KNN Learning Techniques for Proportional Myocontrol in Prosthetics

TL;DR

This paper introduces a k-nearest neighbor (kNN) classification method with a proportionality scheme for gesture recognition in electromyographic prostheses, demonstrating significant improvements over existing algorithms through extensive validation.

Contribution

It presents a novel kNN-based approach with proportionality scaling for improved gesture recognition in prosthetics, validated through practical experiments and user studies.

Findings

kNN with proportionality scheme outperforms RR-RFF in gesture exertion tasks

Significant statistical improvements over state-of-the-art algorithms

Effective parameter analysis of kNN in EMG-based gesture recognition

Abstract

This work has been conducted in the context of pattern-recognition-based control for electromyographic prostheses. It presents a k-nearest neighbour (kNN) classification technique for gesture recognition, extended by a proportionality scheme. The methods proposed are practically implemented and validated. Datasets are captured by means of a state-of-the-art 8-channel electromyography (EMG) armband positioned on the forearm. Based on this data, the influence of kNN's parameters is analyzed in pilot experiments. Moreover, the effect of proportionality scaling and rest thresholding schemes is investigated. A randomized, double-blind user study is conducted to compare the implemented method with the state-of-research algorithm Ridge Regression with Random Fourier Features (RR-RFF) for different levels of gesture exertion. The results from these experiments show a statistically significant improvement in favour of the kNN-based algorithm.