Identifying underlying individuality across running, walking, and handwriting patterns with conditional cycle–consistent generative adversarial networks
In recent years, the analysis of movement patterns has increasingly focused on the individuality of movements. After long speculations about weak individuality, strong individuality is now accepted, and the first situation–dependent fine structures within it are already identified. Methodologically,...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-08-01
|
| Series: | Frontiers in Bioengineering and Biotechnology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fbioe.2023.1204115/full |
| _version_ | 1797754601297936384 |
|---|---|
| author | Johannes Burdack Sven Giesselbach Sven Giesselbach Marvin L. Simak Mamadou L. Ndiaye Christian Marquardt Wolfgang I. Schöllhorn |
| author_facet | Johannes Burdack Sven Giesselbach Sven Giesselbach Marvin L. Simak Mamadou L. Ndiaye Christian Marquardt Wolfgang I. Schöllhorn |
| author_sort | Johannes Burdack |
| collection | DOAJ |
| description | In recent years, the analysis of movement patterns has increasingly focused on the individuality of movements. After long speculations about weak individuality, strong individuality is now accepted, and the first situation–dependent fine structures within it are already identified. Methodologically, however, only signals of the same movements have been compared so far. The goal of this work is to detect cross-movement commonalities of individual walking, running, and handwriting patterns using data augmentation. A total of 17 healthy adults (35.8 ± 11.1 years, eight women and nine men) each performed 627.9 ± 129.0 walking strides, 962.9 ± 182.0 running strides, and 59.25 ± 1.8 handwritings. Using the conditional cycle-consistent generative adversarial network (CycleGAN), conditioned on the participant’s class, a pairwise transformation between the vertical ground reaction force during walking and running and the vertical pen pressure during handwriting was learned in the first step. In the second step, the original data of the respective movements were used to artificially generate the other movement data. In the third step, whether the artificially generated data could be correctly assigned to a person via classification using a support vector machine trained with original data of the movement was tested. The classification F1–score ranged from 46.8% for handwriting data generated from walking data to 98.9% for walking data generated from running data. Thus, cross–movement individual patterns could be identified. Therefore, the methodology presented in this study may help to enable cross–movement analysis and the artificial generation of larger amounts of data. |
| first_indexed | 2024-03-12T17:34:46Z |
| format | Article |
| id | doaj.art-9c99900e9d0645519cf6b87cfcbabb49 |
| institution | Directory Open Access Journal |
| issn | 2296-4185 |
| language | English |
| last_indexed | 2024-03-12T17:34:46Z |
| publishDate | 2023-08-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Bioengineering and Biotechnology |
| spelling | doaj.art-9c99900e9d0645519cf6b87cfcbabb492023-08-04T12:08:10ZengFrontiers Media S.A.Frontiers in Bioengineering and Biotechnology2296-41852023-08-011110.3389/fbioe.2023.12041151204115Identifying underlying individuality across running, walking, and handwriting patterns with conditional cycle–consistent generative adversarial networksJohannes Burdack0Sven Giesselbach1Sven Giesselbach2Marvin L. Simak3Mamadou L. Ndiaye4Christian Marquardt5Wolfgang I. Schöllhorn6Department of Training and Movement Science, Institute of Sport Science, Johannes Gutenberg-University, Mainz, GermanyKnowledge Discovery, Fraunhofer-Institute for Intelligent Analysis and Information Systems, Sankt Augustin, GermanyLamarr Institute for Machine Learning and Artificial Intelligence, Sankt Augustin, GermanyDepartment of Training and Movement Science, Institute of Sport Science, Johannes Gutenberg-University, Mainz, GermanyDepartment of Training and Movement Science, Institute of Sport Science, Johannes Gutenberg-University, Mainz, GermanyScience&Motion GmbH, Munich, GermanyDepartment of Training and Movement Science, Institute of Sport Science, Johannes Gutenberg-University, Mainz, GermanyIn recent years, the analysis of movement patterns has increasingly focused on the individuality of movements. After long speculations about weak individuality, strong individuality is now accepted, and the