To solve the problem of missing data features using a deep convolutional neural network (DCNN), this paper proposes an improved gesture recognition method. The method first extracts the time-frequency spectrogram of surface electromyography (sEMG) using the continuous wavelet transform. Then, the Spatial Attention Module (SAM) is introduced to construct the DCNN-SAM model. The residual module is embedded to improve the feature representation of relevant regions, and reduces the problem of missing features. Finally, experiments with 10 different gestures are done for verification. The results validate that the recognition accuracy of the improved method is 96.1%. Compared with the DCNN, the accuracy is improved by about 6 percentage points.
基金：
Natural Science Foundation of Hebei Province [F2021201002]; National Natural Science Foundation of China [62276087]; Science and Technology Project of Hebei Education Department [ZD2020146]
第一作者机构：[1]Hebei Univ, Coll Elect & Informat Engn, Baoding, Peoples R China[2]Hebei Univ, Key Lab Digital Med Engn Hebei Prov, Baoding, Peoples R China
通讯作者：
通讯机构：[1]Hebei Univ, Coll Elect & Informat Engn, Baoding, Peoples R China[2]Hebei Univ, Key Lab Digital Med Engn Hebei Prov, Baoding, Peoples R China
推荐引用方式(GB/T 7714)：
Liu Xiaoguan,Zhang Mingjin,Wang Jiawei,et al.Gesture recognition of continuous wavelet transform and deep convolution attention network[J].MATHEMATICAL BIOSCIENCES AND ENGINEERING.2023,20(6):11139-11154.doi:10.3934/mbe.2023493.
APA：
Liu, Xiaoguan,Zhang, Mingjin,Wang, Jiawei,Wang, Xiaodong,Liang, Tie...&Liu, Xiuling.(2023).Gesture recognition of continuous wavelet transform and deep convolution attention network.MATHEMATICAL BIOSCIENCES AND ENGINEERING,20,(6)
MLA：
Liu, Xiaoguan,et al."Gesture recognition of continuous wavelet transform and deep convolution attention network".MATHEMATICAL BIOSCIENCES AND ENGINEERING 20..6(2023):11139-11154
