Gesture recognition of continuous wavelet transform and deep convolution attention network

Xiaoguang Liu; Mingjin Zhang; Jiawei Wang; Xiaodong Wang; Tie Liang; Jun Li; Peng Xiong; Xiuling Liu

doi:10.3934/mbe.2023493

Mathematical Biosciences and Engineering (Apr 2023)

Gesture recognition of continuous wavelet transform and deep convolution attention network

Xiaoguang Liu,
Mingjin Zhang ,
Jiawei Wang,
Xiaodong Wang,
Tie Liang,
Jun Li ,
Peng Xiong,
Xiuling Liu

Affiliations

Xiaoguang Liu: 1. College of Electronic and Information Engineering, Hebei University, Baoding, China 2. Key Laboratory of Digital Medical Engineering of Hebei Province, Hebei University, Baoding, China
Mingjin Zhang: 1. College of Electronic and Information Engineering, Hebei University, Baoding, China 2. Key Laboratory of Digital Medical Engineering of Hebei Province, Hebei University, Baoding, China
Jiawei Wang: 1. College of Electronic and Information Engineering, Hebei University, Baoding, China 2. Key Laboratory of Digital Medical Engineering of Hebei Province, Hebei University, Baoding, China
Xiaodong Wang: 3. Affiliated Hospital of Hebei University, Baoding, China
Tie Liang: 1. College of Electronic and Information Engineering, Hebei University, Baoding, China 2. Key Laboratory of Digital Medical Engineering of Hebei Province, Hebei University, Baoding, China
Jun Li: 1. College of Electronic and Information Engineering, Hebei University, Baoding, China 2. Key Laboratory of Digital Medical Engineering of Hebei Province, Hebei University, Baoding, China
Peng Xiong: 1. College of Electronic and Information Engineering, Hebei University, Baoding, China 2. Key Laboratory of Digital Medical Engineering of Hebei Province, Hebei University, Baoding, China
Xiuling Liu: 1. College of Electronic and Information Engineering, Hebei University, Baoding, China 2. Key Laboratory of Digital Medical Engineering of Hebei Province, Hebei University, Baoding, China

DOI: https://doi.org/10.3934/mbe.2023493
Journal volume & issue: Vol. 20, no. 6
pp. 11139 – 11154

Abstract

Read online

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.

Published in Mathematical Biosciences and Engineering

ISSN: 1551-0018 (Online)
Publisher: AIMS Press
Country of publisher: United States
LCC subjects: Technology: Chemical technology: Biotechnology; Science: Mathematics
Website: https://www.aimspress.com/journal/MBE

About the journal

Abstract

Keywords