From Electrode to Global Brain: Integrating Multi- and Cross-Scale Brain Connections and Interactions Under Cross-Subject and Within-Subject Scenarios

TL;DR

This paper introduces a novel multi-scale spatial domain adaptation network to address individual variability in EEG-based motor imagery classification, leveraging multi-scale brain structures for improved cross-subject and intra-subject performance.

Contribution

It proposes a new multi-scale spatial domain adaptation network (MSSDAN) combining feature extraction and domain adaptation for EEG MI classification.

Findings

Improved classification accuracy across subjects.

Effective handling of multi-scale spatial data differences.

First to address multi-scale spatial distribution in STS MI tasks.

Abstract

The individual variabilities of electroencephalogram signals pose great challenges to cross-subject motor imagery (MI) classification, especially for the data-scarce single-source to single-target (STS) scenario. The multi-scale spatial data distribution differences can not be fully eliminated in MI experiments for the topological structure and connection are the inherent properties of the human brain. Overall, no literature investigates the multi-scale spatial data distribution problem in STS cross-subject MI classification task, neither intra-subject nor inter-subject scenarios. In this paper, a novel multi-scale spatial domain adaptation network (MSSDAN) consists of both multi-scale spatial feature extractor (MSSFE) and deep domain adaptation method called multi-scale spatial domain adaptation (MSSDA) is proposed and verified, our goal is to integrate the principles of multi-scale brain topological structures in order to solve the multi-scale spatial data distribution difference problem.