EMG Signal Based Human Stress Level Classification Using Wavelet Packet Transform

The myoelectric signal (MES) with broad applications in various areas especially in prosthetics and myoelectric control, is one of the biosignals utilized in helping humans to control equipments. In this paper, a technique for feature extraction of forearm electromyographic (EMG) signals using wavelet packet transform (WPT) and singular value decomposition (SVD) is proposed. In the first step, the WPT is employed to generate a wavelet decomposition tree from which features are extracted. In the second step, an algorithm based on singular value decomposition (SVD) method is introduced to compute the feature vectors for every hand motion. This technique can successfully identify eight hand motions including forearm pronation, forearm supination, wrist flexion, wrist abduction, wrist adduction, chuck grip, spread fingers and rest state. These motions can be obtained by measuring the surface EMG signal through sixteen electrodes mounted on the pronator and supinator teres, flexor digitorum, sublimas, extensor digitorum communis, and flexor and extensor carpi ulnaris. Moreover, through quantitative comparison with other feature extraction methods like entropy concept in this paper, SVD method has a better performance. The results showed that proposed technique can achieve a classification recognition accuracy of over 96% for the eight hand motions.

Download Full-text

Multifunctional Prosthesis Control with Simulation of Myoelectric Signals

KnE Engineering ◽

10.18502/keg.v5i6.7101 ◽

2020 ◽

Author(s):

João Fermeiro ◽

Filipa Moreira ◽

José Pombo ◽

Rosário Calado ◽

Sílvio Mariano

Keyword(s):

Neural Networks ◽

Feature Extraction ◽

Support Vector Machines ◽

Wavelet Packet ◽

Wavelet Packet Transform ◽

Support Vector ◽

Signal Conditioning ◽

Myoelectric Signals ◽

Emg Signal ◽

Vector Machines

The skeletal muscle activation generates electric signals called myoelectric signals. In recent years a strong scientific activity has been developed in the recognition of limb movements from electromyography (EMG) signals recorded from non-invasive (surface) electrodes, in order to design systems for prosthetic control. Surface EMG acquire the activation of surrounding muscles and for that reason the obtained signal needs to be conditioned and processed, with pattern recognition techniques for extraction and classification. In this work EMG signals were acquired for two hand movements, “hand close” and “hand open”. The EMG electrodes were placed on the forearm and positioned over the extensor digitorum muscle, for the “hand open” and flexor digitorum muscle, for the “hand close”. Using MATLAB software the signal conditioning, feature extraction and classification were performed. The feature extraction process was carried with the Wavelet Packet Transform (WPT) technique and the classification process was done with two different techniques for comparison purposes, Neural Networks (NN) and Support Vector Machines (SVM). The results show that the SVM classifier used presented better classification performance compared to NN classifier used. Keywords: EMG, Signal conditioning, Wavelet Packet Transform (WPT), Neural Networks (NN), Support Vector Machines (SVM)

Download Full-text