importance rankings. Significant reductions in network complexity and segregation, hallmarks of epileptiform activity induced by bicuculline, were revealed. While bicuculline's effects are well established, this framework is designed to be broadly applicable for detecting both strong and subtle network alterations induced by neuroactive compounds. The results demonstrate the potential of this methodology for advancing biosensor applications in neuropharmacology and drug discovery.}, subject = {Maschinelles Lernen}, language = {en} } @article{SallumAlvesdeOToutainetal.2025, author = {Sallum, Loriz Francisco and Alves, Caroline L. and de O Toutain, Thaise Graziele L and Porto, Joel Augusto Moura and Thielemann, Christiane and Rodrigues, Francisco A.}, title = {Revealing patterns in major depressive disorder with machine learning and networks}, series = {Chaos, Solitons \& Fractals}, volume = {194}, journal = {Chaos, Solitons \& Fractals}, publisher = {Elsevier BV}, issn = {0960-0779}, doi = {https://doi.org/10.1016/j.chaos.2025.116163}, year = {2025}, abstract = {Major depressive disorder (MDD) is a multifaceted condition that affects millions of people worldwide and is a leading cause of disability. There is an urgent need for an automated and objective method to detect MDD due to the limitations of traditional diagnostic approaches. In this paper, we propose a methodology based on machine and deep learning to classify patients with MDD and identify altered functional connectivity patterns from EEG data. We compare several connectivity metrics and machine learning algorithms. Complex network measures are used to identify structural brain abnormalities in MDD. Using Spearman correlation for network construction and the SVM classifier, we verify that it is possible to identify MDD patients with high accuracy, exceeding literature results. The SHAP (SHAPley Additive Explanations) summary plot highlights the importance of C4-F8 connections and also reveals dysfunction in certain brain areas and hyperconnectivity in others. Despite the lower performance of the complex network measures for the classification problem, assortativity was found to be a promising biomarker. Our findings suggest that understanding and diagnosing MDD may be aided by the use of machine learning methods and complex networks.}, subject = {Depression}, language = {en} } @inproceedings{XuMoeckel2024, author = {Xu, Xukuan and M{\"o}ckel, Michael}, title = {Machine Learning Based Early Rejection of Low Performance Cells in Li Ion Battery Production}, series = {CACML '24: Proceedings of the 2024 3rd Asia Conference on Algorithms, Computing and Machine Learning}, booktitle = {CACML '24: Proceedings of the 2024 3rd Asia Conference on Algorithms, Computing and Machine Learning}, doi = {https://doi.org/10.1145/3654823.3654870}, pages = {251 -- 256}, year = {2024}, abstract = {Lithium-ion battery cell production is conducted through a multistep production process which suffers from a notable scrap rate. Machine learning (ML) based process monitoring provides solutions to mitigate the impact of substantial scrap rates by repeated multifactorial quality predictions (virtual quality gates) along the process line. This enables an early rejection of battery cells which are unlikely to reach required specifications, avoids further waste of resources at later process steps and simplifies recycling of rejected cells. A hierarchical architecture is used to apply ML algorithms first for process-adapted feature extraction which is guided by a priori knowledge on typical production anomalies. In a second step, these features are correlated with end-of-line quality control data using explainable ML methods. The resulting predictions may lead to pass or fail of a battery cell, or -in the context of flexible production- may also trigger adjustments of later process steps to compensate for detected deficiencies. An example ML based quality control concept is illustrated for a pilot battery cell production line.