Mental State Classification Using Multi-graph Features

TL;DR

This paper introduces a novel multi-graph feature extraction method from EEG data to classify mental states, demonstrating its effectiveness and neuroscientific validity compared to traditional features.

Contribution

The paper presents a new multi-graph based feature extraction approach for EEG data, enhancing mental state classification with neuroscientifically valid insights.

Findings

Multi-graph features improve classification accuracy.

Features provide complementary information to traditional band power features.

Identified key channels relevant to mental state classification.

Abstract

We consider the problem of extracting features from passive, multi-channel electroencephalogram (EEG) devices for downstream inference tasks related to high-level mental states such as stress and cognitive load. Our proposed method leverages recently developed multi-graph tools and applies them to the time series of graphs implied by the statistical dependence structure (e.g., correlation) amongst the multiple sensors. We compare the effectiveness of the proposed features to traditional band power-based features in the context of three classification experiments and find that the two feature sets offer complementary predictive information. We conclude by showing that the importance of particular channels and pairs of channels for classification when using the proposed features is neuroscientifically valid.