Hermann Baumgartl
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Hermann Baumgartl has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Ricardo Buettner
Chair of Hybrid Intelligence, Helmut-Schmidt-University/University of the Federal Armed Forces Hamburg, Hamburg, Germany
4 shared publications - Jan Gross
Department of Business Information Systems, Aalen University, Aalen, Germany
1 shared publication Janek Frick
Affiliation Machine Learning Research Group, Aalen University, Aalen, Germany
1 shared publication- Josef Tomas
Aalen University of Applied Sciences
1 shared publication - Markus Merkel
Institute for Virtual Product Development, Aalen University, Aalen, Germany
1 shared publication Ricardo Buettner
Aalen University
1 shared publication
Latest Publications
- Open Access
- 1 February 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 16977-16991
Benchmarking Transfer Learning Strategies in Time-Series Imaging: Recommendations for Analyzing Raw Sensor Data
With the growing availability and complexity of time-series sequences, scalable and robust machine learning approaches are required that overcome the sampling challenge of quantitatively sufficient training data. Following the research trend towards the deep learning-based analysis of time-series encoded as images, this study proposes a time-series imaging workflow that overcomes the challenge of quantitatively limited sensor data across domains (i.e., medicine and engineering). After systematically identifying the three relevant dimensions that affect the performance of the deep learning-based analysis of visualized time-series data, we performed a benchmarking evaluation with a total of 24 unique convolutional neural network models. Following a two-level transfer learning investigation, we reveal that fine-tuning the mid-level features results in the best classification performance. As a result, we present an optimized representation of the VGG16 network, which outperforms previous studies in the field. Our approach is accurate, robust, and manifests internal and external validity. By only using the raw time-series data, our model does not require manual feature engineering, being of high practical relevance. As the post-hoc analysis of our results reveals that our model allows automated extraction of meaningful features based on the trend of the underlying time-series data, our study also adds to explainable artificial intelligence. Furthermore, our proposed workflow reduces the sequence length of the input data while preserving all information. Especially with the hurdle of long-term dependencies in sequential time-series data, we overcome related work’s limitation of the vanishing gradients problem and contribute to the sequential learning theory in artificial intelligence.
- 1 February 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 16977-16991
Open AccessBenchmarking Transfer Learning Strategies in Time-Series Imaging: Recommendations for Analyzing Raw Sensor Data
With the growing availability and complexity of time-series sequences, scalable and robust machine learning approaches are required that overcome the sampling challenge of quantitatively sufficient training data. Following the research trend towards the deep learning-based analysis of time-series encoded as images, this study proposes a time-series imaging workflow that overcomes the challenge of quantitatively limited sensor data across domains (i.e., medicine and engineering). After systematically identifying the three relevant dimensions that affect the performance of the deep learning-based analysis of visualized time-series data, we performed a benchmarking evaluation with a total of 24 unique convolutional neural network models. Following a two-level transfer learning investigation, we reveal that fine-tuning the mid-level features results in the best classification performance. As a result, we present an optimized representation of the VGG16 network, which outperforms previous studies in the field. Our approach is accurate, robust, and manifests internal and external validity. By only using the raw time-series data, our model does not require manual feature engineering, being of high practical relevance. As the post-hoc analysis of our results reveals that our model allows automated extraction of meaningful features based on the trend of the underlying time-series data, our study also adds to explainable artificial intelligence. Furthermore, our proposed workflow reduces the sequence length of the input data while preserving all information. Especially with the hurdle of long-term dependencies in sequential time-series data, we overcome related work’s limitation of the vanishing gradients problem and contribute to the sequential learning theory in artificial intelligence.