}, subject = {Maschinelles Lernen}, language = {en} } @article{XuDonghuiBietal.2024, author = {Xu, Xukuan and Donghui, Li and Bi, Jinghou and M{\"o}ckel, Michael}, title = {AutoML based workflow for design of experiments (DOE) selection and benchmarking data acquisition strategies with simulation models}, series = {Scientific Reports}, journal = {Scientific Reports}, doi = {https://doi.org/10.1038/s41598-024-83581-3}, year = {2024}, abstract = {Design of experiments (DOE) is an established method to allocate resources for efficient parameter space exploration. Model based active learning (AL) data sampling strategies have shown potential for further optimization. This paper introduces a workflow for conducting DOE comparative studies using automated machine learning. Based on a practical definition of model complexity in the context of machine learning, the interplay of systematic data generation and model performance is examined considering various sources of uncertainty: this includes uncertainties caused by stochastic sampling strategies, imprecise data, suboptimal modeling, and model evaluation. Results obtained from electrical circuit models with varying complexity show that not all AL sampling strategies outperform conventional DOE strategies, depending on the available data volume, the complexity of the dataset, and data uncertainties. Trade-offs in resource allocation strategies, in particular between identical replication of data points for statistical noise reduction and broad sampling for maximum parameter space exploration, and their impact on subsequent machine learning analysis are systematically investigated. Results indicate that replication oriented strategies should not be dismissed but may prove advantageous for cases with non-negligible noise impact and intermediate resource availability. The provided workflow can be used to simulate practical experimental conditions for DOE testing and DOE selection.}, subject = {Maschinelles Lernen}, language = {en} } @incollection{TalluriWeidl2024, author = {Talluri, Kranthi Kumar and Weidl, Galia}, title = {Impact of Accidents on Traffic Congestions: A Bayesian Network Approach Using Real City Data}, series = {Advances in Transdisciplinary Engineering}, booktitle = {Advances in Transdisciplinary Engineering}, number = {63}, publisher = {IOS Press}, isbn = {9781643685601}, issn = {2352-751X}, doi = {10.3233/ATDE241181}, pages = {64 -- 78}, year = {2024}, abstract = {Traffic congestion has been a major concern in urban areas due to its strong impact on various social, economic, and human safety sectors. Understanding the relationship and analyzing the trends and patterns between congestion and accidents can strengthen the strategy for reducing traffic congestion. Research on causes of accidents and their impact on congestion has recently been explored on a greater scale, but there is still a lot of scope for vast areas of improvement. To tackle this issue, we built a Bayesian Network (BN) model for analyzing and predicting congestion probability that can occur due to accidents. In this work, the complexity of handling real data obtained from Darmstadt city is described in detail. The accidents and congestion are correlated by introducing a novel threshold-based approach, which identifies congestion based on the change in vehicle density immediately following an accident. Different thresholds are explored to determine the most reliable measure of congestion, with the T4 threshold emerging as the optimal choice. Moreover, the proposed BN model is evaluated against several machine learning models, demonstrating competitive performance and its ability to understand the root cause of traffic congestion.}, subject = {Verkehrsstau}, language = {en} } @inproceedings{AkcatepeMoeckel2023, author = {Akcatepe, Osman and M{\"o}ckel, Michael}, title = {Hybrid Physics-Inspired Machine Learning Framework for Predictive Maintenance of Forklift Chains: Leveraging Sensor Data Characteristics}, doi = {10.1109/ICCMA59762.2023.10375057}, year = {2023}, abstract = {Bridging the gap between physics-based modeling and data-driven machine learning promises to reduce the amount of training data required and to improve explainability in predictive maintenance applications. For a small fleet of industrial forklift trucks, we develop a physically inspired framework for predicting remaining useful life (RUL) for selected components by integrating physically motivated feature extraction, degradation modelling and machine learning. The discussed approach is promising for situations of limited data availability or large data heterogeneity, which often occurs in fleets of customized vehicles optimized for particular tasks.