Myoelectric Pattern Recognition Performance Enhancement Using Nonlinear Features

TL;DR

This paper introduces nonlinear time-domain features, LMAV and NSV, to improve myoelectric pattern recognition performance, especially with fewer channels, validated across multiple datasets and conditions.

Contribution

Proposes novel nonlinear features LMAV and NSV, and a combined feature extraction method to enhance EMG pattern recognition accuracy with fewer channels.

Findings

Accuracy improved by up to 1.18%

Sensitivity increased by up to 5.90%

F1 score increased by up to 6.04%

Abstract

The multichannel electrode array used for electromyogram (EMG) pattern recognition provides good performance, but it has a high cost, is computationally expensive, and is inconvenient to wear. Therefore, researchers try to use as few channels as possible while maintaining improved pattern recognition performance. However, minimizing the number of channels affects the performance due to the least separable margin among the movements possessing weak signal strengths. To meet these challenges, two time-domain features based on nonlinear scaling, the log of the mean absolute value (LMAV) and the nonlinear scaled value (NSV), are proposed. In this study, we validate the proposed features on two datasets, existing four feature extraction methods, variable window size and various signal to noise ratios (SNR). In addition, we also propose a feature extraction method where the LMAV and NSV are grouped with the existing 11 time-domain features. The proposed feature extraction method enhances accuracy, sensitivity, specificity, precision, and F1 score by 1.00%, 5.01%, 0.55%, 4.71%, and 5.06% for dataset 1, and 1.18%, 5.90%, 0.66%, 5.63%, and 6.04% for dataset 2, respectively. Therefore, the experimental results strongly suggest the proposed feature extraction method, for taking a step forward with regard to improved myoelectric pattern recognition performance.