陈万忠,
张涛,
蒋鋆,
任水芳
吉林大学通信工程学院 长春 130012
基金项目:吉林省科技发展计划项目(20190302034GX)
详细信息
作者简介:严光君：男，1995年生，硕士生，研究方向为生物信号感知与模式识别
陈万忠：男，1963年生，教授，研究方向为生物信号处理和人机交互
张涛：男，1991年生，讲师，研究方向为信号处理与模式识别
蒋鋆：女，1994年生，博士生，研究方向为生物信号处理与模式识别
任水芳：女，1994年生，硕士生，研究方向为信号处理与模式识别
通讯作者:严光君 yangj18@mails.jlu.edu.cn
中图分类号:TP391.4计量
文章访问数:201
HTML全文浏览量:109
PDF下载量:26
被引次数:0
出版历程
收稿日期:2020-10-04
修回日期:2021-03-08
网络出版日期:2021-04-08
刊出日期:2021-09-16
Research on Gesture Classification Methods in Amputee Subjects Based on Gray Theory Model
Guangjun YAN,,Wanzhong CHEN,
Tao ZHANG,
Yun JIANG,
Shuifang REN
College of Communication Engineering, Jilin University, Changchun 130012, China
Funds:The Program of Science and Technology of Jilin Province (20190302034GX)
摘要
摘要:针对截肢者手势动作特征提取复杂、动作识别率较低的问题，该文提出一种基于灰度模型的特征提取方法。首先对预处理后的肌电信号与加速度信号经滑动窗信号截取。然后提取表面肌电信号均值、灰度模型的驱动项系数和加速度信号的绝对值均值构成特征向量，最后对滑动窗截取信号特征进行连续的识别。该文采用NinaPro(Non invasive adaptive Prosthetics)公开数据集对提出的方法进行验证，实验表明该文算法能够有效提取肌电和加速度信号的特征，对9名截肢受试者的17类手势动作的平均识别率达到91.14%，提高了17类手势的识别准确率，为仿生假肢人机交互控制算法提供了一种新的思路。
关键词:灰度理论模型/
手势动作分类/
表面肌电信号/
连续识别
Abstract:In view of the complexity and low accuracy of feature extraction of amputees’ movement gestures, a feature extraction method based on gray model is proposed in this paper. Firstly, the pre-processed surface ElectroMyoGraphy (sEMG) and acceleration signals are intercepted by sliding window. Then, the mean value of the surface EMG signal, the driving coefficient of the gray model and the absolute mean value of the acceleration signal are extracted as features to form a feature vector. Finally, the features of the signal intercepted by sliding window are identified continuously. The proposed method is verified using NinaPro (Non Invasive Adaptive Prosthetics) public dataset, experimental results show that the proposed algorithm can effectively extract the characteristics of the electromyography and acceleration signals. An average accuracy of 91.14% is reached for 17 action gestures of 9 amputation subjects. The proposed approach provides a new way for the control algorithm of bionic limbs based human-computer interaction.
Key words:Gray theory model/
Gesture classification/
Surface electromyography/
Continuous recognition
PDF全文下载地址:
https://jeit.ac.cn/article/exportPdf?id=758ee9b3-1e75-489d-9131-83b053bf6421
