Iterative Self-Training Based Domain Adaptation for Cross-User sEMG Gesture Recognition
文献类型：期刊论文
| 作者 | Wang, Kang3,5; Chen, Yiqiang1,2,3,4; Zhang, Yingwei1,2,3,4; Yang, Xiaodong1,2,3,4; Hu, Chunyu5 |
| 刊名 | IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING
 |
| 出版日期 | 2023 |
| 卷号 | 31页码:2974-2987 |
| ISSN号 | 1534-4320 |
| 关键词 | Surface electromyography gesture recognition cross-user domain adaptation semi-supervised learning |
| DOI | 10.1109/TNSRE.2023.3293334 |
| 英文摘要 | Surface electromyography (sEMG) based gesture recognition has received broad attention and application in rehabilitation areas for its direct and fine-grained sensing ability. sEMG signals exhibit strong user dependence properties among users with different physiology, causing the inapplicability of the recognition model on new users. Domain adaptation is the most representative method to reduce the user gap with feature decoupling to acquire motion-related features. However, the existing domain adaptation method shows awful decoupling results when handling complex time-series physiological signals. Therefore, this paper proposes an Iterative Self-Training based Domain Adaptation method (STDA) to supervise the feature decoupling process with the pseudo-label generated by self-training and to explore cross-user sEMG gesture recognition. STDA mainly consists of two parts, discrepancy-based domain adaptation (DDA) and pseudo-label iterative update (PIU). DDA aligns existing users' data and new users' unlabeled data with a Gaussian kernel-based distance constraint. PIU Iteratively continuously updates pseudo-labels to generate more accurate labelled data on new users with category balance. Detailed experiments are performed on publicly available benchmark datasets, including the NinaPro dataset (DB-1 and DB-5) and the CapgMyo dataset (DB-a, DB-b, and DB-c). Experimental results show that the proposed method achieves significant performance improvement compared with existing sEMG gesture recognition and domain adaption methods. |
| 资助项目 | National Key Research and Development Plan of China[2021YFC2501202] ; National Natural Science Foundation of China[61972383] ; National Natural Science Foundation of China[62202455] ; Beijing Municipal Science amp; Technology Commission[Z221100002722009] ; Innovative Research Program of Shandong Academy of Intelligent Computing Technology[SDAICT2191010] |
| WOS研究方向 | Engineering ; Rehabilitation |
| 语种 | 英语 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| WOS记录号 | WOS:001037757900002 |
| 源URL | [http://119.78.100.204/handle/2XEOYT63/21339]  |
| 专题 | 中国科学院计算技术研究所期刊论文_英文 |
| 通讯作者 | Chen, Yiqiang |
| 作者单位 | 1.Beijing Key Lab Mobile Comp & Pervas Device, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Beijing 101408, Peoples R China 3.Shangdong Acad Intelligent Comp Technol, Jinan 100190, Peoples R China 4.Chinese Acad Sci, Inst Comp Technol, Beijing 100045, Peoples R China 5.Qilu Univ Technol, Shandong Acad Sci, Sch Comp Sci & Technol, Jinan 250353, Peoples R China |
| 推荐引用方式 GB/T 7714 | Wang, Kang,Chen, Yiqiang,Zhang, Yingwei,et al. Iterative Self-Training Based Domain Adaptation for Cross-User sEMG Gesture Recognition[J]. IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING,2023,31:2974-2987. |
| APA | Wang, Kang,Chen, Yiqiang,Zhang, Yingwei,Yang, Xiaodong,&Hu, Chunyu.(2023).Iterative Self-Training Based Domain Adaptation for Cross-User sEMG Gesture Recognition.IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING,31,2974-2987. |
| MLA | Wang, Kang,et al."Iterative Self-Training Based Domain Adaptation for Cross-User sEMG Gesture Recognition".IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING 31(2023):2974-2987. |
入库方式： OAI收割
来源：计算技术研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。