Effect of forearm rotation towards cross-user classification accuracy of forearm gestures / Zinvi Fu … [et al.]
Electromyography (EMG) is a random biological signal that depends on the electrode placement and the physiology of the individual. Currently, EMG control is practically limited by this individualistic nature and requires per session training. This study investigates the EMG signals based on six l...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | en |
| Published: |
Universiti Teknologi MARA, Sabah
2020
|
| Subjects: | |
| Online Access: | https://ir.uitm.edu.my/id/eprint/50270/1/50270.pdf https://ir.uitm.edu.my/id/eprint/50270/ https://borneoakademika.sabah.uitm.edu.my/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1833069147021377536 |
|---|---|
| author | Fu, Zinvi Bani Hashim, Ahmad Yusairi Jamaludin, Zamberi Mohamad, Imran Syakir |
| author_facet | Fu, Zinvi Bani Hashim, Ahmad Yusairi Jamaludin, Zamberi Mohamad, Imran Syakir |
| author_sort | Fu, Zinvi |
| building | Tun Abdul Razak Library |
| collection | Institutional Repository |
| content_provider | Universiti Teknologi Mara |
| content_source | UiTM Institutional Repository |
| continent | Asia |
| country | Malaysia |
| description | Electromyography (EMG) is a random biological signal that depends on the
electrode placement and the physiology of the individual. Currently, EMG control
is practically limited by this individualistic nature and requires per session training.
This study investigates the EMG signals based on six locations on the lower forearm
during contraction. Gesture classification was performed en-bloc across 20 subjects
without retraining with the objective of determining the most classifiable gestures
based on the similarity of their resultant EMG signals. Principle component
analysis (PCA) and linear discriminant analysis (LDA) were the principal tools for
analysis. The results showed that many gesture pairs could be accurately classified
per channel with accuracies of over 85%. However, classification rates dropped to
unreliable levels when up to nine gestures were classified over the single channels.
The classification results show universal classification based on a common EMG
database is possible without retraining for limited gestures. |
| format | Article |
| id | my.uitm.ir-50270 |
| institution | Universiti Teknologi Mara |
| language | en |
| publishDate | 2020 |
| publisher | Universiti Teknologi MARA, Sabah |
| record_format | eprints |
| spelling | my.uitm.ir-502702021-09-09T07:15:46Z https://ir.uitm.edu.my/id/eprint/50270/ Effect of forearm rotation towards cross-user classification accuracy of forearm gestures / Zinvi Fu … [et al.] Fu, Zinvi Bani Hashim, Ahmad Yusairi Jamaludin, Zamberi Mohamad, Imran Syakir Group work in research Musculoskeletal system. Movements Electromyography Electromyography (EMG) is a random biological signal that depends on the electrode placement and the physiology of the individual. Currently, EMG control is practically limited by this individualistic nature and requires per session training. This study investigates the EMG signals based on six locations on the lower forearm during contraction. Gesture classification was performed en-bloc across 20 subjects without retraining with the objective of determining the most classifiable gestures based on the similarity of their resultant EMG signals. Principle component analysis (PCA) and linear discriminant analysis (LDA) were the principal tools for analysis. The results showed that many gesture pairs could be accurately classified per channel with accuracies of over 85%. However, classification rates dropped to unreliable levels when up to nine gestures were classified over the single channels. The classification results show universal classification based on a common EMG database is possible without retraining for limited gestures. Universiti Teknologi MARA, Sabah 2020-10 Article PeerReviewed text en https://ir.uitm.edu.my/id/eprint/50270/1/50270.pdf Effect of forearm rotation towards cross-user classification accuracy of forearm gestures / Zinvi Fu … [et al.]. (2020) Borneo Akademika <https://ir.uitm.edu.my/view/publication/Borneo_Akademika/>, 4 (4): 6. pp. 42-58. ISSN 2462-1641 https://borneoakademika.sabah.uitm.edu.my/ |
| spellingShingle | Group work in research Musculoskeletal system. Movements Electromyography Fu, Zinvi Bani Hashim, Ahmad Yusairi Jamaludin, Zamberi Mohamad, Imran Syakir Effect of forearm rotation towards cross-user classification accuracy of forearm gestures / Zinvi Fu … [et al.] |
| title | Effect of forearm rotation towards cross-user classification accuracy of forearm gestures / Zinvi Fu … [et al.] |
| title_full | Effect of forearm rotation towards cross-user classification accuracy of forearm gestures / Zinvi Fu … [et al.] |
| title_fullStr | Effect of forearm rotation towards cross-user classification accuracy of forearm gestures / Zinvi Fu … [et al.] |
| title_full_unstemmed | Effect of forearm rotation towards cross-user classification accuracy of forearm gestures / Zinvi Fu … [et al.] |
| title_short | Effect of forearm rotation towards cross-user classification accuracy of forearm gestures / Zinvi Fu … [et al.] |
| title_sort | effect of forearm rotation towards cross-user classification accuracy of forearm gestures / zinvi fu … [et al.] |
| topic | Group work in research Musculoskeletal system. Movements Electromyography |
| url | https://ir.uitm.edu.my/id/eprint/50270/1/50270.pdf https://ir.uitm.edu.my/id/eprint/50270/ https://borneoakademika.sabah.uitm.edu.my/ |
| url_provider | http://ir.uitm.edu.my/ |