
EMG-Based Feature Extraction and Classification for Prosthetic Hand Control
Author(s) -
Reza Bagherian Azhiri,
Mohammad Esmaeili,
Mehrdad Nourani
Publication year - 2022
Publication title -
epic series in computing
Language(s) - English
Resource type - Conference proceedings
ISSN - 2398-7340
DOI - 10.29007/zflb
Subject(s) - computer science , feature extraction , pattern recognition (psychology) , artificial intelligence , consistency (knowledge bases) , wavelet , signal (programming language) , process (computing) , feature (linguistics) , set (abstract data type) , speech recognition , linguistics , philosophy , programming language , operating system
In recent years, real-time control of prosthetic hands has gained a great deal of attention. In particular, real-time analysis of Electromyography (EMG) signals has several challenges to achieve an acceptable accuracy and execution delay. In this paper, we address some of these challenges by improving the accuracy in a shorter signal length. We first introduce a set of new feature extraction functions applying on each level of wavelet decomposition. Then, we propose a postprocessing ap- proach to process the neural network outputs. The experimental results illustrate that the proposed method enhances the accuracy of real-time classification of EMG signals up to 95.5 percent for 800 msec signal length. The proposed postprocessing method achieves higher consistency compared with conventional majority voting and Bayesian fusion methods.