HFMCA: Orthonormal Feature Learning for EEG-based Brain Decoding

TL;DR

This paper introduces HFMCA, a self-supervised framework that learns orthonormal EEG features to improve brain decoding accuracy and generalization across subjects, addressing noise and high dimensionality challenges.

Contribution

The paper presents a novel hierarchical functional maximal correlation algorithm (HFMCA) for EEG feature learning, enhancing robustness and cross-subject generalization in brain decoding tasks.

Findings

HFMCA outperforms baseline methods in EEG classification accuracy.

Achieves 2.71% and 2.57% improvements on benchmark datasets.

Demonstrates superior cross-subject generalization in EEG tasks.

Abstract

Electroencephalography (EEG) analysis is critical for brain-computer interfaces and neuroscience, but the intrinsic noise and high dimensionality of EEG signals hinder effective feature learning. We propose a self-supervised framework based on the Hierarchical Functional Maximal Correlation Algorithm (HFMCA), which learns orthonormal EEG representations by enforcing feature decorrelation and reducing redundancy. This design enables robust capture of essential brain dynamics for various EEG recognition tasks. We validate HFMCA on two benchmark datasets, SEED and BCIC-2A, where pretraining with HFMCA consistently outperforms competitive self-supervised baselines, achieving notable gains in classification accuracy. Across diverse EEG tasks, our method demonstrates superior cross-subject generalization under leave-one-subject-out validation, advancing state-of-the-art by 2.71\% on SEED emotion recognition and 2.57\% on BCIC-2A motor imagery classification.