Hand Motion Recognition from Single Channel Surface EMG Using Wavelet & Artificial Neural Network

Abstract

The strength of the muscle contraction can be easily measured by the muscle activity extracted at the skin surface. Analysis of surface Electromyogram (sEMG) is one of the standard procedures to identify posture, gesture and actions (i.e. control of prosthesis via learnt body actions). sEMG signals are usually complex in nature. It can be easily classified into differentiated muscular activities with appropriate signal processing tools. In order to analyze its complexity, various studies have been carried out but have proved unsuccessful, due to huge differences in muscular activities of some muscles over the other. This paper presents a new technique to identify low level hand movement by classifying the single channel sEMG. Single channel sEMG analysis is preferred over multi-channel due to its simplicity, computational cost and efficiency. Wavelet transformation and artificial neural network (ANN) classifier are utilized to classify and analyze the sEMG signal in a better way. c 2014 The Authors. Published by Elsevier B.V. Peer-review under responsibility of organizing committee of the 4th International Conference on Advances in Computing, Communication and Control (ICAC3'15).

sEMG Based Human Motion Intention Recognition

“…It is only used to analyze the fatigue of muscle [34]. For the timefrequency domain feature, Fourier Transform Features [27] and Wavelet Transform Features [35] are commonly used.…”

“…The results showed that the average classification accuracy could reach 96.7%. Mane et al [35] utilized ANN to classify open palm, closed palm, and wrist extension of hand motion. Discrete wavelet transform was used for feature extraction.…”

Pattern Recognition of Single-Channel sEMG Signal Using PCA and ANN Method to Classify Nine Hand Movements

“…The studies presented in Table 1 show that the support vector machine (SVM), k-nearest neighbors (KNN), and artificial neural network (ANN) have been commonly used for EMG pattern recognition as classifiers. Most of the previous research employed sEMG signals with more than one channel [6][7][8][9][10][11][12][13][14]. The range of the sample frequency of the sEMG data acquisition was from 1 kHz to 4 kHz.…”

“…Multiclass classification with a single-channel sEMG sensor is quite challenging, especially with lower sampling frequency and a higher number class. The previous study conducted hand gesture multi-class classification of a single-channel sEMG sensor with a sampling frequency of 1000 Hz [5,11]. The number of classes that have been studied in the research is five and three, respectively.…”

Human-Computer Interaction for Image Guided Surgery Systems using Physiological Signals: Application to Deep Brain Stimulation Surgery

“…[8]. The success of this applications relies on the features extraction, but as told in [4] "the nature of EMG signal is complex and highly nonlinear that makes it difficult to have an explicit relation between the measured signals and a motion command. To distinguish and identify the functionality of different sEMG signals from their extracted features, pattern recognition techniques are very important" is not easy to extract features from sEMG signals without a pre-processing of them so there are different methods to extract features from sEMG signals in time and frequency domain [9].…”