Supervised learning for analysing movement patterns in a virtual reality experiment
The projection into a virtual character and the concomitant illusionary body ownership can lead to transformations of one’s entity. Both during and after the exposure, behavioural and attitudinal changes may occur, depending on the characteristics or stereotypes associated with the embodied avatar....
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
The Royal Society
2022-04-01
|
| Series: | Royal Society Open Science |
| Subjects: | |
| Online Access: | https://royalsocietypublishing.org/doi/10.1098/rsos.211594 |
| _version_ | 1797837567848087552 |
|---|---|
| author | Frederike Vogel Nils M. Vahle Jan Gertheiss Martin J. Tomasik |
| author_facet | Frederike Vogel Nils M. Vahle Jan Gertheiss Martin J. Tomasik |
| author_sort | Frederike Vogel |
| collection | DOAJ |
| description | The projection into a virtual character and the concomitant illusionary body ownership can lead to transformations of one’s entity. Both during and after the exposure, behavioural and attitudinal changes may occur, depending on the characteristics or stereotypes associated with the embodied avatar. In the present study, we investigated the effects on physical activity when young students experience being old. After assignment (at random) to a young or an older avatar, the participants’ body movements were tracked while performing upper body exercises. We propose and discuss the use of supervised learning procedures to assign these movement patterns to the underlying avatar class in order to detect behavioural differences. This approach can be seen as an alternative to classical feature-wise testing. We found that the classification accuracy was remarkably good for support vector machines with linear kernel and deep learning by convolutional neural networks, when inserting time sub-sequences extracted at random and repeatedly from the original data. For hand movements, associated decision boundaries revealed a higher level of local, vertical positions for the young avatar group, indicating increased agility in their performances. This occurrence held for both guided movements as well as achievement-orientated exercises. |
| first_indexed | 2024-04-09T15:27:54Z |
| format | Article |
| id | doaj.art-67760b28856841b4ad6db8e509a48a1d |
| institution | Directory Open Access Journal |
| issn | 2054-5703 |
| language | English |
| last_indexed | 2024-04-09T15:27:54Z |
| publishDate | 2022-04-01 |
| publisher | The Royal Society |
| record_format | Article |
| series | Royal Society Open Science |
| spelling | doaj.art-67760b28856841b4ad6db8e509a48a1d2023-04-28T11:05:35ZengThe Royal SocietyRoyal Society Open Science2054-57032022-04-019410.1098/rsos.211594Supervised learning for analysing movement patterns in a virtual reality experimentFrederike Vogel0Nils M. Vahle1Jan Gertheiss2Martin J. Tomasik3Department of Mathematics and Statistics, School of Economics and Social Sciences, Helmut Schmidt University, Hamburg, GermanyDepartment of Psychology and Psychotherapy, University of Witten/Herdecke, Witten, Nordrhein-Westfalen, GermanyDepartment of Mathematics and Statistics, School of Economics and Social Sciences, Helmut Schmidt University, Hamburg, GermanyDepartment of Psychology and Psychotherapy, University of Witten/Herdecke, Witten, Nordrhein-Westfalen, GermanyThe projection into a virtual character and the concomitant illusionary body ownership can lead to transformations of one’s entity. Both during and after the exposure, behavioural and attitudinal changes may occur, depending on the characteristics or stereotypes associated with the embodied avatar. In the present study, we investigated the effects on physical activity when young students experience being old. After assignment (at random) to a young or an older avatar, the participants’ body movements were tracked while performing upper body exercises. We propose and discuss the use of supervised learning procedures to assign these movement patterns to the underlying avatar class in order to detect behavioural differences. This approach can be seen as an alternative to classical feature-wise testing. We found that the classification accuracy was remarkably good for support vector machines with linear kernel and deep learning by convolutional neural networks, when inserting time sub-sequences extracted at random and repeatedly from the original data. For hand movements, associated decision boundaries revealed a higher level of local, vertical positions for the young avatar group, indicating increased agility in their performances. This occurrence held for both guided movements as well as achievement-orientated exercises.https://royalsocietypublishing.org/doi/10.1098/rsos.211594deep learningdata augmentationresamplingageingembodiment |
| spellingShingle | Frederike Vogel Nils M. Vahle Jan Gertheiss Martin J. Tomasik Supervised learning for analysing movement patterns in a virtual reality experiment Royal Society Open Science deep learning data augmentation resampling ageing embodiment |
| title | Supervised learning for analysing movement patterns in a virtual reality experiment |
| title_full | Supervised learning for analysing movement patterns in a virtual reality experiment |
| title_fullStr | Supervised learning for analysing movement patterns in a virtual reality experiment |
| title_full_unstemmed | Supervised learning for analysing movement patterns in a virtual reality experiment |
| title_short | Supervised learning for analysing movement patterns in a virtual reality experiment |
| title_sort | supervised learning for analysing movement patterns in a virtual reality experiment |
| topic | deep learning data augmentation resampling ageing embodiment |
| url | https://royalsocietypublishing.org/doi/10.1098/rsos.211594 |
| work_keys_str_mv | AT frederikevogel supervisedlearningforanalysingmovementpatternsinavirtualrealityexperiment AT nilsmvahle supervisedlearningforanalysingmovementpatternsinavirtualrealityexperiment AT jangertheiss supervisedlearningforanalysingmovementpatternsinavirtualrealityexperiment AT martinjtomasik supervisedlearningforanalysingmovementpatternsinavirtualrealityexperiment |