A robotic arm control system integrating particle swarm optimization-genetic cooperative optimization (PSO-GA) and adaptive fuzzy proportional-derivative (AF-PD) control was proposed to address challenges in dynamic gesture recognition based on surface electromyography (sEMG), including time variability, nonlinearity, and difficulties in traditional control parameter tuning. Eight-channel sEMG signals were first collected, and multi-dimensional features were extracted to establish an end-to-end control architecture. The PSO-GA co-optimization algorithm was proposed to parallelly optimize the path constraint parameters of dynamic time warping (DTW) and the hyperparameters of the random forest (RF) classifier. An average recognition accuracy of 98.7%±0.6% is achieved on a self-constructed six-gesture dataset, which is 5.2% higher than that of the traditional RF-DTW method, while training time is reduced by 40%. A recognition rate of over 94.5%±1.0% is maintained on the public Ninapro DB1 dataset, demonstrating strong generalization capability. An AF-PD controller is designed, integrating a gesture library and a joint mapping strategy to enable smooth transitions from discrete gestures to continuous joint motion. Experimental validation shows that the system achieved a control delay of less than 100 ms and a task operation success rate of 96.3%. This work is of positive significance for advancing rehabilitation aids and human-computer interaction technologies.
WANG Yi-meng, HAN Tuan-jun, JI Zhi-qi, LI Kai-yang, LIU Qing-jiang.
sEMG Human-computer Interaction System Based on PSO-GA Collaborative Optimization[J].
Science Technology and Engineering, 2026, 26(21): 8914-8926 DOI:10.12404/j.issn.1671-1815.2600304
MohammadiazniM, LizotteJ D, TrejosL A. Stacked one-vs-one (SOvO): a new approach for multi-class classification for sEMG recognition[J]. Pattern Recognition, 2026, 172(PD): 112659.
YouBo, LiuJiaqi, ChengChenchen, et al. Research on human-machine interactive follow-up control based on sEMG[J]. Chinese Journal of Scientific Instrument, 2025, 46(3): 123-142.
[4]
LiB, QiuS, YeH, et al. Motion planning for 7-degree-of-freedom bionic arm: deep deterministic policy gradient algorithm based on imitation of human action[J]. Engineering Applications of Artificial Intelligence, 2025, 140: 109673.
ZhongXu, ZhangBi, LiJiwei, et al. Multi-modal synergistic quantitative analysis and rehabilitation assessment of lower limbs for exoskeleton[J]. Journal of Biomedical Engineering, 2023, 40(5): 953-964.
[9]
NiS, ShenJ, TangC, et al. DKD-MNet: decoupled knowledge distillation and multimodal network for sEMG-based gesture recognition[J]. Knowledge-Based Systems, 2025, 331: 114775.
HuXuezheng, TaoQing, ZhaoMuchao, et al. sEMG gesture recognition method using transfer learning[J]. Science Technology and Engineering, 2024, 24(12): 5044-5050.
[12]
DuC, DaiS, SunQ. Theoretical modeling of a bionic arm with elastomer fiber as artificial muscle controlled by periodic illumination[J]. Polymers, 2025, 17(15): 2122.
ZhaoShihao, ZhouJianhua, FuYunfa. Investigation of gesture recognition using attention mechanism CNN combined electromyography feature matrix[J]. Journal of Electronic Measurement and Instrumentation, 2023, 37(6): 59-67.
[17]
NiS, QanessA A M. PTCVS-net: patch-based transformer-CNN with variable sparse attention network for sEMG-based gesture recognition[J]. Applied Soft Computing, 2026, 187: 114316.
[18]
HeD, LiuW, WangX, et al. DSRANet: a lightweight depthwise separable residual attention network for sEMG gesture recognition[J]. Biomedical Signal Processing and Control, 2026, 113( PB): 108845.
[19]
ZhangY, WangD W. A modality-wise multi-modal transfer learning and dual stream CNN-Transformer hybrid network for ACC-sEMG-based continuous estimation of finger joint angles[J]. Biomedical Signal Processing and Control, 2026, 112: 108445.
[20]
ZhaoH, LiW, YinK, et al. Powered ankle exoskeleton control based on sEMG-driven model through adaptive fuzzy inference[J]. Mathematics, 2025, 13(23): 3839.
[21]
LiS, WangY, LiW, et al. Enhancing sEMG recognition with dynamic asymmetric training in context-informed virtual-real fusion system[J]. Biomedical Signal Processing and Control, 2026, 113: 109235.
CuiBingyan, DengJia, ZhangXiang. Hand gesture recognition based on surface electromyography[J]. Science Technology and Engineering, 2023, 23(35): 15133-15141.
LiKaiyang, HanTuanjun, LiuQingjiang. Gesture recognition method based on entropy features of surface electromyography signals and improved PSO-SVM[J]. Science Technology and Engineering, 2025, 25(35): 15155-15164.
[26]
FuL, WangJ, FuX, et al. Finite-time pade-based adaptive FNN controller implementation for microbial fuel cell with delay and multi-disturbance[J]. International Journal of Hydrogen Energy, 2025, 98: 1034-1043.
[27]
MiahM S A, ShinJ, HasanM A M. Effective features extraction and selection for hand gesture recognition using sEMG signal[J]. Multimedia Tools and Applications, 2024, 83(37): 85169-85193.
DuYihao, CaoTianfu, FanQiang, et al. Research on gesture recognition based on GA-BLS method[J]. Acta Metrologica Sinica, 2024, 45(1): 121-127.
[30]
ZhangX, LiT, SunM, et al. Replay-based incremental learning framework for gesture recognition overcoming the time-varying characteristics of sEMG signals[J]. Sensors, 2024, 24(22): 7198.
[31]
PrabhavathyT, ElumalaiV K, BalajiE. Gesture recognition framework for upper-limb prosthetics using entropy features from electromyographic signals and a Gaussian kernel SVM classifier[J]. Applied Soft Computing, 2024, 167: 112382.
[32]
LiuX, HuL, TieL, et al. Integration of convolutional neural network and vision transformer for gesture recognition using sEMG[J]. Biomedical Signal Processing and Control, 2024, 98: 106686.
[33]
ShinJ, MiahM S A, KonnaiS, et al. Hand gesture recognition using sEMG signals with a multi-stream time-varying feature enhancement approach[J]. Scientific Reports, 2024, 14(1): 22061.
[34]
WangG, LiuY, LiuK, et al. sEMG data driven-based anti-disturbance control enables adaptive interaction of lower limb rehabilitation exoskeleton[J]. Biomedical Signal Processing and Control, 2024, 94: 106347.