Decoding Electromyographic Signal With Multiple Labels for Hand Gesture Recognition
- 5 April 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 30 (10709908) , 483-487
Abstract
Surface electromyography (sEMG) is a significant interaction signal in the fields of human-computer interaction and rehabilitation assessment, as it can be used for hand gesture recognition. This paper proposes a novel MLHG model to improve the robustness of sEMG-based hand gesture recognition. The model utilizes multiple labels to decode the sEMG signals from two different perspectives. In the first view, the sEMG signals are transformed into motion signals using the proposed FES-MSCNN (Feature Extraction of sEMG with Multiple Sub-CNN modules). Furthermore, a discriminator FEM-SAGE (Feature Extraction of Motion with graph SAmple and aggreGatE model) is employed to judge the authenticity of the generated motion data. The deep features of the motion signals are extracted using the FEM-SAGE model. In the second view, the deep features of the sEMG signals are extracted using the FES-MSCNN model. The extracted features of the sEMG signals and the generated motion signals are then fused for hand gesture recognition. To evaluate the performance of the proposed model, a dataset containing sEMG signals and multiple labels from 12 subjects has been collected. The experimental results indicate that the MLHG model achieves an accuracy of $99.26\%$ for within-session hand gesture recognition, $78.47\%$ for cross-time, and $53.52\%$ for cross-subject. These results represent a significant improvement compared to using only the gesture labels, with accuracy improvements of $1.91\%$ , $5.35\%$ , and $5.25\%$ in the within-session, cross-time and cross-subject cases, respectively.Keywords
Funding Information
- National Key Research and Development Program of China (2022YFB4703204)
- CAS Project for Young Scientists in Basic Research (YSBR-034)
This publication has 18 references indexed in Scilit:
- EPGAT: Gene Essentiality Prediction With Graph Attention NetworksIEEE/ACM Transactions on Computational Biology and Bioinformatics, 2021
- Hand Gesture Recognition based on Surface Electromyography using Convolutional Neural Network with Transfer Learning MethodIEEE Journal of Biomedical and Health Informatics, 2020
- Classification of Electromyographic Hand Gesture Signals Using Modified Fuzzy C-Means Clustering and Two-Step Machine Learning ApproachIEEE Transactions on Neural Systems and Rehabilitation Engineering, 2020
- Dynamic Hand Gesture Recognition Based on a Leap Motion Controller and Two-Layer Bidirectional Recurrent Neural NetworkSensors, 2020
- Optimized Graph Convolution Recurrent Neural Network for Traffic PredictionIEEE Transactions on Intelligent Transportation Systems, 2020
- Hand Gesture Recognition Enhancement Based on Spatial Fuzzy Matching in Leap MotionIEEE Transactions on Industrial Informatics, 2019
- sEMG-Based Tremor Severity Evaluation for Parkinson's Disease Using a Light-Weight CNNIEEE Signal Processing Letters, 2019
- Repeatability of grasp recognition for robotic hand prosthesis control based on sEMG data2017
- sEMG Signal-Based Lower Limb Human Motion Detection Using a Top and Slope Feature Extraction AlgorithmIEEE Signal Processing Letters, 2016
- Dynamic Hand Gesture Recognition With Leap Motion ControllerIEEE Signal Processing Letters, 2016