}, subject = {Maschinelles Lernen}, language = {en} } @article{VoigtMoeckel2022, author = {Voigt, Jorrit and M{\"o}ckel, Michael}, title = {Benchmarking a multi-layer approach and neural network architectures for defect detection in PBF-LB/M}, series = {Materials Today Communications}, volume = {2022}, journal = {Materials Today Communications}, number = {33/104878}, doi = {https://doi.org/10.1016/j.mtcomm.2022.104878}, pages = {* -- *}, year = {2022}, abstract = {The substitution of expensive non-destructive material testing by data-based process monitoring is intensively explored in quality assurance for additive manufactured components. Machine learning show promising results for defect detection but require conceptual adaption to layer wise manufacturing and line scanning patterns in laser powder bed fusion. A multi-layer approach to co-register µ-computer tomography measurements with process monitoring data is developed and a workflow for automatic data set generation is implemented. The objective of this research is to benchmark the volumetric multi-layer approach and specifically selected deep learning methods for defect detection. The volumetric approach shows superior results compared to single slice monitoring. All investigated structured neural network topologies deliver similar performance.}, subject = {Neuronales Netz}, language = {en} } @article{VoigtBockHilpertetal.2022, author = {Voigt, Jorrit and Bock, Thomas and Hilpert, Uwe and Hellmann, Ralf and M{\"o}ckel, Michael}, title = {Increased relative density and characteristic melt pool Signals at the edge in PBF-LB/M}, series = {Additive Manufacturing}, volume = {2022}, journal = {Additive Manufacturing}, number = {57/102798}, doi = {https://doi.org/10.1016/j.addma.2022.102798}, pages = {* -- *}, year = {2022}, abstract = {Limited process control can cause metallurgical defect formation and inhomogeneous relative density in laser powder bed fusion manufactured parts. This study shows that process monitoring, based on optical melt-pool signal analysis is capable of tracing relative density variations: Unsupervised machine learning, applied to cluster multiple-slice monitoring data, reveals characteristic patterns in this noisy time-series signal, which can be co-registered with geometrical positions in the build part. For cylindrical 15-5 PH stainless steel specimens, manufactured under constant process parameters and post-analyzed by µ-computer tomography, correlations between such patterns and an increased local relative density at the edge have been observed. Finite element method (FEM) modeling of thermal histories at exemplary positions close to the edge suggest pre-heating effects caused by neighboring laser scan trajectories as possible reasons for the increased melt pool intensity at the edge.}, subject = {Maschinelles Lernen}, language = {en} } @article{PinedaAlvesMoeckeletal.2023, author = {Pineda, Aruane M. and Alves, Caroline L. and M{\"o}ckel, Michael and de O Toutain, Thaise Graziele L and Moura Porto, Joel Augusto and Rodrigues, Francisco A.}, title = {Analysis of quantile graphs in EGC data from elderly and young individuals using machine learning and deep learning}, series = {Journal of Complex Networks}, volume = {2023}, journal = {Journal of Complex Networks}, number = {11/5}, doi = {https://doi.org/10.1093/comnet/cnad030}, pages = {* -- *}, year = {2023}, abstract = {Heart disease, also known as cardiovascular disease, encompasses a variety of heart conditions that can result in sudden death for many people. Examples include high blood pressure, ischaemia, irregular heartbeats and pericardial effusion. Electrocardiogram (ECG) signal analysis is frequently used to diagnose heart diseases, providing crucial information on how the heart functions. To analyse ECG signals, quantile graphs (QGs) is a method that maps a time series into a network based on the time-series fluctuation proprieties. Here, we demonstrate that the QG methodology can differentiate younger and older patients. Furthermore, we construct networks from the QG method and use machine-learning algorithms to perform the automatic diagnosis, obtaining high accuracy. Indeed, we verify that this method can automatically detect changes in the ECG of elderly and young subjects, with the highest classification performance for the adjacency matrix with a mean area under the receiver operating characteristic curve close to one. The findings reported here confirm the QG method's utility in deciphering intricate, nonlinear signals like those produced by patient ECGs. Furthermore, we find a more significant, more connected and lower distribution of information networks associated with the networks from ECG data of the elderly compared with younger subjects. Finally, this methodology can be applied to other ECG data related to other diseases, such as ischaemia.}, subject = {Maschinelles Lernen}, language = {en} }