Impact of dataset size and long-term ECoG-based BCI usage on deep learning decoders performance

Classifying mental motor tasks from chronic ECoG-BCI recordings using phase-amplitude coupling features

Introduction

Phase-amplitude coupling (PAC), the modulation of high-frequency neural oscillations by the phase of slower oscillations, is increasingly recognized as a marker of goal-directed motor behavior. Despite this interest, its specific role and potential value in decoding attempted motor movements remain unclear.

Methods

This study investigates whether PAC-derived features can be leveraged to classify different motor behaviors from ECoG signals within Brain-Computer Interface (BCI) systems. ECoG data were collected using the WIMAGINE implant during BCI experiments with a tetraplegic patient performing mental motor tasks. The data underwent preprocessing to extract complex neural oscillation features (amplitude, phase) through spectral decomposition techniques. These features were then used to quantify PAC by calculating different coupling indices. PAC metrics served as input features in a machine learning pipeline to evaluate their effectiveness in predicting mental tasks (idle state, right-hand movement, left-hand movement) in both offline and pseudo-online modes.

Results

The PAC features demonstrated high accuracy in distinguishing among motor tasks, with key classification features highlighting the coupling of theta/low-gamma and beta/high-gamma frequency bands.

Discussion

These preliminary findings hold significant potential for advancing our understanding of motor behavior and for developing optimized BCI systems.

EEG Amplitude Modulation Analysis across Mental Tasks: Towards Improved Active BCIs

Brain-computer interface (BCI) technology has emerged as an influential communication tool with extensive applications across numerous fields, including entertainment, marketing, mental state monitoring, and particularly medical neurorehabilitation. Despite its immense potential, the reliability of BCI systems is challenged by the intricacies of data collection, environmental factors, and noisy interferences, making the interpretation of high-dimensional electroencephalogram (EEG) data a pressing issue. While the current trends in research have leant towards improving classification using deep learning-based models, our study proposes the use of new features based on EEG amplitude modulation (AM) dynamics. Experiments on an active BCI dataset comprised seven mental tasks to show the importance of the proposed features, as well as their complementarity to conventional power spectral features. Through combining the seven mental tasks, 21 binary classification tests were explored. In 17 of these 21 tests, the addition of the proposed features significantly improved classifier performance relative to using power spectral density (PSD) features only. Specifically, the average kappa score for these classifications increased from 0.57 to 0.62 using the combined feature set. An examination of the top-selected features showed the predominance of the AM-based measures, comprising over 77% of the top-ranked features. We conclude this paper with an in-depth analysis of these top-ranked features and discuss their potential for use in neurophysiology.