In order to improve the accuracy of gesture recognition, a two-flow recurrent neural network (RNN) architecture based on dynamic Adam optimization was proposed for gesture classification of surface electromyography (sEMG). The two-flow RNN was used to capture the spatiotemporal characteristics of sEMG signals, and the dynamic Adam optimizer was introduced to adjust the learning rate adaptively, which significantly improvesd the classification accuracy and model convergence speed. In the comparison experiment, the accuracy of the proposed model reaches 92.86%, which is more than 10% higher than that of traditional algorithms and single-stream RNN model, and has good classification performance and good generalization ability. The experimental results fully validate the effectiveness and superiority of the proposed model in sEMG-based gesture recognition, providing strong technical support for high-accuracy and robust electromyography-based interactive systems.
LIU Qing-jiang, HAN Tuan-jun, LI Kai-yang.
Two-stream RNN Gesture Classification Method Based on Dynamic Adam Optimization[J].
Science Technology and Engineering, 2026, 26(7): 2968-2976 DOI:10.12404/j.issn.1671-1815.2501951
CuiBingyan, ZhangXiang, DengJia. Research on lower limb motion pattern recognition by sEMG signals based on GA-BP[J]. Transducer and Microsystem Technologies, 2024, 43(9): 63-67.
HuXuezheng, TaoQing, ZhaoMuchao, et al. sEMG gesture gecognition method using transfer learning[J]. Science Technology and Engineering, 2024, 24(12): 5044-5050.
JiangHaiyan, XuXianjing, ZhongLingjun, et al. Gesture recognition of surface electromyography based on variational mode decomposition and domain adaptation[J]. Journal of Xi'an Jiaotong University, 2024, 58(5): 75-87.
WangWenmiao. Prediction of lower limb joint angles based on VMD-ELMAN Electromyographic Signals[J]. Computer Science, 2024, 51(3): 257-264.
[9]
JiangY J, SongL, ZhangJ M, et al. Multi-category gesture recognition modeling based on sEMG and IMU signals[J]. Sensors, 2022, 22(15): 5855-5855.
[10]
LuoX, HuangW, WangZ, et al. InRes-ACNet: gesture recognition model of multi-scale attention mechanisms based on surface electromyography signals[J]. Applied Sciences, 2024, 14(8): 3237.
[11]
DaiQ, WongY, KankanhalliM, et al. Rejecting unknown gestures based on surface-electromyography using variational autoencoder[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2024, 32: 750-758.
[12]
LiuY C, LaiK. Surface electromyography relation network[J]. 2024 IEEE International Conference on Advanced Robotics and Its Social Impacts (ARSO). New York: IEEE, 2024: 140-145.
[13]
MoslhiA M, ElmessieryM, AlyH H. The impact of feature extraction on classification accuracy examined by employing a signal transformer to classify hand gestures using surface electromyography signals[J]. Sensors (Basel, Switzerland), 2024(4): 1259.
CuiBingyan, DengJia, ZhangXiang. Hand gesture recognition based on surface electromyography[J]. Science Technology and Engineering, 2023, 23(35): 15133-15141.
[16]
ZafarA, WasimM, AkramA B, et al. Prediction of perinatal depression among women in Pakistan using hybrid RNN-LSTM model[J]. PeerJ Computer Science, 2025, 11: 2673.
[17]
SiuM A, VergaraI, RodríguezE H J. The use of hybrid CNN-RNN deep learning models to discriminate tumor tissue in dynamic breast thermography[J]. Journal of Imaging, 2024, 10(12): 329-329.
[18]
NingJ, ZhangW. Speech-based emotion recognition using a hybrid RNN-CNN network[J]. Signal, Image and Video Processing, 2024, 19(1): 124-124.
[19]
NannenL, WessM. A Krylov eigenvalue solver based on filtered time domain solutions[J]. Computers and Mathematics with Applications, 2024, 176: 179-188.
YouChangxin, HanJing, ChangHao, et al. Research on EMG signals gesture recognition based on migration learning strategy[J]. Journal of North University of China(Natural Science Edition), 2024, 45(4): 531-538.
YangXusheng, FanJingzhe, HuFo, et al. A gesture recognition method based on recurrent spatiotemporal deep neural networks[J]. Chinese Journal of Sensors and Actuators, 2024, 37(2): 278-287.
WangHui, ZhangPin, JinFenghu, et al. Mental fatigue state recognition method based on convolution neural network and longshort-term memory[J]. Journal of Biomedical Engineering, 2024, 41(1): 34-40.
WangWanliang, PanJie, WangZheng, et al. Recognition method of surface electromyographic signal based on two-branch network[J]. Journal of Zhejiang University(Engineering Science), 2024, 58(11): 2208-2218, 2229.
GuXuejing, ShenPan, LiuHaiwang, et al. Gesture recognition based on multi-stream convolutional network for surface emg signal[J]. Computer Applications and Software, 2022, 39(8): 220-225.