Single Channel-based Motor Imagery Classification using Fisher's Ratio and Pearson Correlation

TL;DR

This paper proposes a novel single-channel motor imagery classification framework combining Fisher's Ratio and Pearson Correlation, demonstrating its effectiveness across multiple datasets and identifying optimal channels and classes.

Contribution

It introduces an integrated framework that enhances single-channel classification by combining Fisher's Ratio and Pearson Correlation, a novel approach in MI-based BCI systems.

Findings

Effective in 2-class classification across datasets

Identifies optimal channels for individual subjects

Shows efficiency in specific classes with single-channel setup

Abstract

Motor imagery-based BCI systems have been promising and gaining popularity in rehabilitation and Activities of daily life(ADL). Despite this, the technology is still emerging and has not yet been outside the laboratory constraints. Channel reduction is one contributing avenue to make these systems part of ADL. Although Motor Imagery classification heavily depends on spatial factors, single channel-based classification remains an avenue to be explored thoroughly. Since Fisher's ratio and Pearson Correlation are powerful measures actively used in the domain, we propose an integrated framework (FRPC integrated framework) that integrates Fisher's Ratio to select the best channel and Pearson correlation to select optimal filter banks and extract spectral and temporal features respectively. The framework is tested for a 2-class motor imagery classification on 2 open-source datasets and 1 collected dataset and compared with state-of-art work. Apart from implementing the framework, this study also explores the most optimal channel among all the subjects and later explores classes where the single-channel framework is efficient.