Activity Coefficient-based Channel Selection for Electroencephalogram: A Task-Independent Approach

TL;DR

This paper introduces a task-independent EEG channel selection method called ACCS, which uses a novel metric to improve classification accuracy and is adaptable across various applications without re-optimization.

Contribution

The paper presents a new task-agnostic channel selection technique using the Channel Activity Coefficient, enabling reusable and adaptable EEG channel subsets for diverse tasks.

Findings

Up to 34.97% improvement in classification accuracy.

Selected channels are reusable across different tasks.

Method reduces need for re-optimization in new applications.

Abstract

Electroencephalogram (EEG) signals have gained widespread adoption in brain-computer interface (BCI) applications due to their non-invasive, low-cost, and relatively simple acquisition process. The demand for higher spatial resolution, particularly in clinical settings, has led to the development of high-density electrode arrays. However, increasing the number of channels introduces challenges such as cross-channel interference and computational overhead. To address these issues, modern BCI systems often employ channel selection algorithms. Existing methods, however, are typically task-specific and require re-optimization for each new application. This work proposes a task-agnostic channel selection method, Activity Coefficient-based Channel Selection (ACCS), which uses a novel metric called the Channel Activity Coefficient (CAC) to quantify channel utility based on activity levels. By selecting the top 16 channels ranked by CAC, ACCS achieves up to 34.97% improvement in multi-class classification accuracy. Unlike traditional approaches, ACCS identifies a reusable set of informative channels independent of the downstream task or model, making it highly adaptable for diverse EEG-based applications.