Deep Cross-User Models Reduce the Training Burden in Myoelectric Control
The effort, focus, and time to collect data and train EMG pattern recognition systems is one of the largest barriers to their widespread adoption in commercial applications. In addition to multiple repetitions of motions, including exemplars of confounding factors during the training protocol has be...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2021-05-01
|
| Series: | Frontiers in Neuroscience |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fnins.2021.657958/full |
| _version_ | 1818607110013845504 |
|---|---|
| author | Evan Campbell Angkoon Phinyomark Erik Scheme |
| author_facet | Evan Campbell Angkoon Phinyomark Erik Scheme |
| author_sort | Evan Campbell |
| collection | DOAJ |
| description | The effort, focus, and time to collect data and train EMG pattern recognition systems is one of the largest barriers to their widespread adoption in commercial applications. In addition to multiple repetitions of motions, including exemplars of confounding factors during the training protocol has been shown to be critical for robust machine learning models. This added training burden is prohibitive for most regular use cases, so cross-user models have been proposed that could leverage inter-repetition variability supplied by other users. Existing cross-user models have not yet achieved performance levels sufficient for commercialization and require users to closely adhere to a training protocol that is impractical without expert guidance. In this work, we extend a previously reported adaptive domain adversarial neural network (ADANN) to a cross-subject framework that requires very little training data from the end-user. We compare its performance to single-repetition within-user training and the previous state-of-the-art cross-subject technique, canonical correlation analysis (CCA). ADANN significantly outperformed CCA for both intact-limb (86.8–96.2%) and amputee (64.1–84.2%) populations. Moreover, the ADANN adaptation computation time was substantially lower than the time otherwise devoted to conducting a full within-subject training protocol. This study shows that cross-user models, enabled by deep-learned adaptations, may be a viable option for improved generalized pattern recognition-based myoelectric control. |
| first_indexed | 2024-12-16T14:21:32Z |
| format | Article |
| id | doaj.art-b7ac1f66c4a9410cb4188462398a6cca |
| institution | Directory Open Access Journal |
| issn | 1662-453X |
| language | English |
| last_indexed | 2024-12-16T14:21:32Z |
| publishDate | 2021-05-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neuroscience |
| spelling | doaj.art-b7ac1f66c4a9410cb4188462398a6cca2022-12-21T22:28:28ZengFrontiers Media S.A.Frontiers in Neuroscience1662-453X2021-05-011510.3389/fnins.2021.657958657958Deep Cross-User Models Reduce the Training Burden in Myoelectric ControlEvan CampbellAngkoon PhinyomarkErik SchemeThe effort, focus, and time to collect data and train EMG pattern recognition systems is one of the largest barriers to their widespread adoption in commercial applications. In addition to multiple repetitions of motions, including exemplars of confounding factors during the training protocol has been shown to be critical for robust machine learning models. This added training burden is prohibitive for most regular use cases, so cross-user models have been proposed that could leverage inter-repetition variability supplied by other users. Existing cross-user models have not yet achieved performance levels sufficient for commercialization and require users to closely adhere to a training protocol that is impractical without expert guidance. In this work, we extend a previously reported adaptive domain adversarial neural network (ADANN) to a cross-subject framework that requires very little training data from the end-user. We compare its performance to single-repetition within-user training and the previous state-of-the-art cross-subject technique, canonical correlation analysis (CCA). ADANN significantly outperformed CCA for both intact-limb (86.8–96.2%) and amputee (64.1–84.2%) populations. Moreover, the ADANN adaptation computation time was substantially lower than the time otherwise devoted to conducting a full within-subject training protocol. This study shows that cross-user models, enabled by deep-learned adaptations, may be a viable option for improved generalized pattern recognition-based myoelectric control.https://www.frontiersin.org/articles/10.3389/fnins.2021.657958/fullEMGgesture recognitiondeep learningdomain adaptationcross-usertraining burden |
| spellingShingle | Evan Campbell Angkoon Phinyomark Erik Scheme Deep Cross-User Models Reduce the Training Burden in Myoelectric Control Frontiers in Neuroscience EMG gesture recognition deep learning domain adaptation cross-user training burden |
| title | Deep Cross-User Models Reduce the Training Burden in Myoelectric Control |
| title_full | Deep Cross-User Models Reduce the Training Burden in Myoelectric Control |
| title_fullStr | Deep Cross-User Models Reduce the Training Burden in Myoelectric Control |
| title_full_unstemmed | Deep Cross-User Models Reduce the Training Burden in Myoelectric Control |
| title_short | Deep Cross-User Models Reduce the Training Burden in Myoelectric Control |
| title_sort | deep cross user models reduce the training burden in myoelectric control |
| topic | EMG gesture recognition deep learning domain adaptation cross-user training burden |
| url | https://www.frontiersin.org/articles/10.3389/fnins.2021.657958/full |
| work_keys_str_mv | AT evancampbell deepcrossusermodelsreducethetrainingburdeninmyoelectriccontrol AT angkoonphinyomark deepcrossusermodelsreducethetrainingburdeninmyoelectriccontrol AT erikscheme deepcrossusermodelsreducethetrainingburdeninmyoelectriccontrol |