A Multi-Class SVM for Decoding the Human Activity Mode from sEMG Signals

被引:0
作者
Kalani, Hadi [1 ]
Tahamipour-Z, S. Mohammad [2 ]
Kardan, Iman [3 ]
Akbarzadeh, Alireza [3 ]
Ebrahimi, Amirali [4 ]
Sede, Reza [2 ]
机构
[1] Sadjad Univ Technol, Dept Mech Engn, Mashhad, Razavi Khorasan, Iran
[2] Ferdowsi Univ Mashhad, Elect Engn Dept, Mashhad, Razavi Khorasan, Iran
[3] Ferdowsi Univ Mashhad, Mech Engn Dept, Mashhad, Razavi Khorasan, Iran
[4] Ferdowsi Univ Mashhad, Comp Engn Dept, Mashhad, Razavi Khorasan, Iran
来源
2019 7TH INTERNATIONAL CONFERENCE ON ROBOTICS AND MECHATRONICS (ICROM 2019) | 2019年
关键词
Surface Electromyography (sEMG); Support Vector Machine (SVM); Flexion and Extension Muscles; Exoskeleton Robot; DRIVEN MUSCULOSKELETAL MODEL; FEEDBACK ASSISTIVE CONTROL; POWERED EXOSKELETON; EMG; PREDICTION; ROBOT; REHABILITATION; GENERATION; DESIGN;
D O I
暂无
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Nowadays, the relationship between muscles' electrical activity and body movements has been investigated in many medical applications. This Paper proposes the classification of activity mode of healthy human subjects based on surface Electromyography (sEMG) signals. Support vector machine (SVM) methodology is used to predict human activity mode, using the sEMG signals recorded from four main muscles in flexion and extension of the left leg. The presented method shows promising results with classification accuracies of up to 93%. This method provides a reliable solution for the classification of human activity modes, required in many applications like control of exoskeleton robots.
引用
收藏
页码:265 / 269
页数:5
相关论文
empty
未找到相关数据