Study on Interaction Between Temporal and Spatial Information in Classification of EMG Signals for Myoelectric Prostheses

Abstract

Advanced forearm prosthetic devices employ classifiers to recognize different electromyography (EMG) signal patterns, in order to identify the user's intended motion gesture. The classification accuracy is one of the main determinants of real-time controllability of a prosthetic limb and hence the necessity to achieve as high an accuracy as possible. In this paper, we study the effects of the temporal and spatial information provided to the classifier on its off-line performance and analyze their inter-dependencies. EMG data associated with seven practical hand gestures were recorded from partial-hand and trans-radial amputee volunteers as well as able-bodied volunteers. An extensive investigation was conducted to study the effect of analysis window length, window overlap, and the number of electrode channels on the classification accuracy as well as their interactions. Our main discoveries are that the effect of analysis window length on classification accuracy is practically independent of the number of electrodes for all participant groups; window overlap has no direct influence on classifier performance, irrespective of the window length, number of channels, or limb condition; the type of limb deficiency and the existing channel count influence the reduction in classification error achieved by adding more number of channels; partial-hand amputees outperform trans-radial amputees, with classification accuracies of only 11.3% below values achieved by able-bodied volunteers.

Assessment on Stationarity of EMG Signals with Different Windows Size During Isotonic Contractions

“…They also stated that if the window size increases, it may have a negative impact on the real-time processing, and results in a higher computational load. It was reported that increasing window size from 250 ms to 300 ms and upwards provides no more than 1% average improvement in classification accuracy for each step-wise increment of the window length for all participant cases in [36]. Instead of aiming for higher classification accuracy, this study proved that the stationarity of EMG signals was higher within 200 ms window size, which may enhance the real-time processing in near future.…”

sEMG-Based Gesture Recognition with Convolution Neural Networks

“…As described in [14], to satisfy the requirement of real-time control, the time latency is less than 300 ms. The more extended window lengths led to higher controller delays as well as increased classification accuracy [42][43][44]. In previous works [13,40,45], L is greater than 200 ms to get higher classification accuracy.…”

Domain Adaptation for sEMG-based Gesture Recognition with Recurrent Neural Networks

“…Many researchers focused on presenting new sEMG features based on their domain knowledge or analyzing existing features to propose new feature sets. Traditional machine learning classifiers have been employed to recognize sEMGbased gestures, such as k-Nearest Neighbor (kNN) [20], Linear Discriminate Analysis (LDA) [21], Hidden Markov Model (HMM) [22], and Support Vector Machine (SVM) [20] [23]. The Convolutional Neural Network (CNN) architecture is the most widely used deep learning technique for sEMGbased gesture recognition.…”