Cross-Subject Domain Adaptation for Classifying Working Memory Load with Multi-Frame EEG Images

TL;DR

This paper introduces a deep domain adaptation model with spatial attention for classifying working memory load from EEG data across different subjects, improving generalization and accuracy.

Contribution

The study proposes a novel cross-subject deep adaptation model that transforms EEG data into multi-frame images and employs spatial attention to enhance workload classification.

Findings

Outperforms existing methods on a public EEG dataset.

Effective domain adaptation across subjects.

Utilizes multi-frame EEG images for richer feature extraction.

Abstract

Working memory (WM), denoting the information temporally stored in the mind, is a fundamental research topic in the field of human cognition. Electroencephalograph (EEG), which can monitor the electrical activity of the brain, has been widely used in measuring the level of WM. However, one of the critical challenges is that individual differences may cause ineffective results, especially when the established model meets an unfamiliar subject. In this work, we propose a cross-subject deep adaptation model with spatial attention (CS-DASA) to generalize the workload classifications across subjects. First, we transform EEG time series into multi-frame EEG images incorporating spatial, spectral, and temporal information. First, the Subject-Shared module in CS-DASA receives multi-frame EEG image data from both source and target subjects and learns the common feature representations. Then, in the subject-specific module, the maximum mean discrepancy is implemented to measure the domain distribution divergence in a reproducing kernel Hilbert space, which can add an effective penalty loss for domain adaptation. Additionally, the subject-to-subject spatial attention mechanism is employed to focus on the discriminative spatial features from the target image data. Experiments conducted on a public WM EEG dataset containing 13 subjects show that the proposed model is capable of achieving better performance than existing state-of-the-art methods.