A Spatio-Temporal Graph Convolutional Network for Gesture Recognition from High-Density Electromyography

被引:3
作者
Zhong, Wenjuan [1 ]
Zhang, Yuyang [1 ]
Fu, Peiwen [1 ]
Xiong, Wenxuan [1 ]
Zhang, Mingming [1 ]
机构
[1] Southern Univ Sci & Technol, Dept Biomed Engn, Shenzhen, Peoples R China
来源
2023 29TH INTERNATIONAL CONFERENCE ON MECHATRONICS AND MACHINE VISION IN PRACTICE, M2VIP 2023 | 2023年
基金
中国国家自然科学基金;
关键词
Graph convolution networks; gesture recognition; Human-machine interface; high density sEMG; Muscle network;
D O I
10.1109/M2VIP58386.2023.10413402
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Accurate hand gesture prediction is crucial for effective upper-limb prosthetic limbs control. As the high flexibility and multiple degrees of freedom exhibited by human hands, there has been a growing interest in integrating deep networks with high-density surface electromyography (HD-sEMG) grids to enhance gesture recognition capabilities. However, many existing methods fall short in fully exploit the specific spatial topology and temporal dependencies present in HD-sEMG data. Additionally, these studies are often limited number of gestures and lack generality. Hence, this study introduces a novel gesture recognition method, named STGCN-GR, which leverages spatio-temporal graph convolution networks for HD-sEMG-based human-machine interfaces. Firstly, we construct muscle networks based on functional connectivity between channels, creating a graph representation of HD-sEMG recordings. Subsequently, a temporal convolution module is applied to capture the temporal dependences in the HD-sEMG series and a spatial graph convolution module is employed to effectively learn the intrinsic spatial topology information among distinct HD-sEMG channels. We evaluate our proposed model on a public HD-sEMG dataset comprising a substantial number of gestures (i.e., 65). Our results demonstrate the remarkable capability of the STGCN-GR method, achieving an impressive accuracy of 91.07% in predicting gestures, which surpasses state-of-the-art deep learning methods applied to the same dataset.
引用
收藏
页数:6
相关论文
共 35 条
[31]   A Feature Adaptive Learning Method for High-Density sEMG-Based Gesture Recognition [J].
Zhang, Yingwei ;
Chen, Yiqiang ;
Yu, Hanchao ;
Yang, Xiaodong ;
Sun, Ruizhe ;
Zeng, Bixiao .
PROCEEDINGS OF THE ACM ON INTERACTIVE MOBILE WEARABLE AND UBIQUITOUS TECHNOLOGIES-IMWUT, 2021, 5 (01)
[32]   Deep Heterogeneous Dilation of LSTM for Transient-Phase Gesture Prediction Through High-Density Electromyography: Towards Application in Neurorobotics [J].
Sun, Tianyun ;
Hu, Qin ;
Libby, Jacqueline ;
Atashzar, S. Farokh .
IEEE ROBOTICS AND AUTOMATION LETTERS, 2022, 7 (02) :2851-2858
[33]   S-CONVNET: A SHALLOW CONVOLUTIONAL NEURAL NETWORK ARCHITECTURE FOR NEUROMUSCULAR ACTIVITY RECOGNITION USING INSTANTANEOUS HIGH-DENSITY SURFACE EMG IMAGES [J].
Islam, Md. Rabiul ;
Massicotte, Daniel ;
Nougarou, Francois ;
Massicotte, Philippe ;
Zhu, Wei-Ping .
42ND ANNUAL INTERNATIONAL CONFERENCES OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY: ENABLING INNOVATIVE TECHNOLOGIES FOR GLOBAL HEALTHCARE EMBC'20, 2020, :744-749
[34]   Deep graph convolutional network-based high-performance detection method for spectral domain gesture image stream [J].
Chen, Hong ;
Geng, Qingjia ;
Liu, Aiyong ;
Zhao, Hongdong .
JOURNAL OF ELECTRONIC IMAGING, 2023, 32 (02)
[35]   D-STGCNT: A Dense Spatio-Temporal Graph Conv-GRU Network based on transformer for assessment of patient physical rehabilitation [J].
Mourchid, Youssef ;
Slama, Rim .
COMPUTERS IN BIOLOGY AND MEDICINE, 2023, 165