Target-centered Subject Transfer Framework for EEG Data Augmentation

TL;DR

This paper introduces a target-centered subject transfer framework for EEG data augmentation that enhances data relevance and realism, improving brain-computer interface performance without adding noise.

Contribution

The proposed framework constructs a relevant source data subset and uses generative models to transfer data to the target domain, avoiding noise addition and improving explainability.

Findings

Outperforms existing data augmentation methods in EEG decoding tasks.

Enhances the explainability of target domain data.

Proves effective and robust across extensive experiments.

Abstract

Data augmentation approaches are widely explored for the enhancement of decoding electroencephalogram signals. In subject-independent brain-computer interface system, domain adaption and generalization are utilized to shift source subjects' data distribution to match the target subject as an augmentation. However, previous works either introduce noises (e.g., by noise addition or generation with random noises) or modify target data, thus, cannot well depict the target data distribution and hinder further analysis. In this paper, we propose a target-centered subject transfer framework as a data augmentation approach. A subset of source data is first constructed to maximize the source-target relevance. Then, the generative model is applied to transfer the data to target domain. The proposed framework enriches the explainability of target domain by adding extra real data, instead of noises. It shows superior performance compared with other data augmentation methods. Extensive experiments are conducted to verify the effectiveness and robustness of our approach as a prosperous tool for further research.