Weight-based Channel-model Matrix Framework provides a reasonable solution for EEG-based cross-dataset emotion recognition

TL;DR

This paper introduces the Weight-based Channel-model Matrix Framework (WCMF), a novel method for EEG-based cross-dataset emotion recognition that addresses individual differences and improves stability and accuracy.

Contribution

The paper proposes WCMF, a new framework with four weight extraction methods, including the optimal correction T-test, to enhance cross-dataset EEG emotion recognition.

Findings

WCMF outperforms traditional models in stability and accuracy.

The correction T-test method is identified as the most effective weight extraction approach.

WCMF demonstrates superior performance in practical cross-dataset scenarios.

Abstract

Cross-dataset emotion recognition as an extremely challenging task in the field of EEG-based affective computing is influenced by many factors, which makes the universal models yield unsatisfactory results. Facing the situation that lacks EEG information decoding research, we first analyzed the impact of different EEG information(individual, session, emotion and trial) for emotion recognition by sample space visualization, sample aggregation phenomena quantification, and energy pattern analysis on five public datasets. Based on these phenomena and patterns, we provided the processing methods and interpretable work of various EEG differences. Through the analysis of emotional feature distribution patterns, the Individual Emotional Feature Distribution Difference(IEFDD) was found, which was also considered as the main factor of the stability for emotion recognition. After analyzing the limitations of traditional modeling approach suffering from IEFDD, the Weight-based Channel-model Matrix Framework(WCMF) was proposed. To reasonably characterize emotional feature distribution patterns, four weight extraction methods were designed, and the optimal was the correction T-test(CT) weight extraction method. Finally, the performance of WCMF was validated on cross-dataset tasks in two kinds of experiments that simulated different practical scenarios, and the results showed that WCMF had more stable and better emotion recognition ability.