Research on sEMG gesture recognition based on DenseNet and multidomain features fusion

JIN Yahui; LIU Xin; LIAN Dashan; GUO Yina

Chinese

您当前的位置：

首页 >

文章列表页 >

Research on sEMG gesture recognition based on DenseNet and multidomain features fusion

Research & Approach | 更新时间：2026-01-22

- Research on sEMG gesture recognition based on DenseNet and multidomain features fusion
- Vol. 45, Issue 1, Pages: 30-34(2026)
- 作者机构：
  
  太原科技大学电子信息工程学院,山西,太原,030024
- 作者简介：
- 基金信息：
- DOI：
  CLC： TP391
- Published：2026
- 稿件说明：
移动端阅览
JIN Yahui, LIU Xin, LIAN Dashan, et al. Research on sEMG gesture recognition based on DenseNet and multidomain features fusion[J]. 2026, 45(1): 30-34.
DOI：

JIN Yahui, LIU Xin, LIAN Dashan, et al. Research on sEMG gesture recognition based on DenseNet and multidomain features fusion[J]. 2026, 45(1): 30-34. DOI：

摘要

基于表面肌电（sEMG）信号的手势识别在人机交互领域应用广泛

快速准确识别手势动作可以提供更好的用户体验。由于个体差异性导致在多任务中

整体识别准确率低。提出一种密集连接卷积网络（DenseNet）和多域特征融合的sEMG手势识别方法。首先

从sEMG信号中提取时域和频域特征构成特征集

并与原始信号融合作为网络输入

增强网络输入数据的表达能力。其次

使用融合挤压—激励（SE）注意力和多尺度空洞卷积的DenseNet进行特征提取与分类识别。实验结果表明

在NinaPro DB2数据集中

手势识别整体准确率达到了88.06%

在整体和分类运动中识别性能都有所提升。

Abstract

Hand gesture recognition based on surface electromyography(sEMG)signals is widely used in the field of human-computer interaction

accurately and quickly recognizing gesture actions can provide a better user experience.However

the overall recognition accuracy is low in multitask scenarios due to individual differences.An sEMG gesture recognition method based on densely connected convolutional network(DenseNet) and multi-domain feature fusion is proposed.Firstly

time-domain and frequency-domain features are extracted from sEMG signals to form a feature set

which is fused with the original signals as network inputs to enhance the representation ability of input data.Secondly

a DenseNet network fusing squeeze-and-excitation(SE) attention and multi-scale dilated convolution is used for feature extraction and classification recognition.Experimental results show that the overall recognition accuracy of gesture recognition reaches 88.06% on the NinaPro DB2 dataset

and the recognition performance is improved in both overall and classified movements.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Fine-grained finger motion recognition algorithm based on wearable devices

Single-component muscle fatigue modal extraction of sEMG signals based on ACMD

Gesture recognition based on multi-channel surface electromyography sensor

Development of electrical impedance tomography system for gesture recognition

Research on novel gesture recognition device based on capacitive sensing

Related Author

GUAN Boliang

CHEN Guancheng

CHEN Huihui

YAN Yuanzheng

LI Shaobo

REN Yan

ZHANG Yong

LÜ Donghao

Related Institution

School of Computer Science and Artificial Intelligence,Foshan University

School of Information Engineering,Inner Mongolia University of Science and Technology

College of Artificial Intelligence,Dongguan Polytechnic

Department of Computer Engineering,Maoming Polytechnic

College of Mechanical and Electrical Engineering, Nanjing University of Aeronautics and Astronautics

⁰