- Open Access
- 17 December 2020
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 15 (12) , e0243615
Demonstration of the potential of white-box machine learning approaches to gain insights from cardiovascular disease electrocardiograms
We present the results from a white-box machine learning approach to detect cardiac arrhythmias using electrocardiographic data. A C5.0 is trained to recognize four classes using common features. The four classes are (i) atrial fibrillation and atrial flutter, (ii) tachycardias (iii), sinus bradycardia and (iv) sinus rhythm. Data from 10,646 subjects, 83% of whom have at least one arrhythmia and 17% of whom exhibit a normal sinus rhythm, are used. The C5.0 is trained using 10-fold cross-validation and is able to achieve a balanced accuracy of 95.35%. By using the white-box machine learning approach, a clear and comprehensible tree structure can be revealed, which has selected the 5 most important features from a total of 24 features. These 5 features are ventricular rate, RR-Interval variation, atrial rate, age and difference between longest and shortest RR-Interval. The combination of ventricular rate, RR-Interval variation and atrial rate is especially relevant to achieve classification accuracy, which can be disclosed through the tree. The tree assigns unique values to distinguish the classes. These findings could be applied in medicine in the future. It can be shown that a white-box machine learning approach can reveal granular structures, thus confirming known linear relationships and also revealing nonlinear relationships. To highlight the strength of the C5.0 with respect to this structural revelation, the results of further white-box machine learning and black-box machine learning algorithms are presented.
- 17 December 2020
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 15 (12) , e0243615
Open AccessDemonstration of the potential of white-box machine learning approaches to gain insights from cardiovascular disease electrocardiograms
We present the results from a white-box machine learning approach to detect cardiac arrhythmias using electrocardiographic data. A C5.0 is trained to recognize four classes using common features. The four classes are (i) atrial fibrillation and atrial flutter, (ii) tachycardias (iii), sinus bradycardia and (iv) sinus rhythm. Data from 10,646 subjects, 83% of whom have at least one arrhythmia and 17% of whom exhibit a normal sinus rhythm, are used. The C5.0 is trained using 10-fold cross-validation and is able to achieve a balanced accuracy of 95.35%. By using the white-box machine learning approach, a clear and comprehensible tree structure can be revealed, which has selected the 5 most important features from a total of 24 features. These 5 features are ventricular rate, RR-Interval variation, atrial rate, age and difference between longest and shortest RR-Interval. The combination of ventricular rate, RR-Interval variation and atrial rate is especially relevant to achieve classification accuracy, which can be disclosed through the tree. The tree assigns unique values to distinguish the classes. These findings could be applied in medicine in the future. It can be shown that a white-box machine learning approach can reveal granular structures, thus confirming known linear relationships and also revealing nonlinear relationships. To highlight the strength of the C5.0 with respect to this structural revelation, the results of further white-box machine learning and black-box machine learning algorithms are presented.
- Top Cited PapersOpen Access
- 18 February 2020
- Published by Springer Nature in Progress in Additive Manufacturing
- Vol. 5 (3) , 277-285
A deep learning-based model for defect detection in laser-powder bed fusion using in-situ thermographic monitoring
- 18 February 2020
- Published by Springer Nature in Progress in Additive Manufacturing
- Vol. 5 (3) , 277-285
Top Cited PapersOpen AccessA deep learning-based model for defect detection in laser-powder bed fusion using in-situ thermographic monitoring
- Open Access
- 1 January 2019
- Published by HICSS Conference Office
A Highly Effective Deep Learning Based Escape Route Recognition Module for Autonomous Robots in Crisis and Emergency Situations
Using convolutional neural networks we extend the work by Dugdale's group on socially relevant multi-agent systems in crisis and emergency situations by giving the artificial agent the ability to precisely recognize escape signs, doors and stairs for escape route planning. We build an efficient recognition module consisting of three blocks of a depth-wise separable convolutional layer, a max-pooling layer, and a batchnormalization layer before dense, dropout and classifying the image. A rigorous evaluation based on the MCIndoor20000 dataset shows excellent performance values (e.g. over 99.81 percent accuracy). In addition, our module architecture is 78 times smaller than the MCIndoor20000 benchmark-making it suitable for embedding in operational drones and robots.
- 1 January 2019
- Published by HICSS Conference Office
Open AccessA Highly Effective Deep Learning Based Escape Route Recognition Module for Autonomous Robots in Crisis and Emergency Situations
Using convolutional neural networks we extend the work by Dugdale's group on socially relevant multi-agent systems in crisis and emergency situations by giving the artificial agent the ability to precisely recognize escape signs, doors and stairs for escape route planning. We build an efficient recognition module consisting of three blocks of a depth-wise separable convolutional layer, a max-pooling layer, and a batchnormalization layer before dense, dropout and classifying the image. A rigorous evaluation based on the MCIndoor20000 dataset shows excellent performance values (e.g. over 99.81 percent accuracy). In addition, our module architecture is 78 times smaller than the MCIndoor20000 benchmark-making it suitable for embedding in operational drones and robots.