连续小波变换和深度卷积注意网络的手势识别。

Gesture recognition of continuous wavelet transform and deep convolution attention network.

机构信息

College of Electronic and Information Engineering, Hebei University, Baoding, China.

Key Laboratory of Digital Medical Engineering of Hebei Province, Hebei University, Baoding, China.

出版信息

Math Biosci Eng. 2023 Apr 25;20(6):11139-11154. doi: 10.3934/mbe.2023493.

DOI:10.3934/mbe.2023493

PMID:37322975

Abstract

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.

摘要

为了解决深度卷积神经网络（DCNN）中缺失数据特征的问题，本文提出了一种改进的手势识别方法。该方法首先使用连续小波变换提取表面肌电图（sEMG）的时频声谱图。然后，引入空间注意力模块（SAM）构建 DCNN-SAM 模型。嵌入残差模块可以改善相关区域的特征表示，减少特征缺失的问题。最后，通过 10 种不同的手势进行实验验证。结果验证了改进方法的识别准确率为 96.1%。与 DCNN 相比，准确率提高了约 6 个百分点。