A Dynamic Balanced Single-Source Domain Generalization Model for Cross-Posture Myoelectric Control
Electromyography (EMG) based Human-Computer Interaction (HCI) through wearable devices frequently encounter variability in body postures, which can modify the amplitude and frequency features of surface EMG (sEMG) signals. This variability often results in reduced gesture recognition accuracy. To en...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Transactions on Neural Systems and Rehabilitation Engineering |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10811947/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841536181757542400 |
|---|---|
| author | Tanying Su Xin Tan Xinyu Jiang Xiao Liu Bo Hu Chenyun Dai |
| author_facet | Tanying Su Xin Tan Xinyu Jiang Xiao Liu Bo Hu Chenyun Dai |
| author_sort | Tanying Su |
| collection | DOAJ |
| description | Electromyography (EMG) based Human-Computer Interaction (HCI) through wearable devices frequently encounter variability in body postures, which can modify the amplitude and frequency features of surface EMG (sEMG) signals. This variability often results in reduced gesture recognition accuracy. To enhance the robustness of sEMG-based gesture interfaces, mitigating the effects of body position variability is essential. In this paper, we proposed a Dynamic Balanced Single-Source Domain Generalization (DBSS-DG) transfer learning framework, which only used sEMG signal data from one posture as source domain for model training but can also generate good performance under different body postures as target domain. Validation was performed on the sEMG dataset from 16 subjects across four postures: standing, sitting, walking, and lying. With standing as the source domain, the model achieved gesture recognition accuracies of 90.79 ± 0.09%, 88.78 ± 0.06%, and 90.87 ± 0.1% for sitting, walking, and lying as the target domains, respectively, producing an average improvement of 4.71% over non-transfer learning approaches. Furthermore, the performance of our model exceeded that of many well-known single-source domain generalization methods, establishing its effectiveness in practical applications. |
| format | Article |
| id | doaj-art-7150f410d03b4555bb7b42e024ccf426 |
| institution | Kabale University |
| issn | 1534-4320 1558-0210 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Transactions on Neural Systems and Rehabilitation Engineering |
| spelling | doaj-art-7150f410d03b4555bb7b42e024ccf4262025-01-15T00:00:09ZengIEEEIEEE Transactions on Neural Systems and Rehabilitation Engineering1534-43201558-02102025-01-013325526510.1109/TNSRE.2024.352122910811947A Dynamic Balanced Single-Source Domain Generalization Model for Cross-Posture Myoelectric ControlTanying Su0https://orcid.org/0009-0007-8236-3364Xin Tan1https://orcid.org/0000-0001-6726-1289Xinyu Jiang2https://orcid.org/0000-0002-8518-1415Xiao Liu3https://orcid.org/0000-0001-5514-021XBo Hu4https://orcid.org/0000-0001-6348-010XChenyun Dai5https://orcid.org/0000-0002-3056-4339School of Information Science and Technology, Fudan University, Shanghai, ChinaSchool of Information Science and Technology, Fudan University, Shanghai, ChinaSchool of Informatics, The University of Edinburgh, Edinburgh, U.K.School of Information Science and Technology, Fudan University, Shanghai, ChinaSchool of Information Science and Technology, Fudan University, Shanghai, ChinaSchool of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, ChinaElectromyography (EMG) based Human-Computer Interaction (HCI) through wearable devices frequently encounter variability in body postures, which can modify the amplitude and frequency features of surface EMG (sEMG) signals. This variability often results in reduced gesture recognition accuracy. To enhance the robustness of sEMG-based gesture interfaces, mitigating the effects of body position variability is essential. In this paper, we proposed a Dynamic Balanced Single-Source Domain Generalization (DBSS-DG) transfer learning framework, which only used sEMG signal data from one posture as source domain for model training but can also generate good performance under different body postures as target domain. Validation was performed on the sEMG dataset from 16 subjects across four postures: standing, sitting, walking, and lying. With standing as the source domain, the model achieved gesture recognition accuracies of 90.79 ± 0.09%, 88.78 ± 0.06%, and 90.87 ± 0.1% for sitting, walking, and lying as the target domains, respectively, producing an average improvement of 4.71% over non-transfer learning approaches. Furthermore, the performance of our model exceeded that of many well-known single-source domain generalization methods, establishing its effectiveness in practical applications.https://ieeexplore.ieee.org/document/10811947/Surface electromyographygesture recognitioncross-posturedomain generalizationmyoelectric control |
| spellingShingle | Tanying Su Xin Tan Xinyu Jiang Xiao Liu Bo Hu Chenyun Dai A Dynamic Balanced Single-Source Domain Generalization Model for Cross-Posture Myoelectric Control IEEE Transactions on Neural Systems and Rehabilitation Engineering Surface electromyography gesture recognition cross-posture domain generalization myoelectric control |
| title | A Dynamic Balanced Single-Source Domain Generalization Model for Cross-Posture Myoelectric Control |
| title_full | A Dynamic Balanced Single-Source Domain Generalization Model for Cross-Posture Myoelectric Control |
| title_fullStr | A Dynamic Balanced Single-Source Domain Generalization Model for Cross-Posture Myoelectric Control |
| title_full_unstemmed | A Dynamic Balanced Single-Source Domain Generalization Model for Cross-Posture Myoelectric Control |
| title_short | A Dynamic Balanced Single-Source Domain Generalization Model for Cross-Posture Myoelectric Control |
| title_sort | dynamic balanced single source domain generalization model for cross posture myoelectric control |
| topic | Surface electromyography gesture recognition cross-posture domain generalization myoelectric control |
| url | https://ieeexplore.ieee.org/document/10811947/ |
| work_keys_str_mv | AT tanyingsu adynamicbalancedsinglesourcedomaingeneralizationmodelforcrossposturemyoelectriccontrol AT xintan adynamicbalancedsinglesourcedomaingeneralizationmodelforcrossposturemyoelectriccontrol AT xinyujiang adynamicbalancedsinglesourcedomaingeneralizationmodelforcrossposturemyoelectriccontrol AT xiaoliu adynamicbalancedsinglesourcedomaingeneralizationmodelforcrossposturemyoelectriccontrol AT bohu adynamicbalancedsinglesourcedomaingeneralizationmodelforcrossposturemyoelectriccontrol AT chenyundai adynamicbalancedsinglesourcedomaingeneralizationmodelforcrossposturemyoelectriccontrol AT tanyingsu dynamicbalancedsinglesourcedomaingeneralizationmodelforcrossposturemyoelectriccontrol AT xintan dynamicbalancedsinglesourcedomaingeneralizationmodelforcrossposturemyoelectriccontrol AT xinyujiang dynamicbalancedsinglesourcedomaingeneralizationmodelforcrossposturemyoelectriccontrol AT xiaoliu dynamicbalancedsinglesourcedomaingeneralizationmodelforcrossposturemyoelectriccontrol AT bohu dynamicbalancedsinglesourcedomaingeneralizationmodelforcrossposturemyoelectriccontrol AT chenyundai dynamicbalancedsinglesourcedomaingeneralizationmodelforcrossposturemyoelectriccontrol |