first situation–dependent fine structures within it are already identified. Methodologically, however, only signals of the same movements have been compared so far. The goal of this work is to detect cross-movement commonalities of individual walking, running, and handwriting patterns using data augmentation. A total of 17 healthy adults (35.8 ± 11.1 years, eight women and nine men) each performed 627.9 ± 129.0 walking strides, 962.9 ± 182.0 running strides, and 59.25 ± 1.8 handwritings. Using the conditional cycle-consistent generative adversarial network (CycleGAN), conditioned on the participant’s class, a pairwise transformation between the vertical ground reaction force during walking and running and the vertical pen pressure during handwriting was learned in the first step. In the second step, the original data of the respective movements were used to artificially generate the other movement data. In the third step, whether the artificially generated data could be correctly assigned to a person via classification using a support vector machine trained with original data of the movement was tested. The classification F1–score ranged from 46.8% for handwriting data generated from walking data to 98.9% for walking data generated from running data. Thus, cross–movement individual patterns could be identified. Therefore, the methodology presented in this study may help to enable cross–movement analysis and the artificial generation of larger amounts of data.https://www.frontiersin.org/articles/10.3389/fbioe.2023.1204115/fullcross-movement individualitycross-signal individualityCycleGANdata augmentationdeep learninggenerative adversarial network |
| spellingShingle | Johannes Burdack Sven Giesselbach Sven Giesselbach Marvin L. Simak Mamadou L. Ndiaye Christian Marquardt Wolfgang I. Schöllhorn Identifying underlying individuality across running, walking, and handwriting patterns with conditional cycle–consistent generative adversarial networks Frontiers in Bioengineering and Biotechnology cross-movement individuality cross-signal individuality CycleGAN data augmentation deep learning generative adversarial network |
| title | Identifying underlying individuality across running, walking, and handwriting patterns with conditional cycle–consistent generative adversarial networks |
| title_full | Identifying underlying individuality across running, walking, and handwriting patterns with conditional cycle–consistent generative adversarial networks |
| title_fullStr | Identifying underlying individuality across running, walking, and handwriting patterns with conditional cycle–consistent generative adversarial networks |
| title_full_unstemmed | Identifying underlying individuality across running, walking, and handwriting patterns with conditional cycle–consistent generative adversarial networks |
| title_short | Identifying underlying individuality across running, walking, and handwriting patterns with conditional cycle–consistent generative adversarial networks |
| title_sort | identifying underlying individuality across running walking and handwriting patterns with conditional cycle consistent generative adversarial networks |
| topic | cross-movement individuality cross-signal individuality CycleGAN data augmentation deep learning generative adversarial network |
| url | https://www.frontiersin.org/articles/10.3389/fbioe.2023.1204115/full |
| work_keys_str_mv | AT johannesburdack identifyingunderlyingindividualityacrossrunningwalkingandhandwritingpatternswithconditionalcycleconsistentgenerativeadversarialnetworks AT svengiesselbach identifyingunderlyingindividualityacrossrunningwalkingandhandwritingpatternswithconditionalcycleconsistentgenerativeadversarialnetworks AT svengiesselbach identifyingunderlyingindividualityacrossrunningwalkingandhandwritingpatternswithconditionalcycleconsistentgenerativeadversarialnetworks AT marvinlsimak identifyingunderlyingindividualityacrossrunningwalkingandhandwritingpatternswithconditionalcycleconsistentgenerativeadversarialnetworks AT mamadoulndiaye identifyingunderlyingindividualityacrossrunningwalkingandhandwritingpatternswithconditionalcycleconsistentgenerativeadversarialnetworks AT christianmarquardt identifyingunderlyingindividualityacrossrunningwalkingandhandwritingpatternswithconditionalcycleconsistentgenerativeadversarialnetworks AT wolfgangischollhorn identifyingunderlyingindividualityacrossrunningwalkingandhandwritingpatternswithconditionalcycleconsistentgenerativeadversarialnetworks |