Jan Michael Spoor
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jan Michael Spoor has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
Jens Weber
Faculty of Technology - Mechatronics Trinational, Baden-Wuerttemberg Cooperative State University Lörrach, Germany
1 shared publication- Jens Weber
Faculty of Technology, Baden-Wuerttemberg Cooperative State University Lörrach, Lörrach, Germany
1 shared publication - Jens Weber
Mercedes-Benz Group AG
1 shared publication Jivka Ovtcharova
Institut für Informationsmanagement im Ingenieurwesen, Karlsruhe Institute of Technology, Germany
1 shared publication- Jivka Ovtcharova
Institute for Information Management in Engineering, Karlsruhe Institute of Technology, 76133 Karlsruhe, Germany
1 shared publication
Latest Publications
- Open Access
- 8 December 2023
- Published by Springer Nature
- p. 373-381
A Proposal for Formalization and Definition of Anomalies in Dynamical Systems
Although many scientists strongly focus on anomaly detection in different applications and domains, there currently exists no universally accepted definition of anomalies and outliers. Using an approach based on control theory and dynamical systems, as well as a definition for anomalies as described by philosophy of science, the authors propose a generalized framework viewing anomalies as key drivers of progress for a better understanding of the dynamical systems around us. By mathematically defining anomalies and delimiting deviations within expectations from completely unforeseen instances, this paper aims to be a contribution to set up a universally accepted definition of anomalies and outliers.
- 8 December 2023
- Published by Springer Nature
- p. 373-381
Open AccessA Proposal for Formalization and Definition of Anomalies in Dynamical Systems
Although many scientists strongly focus on anomaly detection in different applications and domains, there currently exists no universally accepted definition of anomalies and outliers. Using an approach based on control theory and dynamical systems, as well as a definition for anomalies as described by philosophy of science, the authors propose a generalized framework viewing anomalies as key drivers of progress for a better understanding of the dynamical systems around us. By mathematically defining anomalies and delimiting deviations within expectations from completely unforeseen instances, this paper aims to be a contribution to set up a universally accepted definition of anomalies and outliers.
- Open Access
- 8 November 2023
- Published by SAGE Publications in Transactions of the Institute of Measurement and Control
- Vol. 47 (7) , 1258-1272
Anomaly detection and prediction evaluation for discrete nonlinear dynamical systems
Anomalies in dynamical systems mostly occur as deviations between measurement and prediction. Current anomaly detection methods in multivariate time series often require prior clustering, training data, or cannot distinguish local and global anomalies. Furthermore, no generalized metric exists to evaluate and compare different prediction functions regarding their amount of anomalous behavior. We propose a novel methodology to detect local and global anomalies in time series data of dynamical systems. For this purpose, a theoretical density distribution is derived assuming that only noise conceals the time series. If the theoretical and the empirical density distribution yield significantly different entropies, an anomaly is assumed. For a local anomaly detection, the Mahalanobis distance using the theoretical noise distribution’s covariance is applied to evaluate sequences of predictions and measurements. In addition, the Wasserstein metric enables a comparison of predictions using the distance between the noise and empirical distribution as a measure for selecting the best prediction function. The proposed method performs well on nonlinear time series such as logistic growth and enables a useful selection of a prediction model for satellite orbits. Thus, the proposed method improves anomaly detection in time series and model selection for nonlinear systems.
- 8 November 2023
- Published by SAGE Publications in Transactions of the Institute of Measurement and Control
- Vol. 47 (7) , 1258-1272
Open AccessAnomaly detection and prediction evaluation for discrete nonlinear dynamical systems
Anomalies in dynamical systems mostly occur as deviations between measurement and prediction. Current anomaly detection methods in multivariate time series often require prior clustering, training data, or cannot distinguish local and global anomalies. Furthermore, no generalized metric exists to evaluate and compare different prediction functions regarding their amount of anomalous behavior. We propose a novel methodology to detect local and global anomalies in time series data of dynamical systems. For this purpose, a theoretical density distribution is derived assuming that only noise conceals the time series. If the theoretical and the empirical density distribution yield significantly different entropies, an anomaly is assumed. For a local anomaly detection, the Mahalanobis distance using the theoretical noise distribution’s covariance is applied to evaluate sequences of predictions and measurements. In addition, the Wasserstein metric enables a comparison of predictions using the distance between the noise and empirical distribution as a measure for selecting the best prediction function. The proposed method performs well on nonlinear time series such as logistic growth and enables a useful selection of a prediction model for satellite orbits. Thus, the proposed method improves anomaly detection in time series and model selection for nonlinear systems.
- Open Access
- 27 June 2023
- Published by Springer Nature in Journal of Intelligent Manufacturing
- Vol. 35 (6) , 2625-2643
Evaluation of process planning in manufacturing by a neural network based on an energy definition of hopfield nets
During the planning stages of new factories for the Body-In-White assembly, the processes used per production system need to be defined. Each production system uses a specific combination of processes, with each process belonging to a main process group. The combination of the processes and groups is subject to restrictions. Since the amount of possible combinations is too large to individually check for restrictions, we propose a Neural Network using an energy measurement derived from Hopfield networks. The proposed network memorizes former correct combinations and provides a recommendation score on how likely a new planned configuration is. Since processes can be paired with processes from their own group or with themselves, the Neural Network is modified to allow loops for joining vertices with themselves. This modification is achieved by adjusting the energy function of Hopfield networks to measure the activation of the combinations of clusters, meaning the edges, and not the activation of vertices during the training phase. We implemented the network for the process planning of factories of a leading European automotive manufacturer, and the results using correct, incorrect, and random process combinations indicate a strong capability of detecting anomalous process combinations.
- 27 June 2023
- Published by Springer Nature in Journal of Intelligent Manufacturing
- Vol. 35 (6) , 2625-2643
Open AccessEvaluation of process planning in manufacturing by a neural network based on an energy definition of hopfield nets
During the planning stages of new factories for the Body-In-White assembly, the processes used per production system need to be defined. Each production system uses a specific combination of processes, with each process belonging to a main process group. The combination of the processes and groups is subject to restrictions. Since the amount of possible combinations is too large to individually check for restrictions, we propose a Neural Network using an energy measurement derived from Hopfield networks. The proposed network memorizes former correct combinations and provides a recommendation score on how likely a new planned configuration is. Since processes can be paired with processes from their own group or with themselves, the Neural Network is modified to allow loops for joining vertices with themselves. This modification is achieved by adjusting the energy function of Hopfield networks to measure the activation of the combinations of clusters, meaning the edges, and not the activation of vertices during the training phase. We implemented the network for the process planning of factories of a leading European automotive manufacturer, and the results using correct, incorrect, and random process combinations indicate a strong capability of detecting anomalous process combinations.
- Open Access
- 30 September 2022
- Published by Springer Nature in Journal of Marketing Analytics
- Vol. 11 (4) , 747-760
Improving customer segmentation via classification of key accounts as outliers
Customer segmentation and key account management are important use cases for clustering algorithms. Here, a data set of a Portuguese wholesaler for food and household supplies is used as an exemplary application. To increase the quality of the analysis, a two-stage approach is proposed. First, key accounts are filtered by a density-based outlier detection. Second, a Gaussian Mixture Model (GMM) is applied to cluster smaller customers. This two-stage approach is aligned with the business implications of key accounts as outstanding and very differently behaving customers as well as with the core idea of an ABC analysis. Also, the exclusion of key accounts corresponds to the definition of outliers as the results of a different underlying mechanism. Using this two-stage approach shows better clustering results compared to using a one-stage approach applying only a GMM. Therefore, it is concluded that density-based detection of key accounts followed by a clustering using a GMM is beneficial for customer segmentation within B2B applications.
- 30 September 2022
- Published by Springer Nature in Journal of Marketing Analytics
- Vol. 11 (4) , 747-760
Open AccessImproving customer segmentation via classification of key accounts as outliers
Customer segmentation and key account management are important use cases for clustering algorithms. Here, a data set of a Portuguese wholesaler for food and household supplies is used as an exemplary application. To increase the quality of the analysis, a two-stage approach is proposed. First, key accounts are filtered by a density-based outlier detection. Second, a Gaussian Mixture Model (GMM) is applied to cluster smaller customers. This two-stage approach is aligned with the business implications of key accounts as outstanding and very differently behaving customers as well as with the core idea of an ABC analysis. Also, the exclusion of key accounts corresponds to the definition of outliers as the results of a different underlying mechanism. Using this two-stage approach shows better clustering results compared to using a one-stage approach applying only a GMM. Therefore, it is concluded that density-based detection of key accounts followed by a clustering using a GMM is beneficial for customer segmentation within B2B applications.