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

by   Huayu Chen, et al.

Cross-dataset emotion recognition as an extremely challenging task in the field of EEG-based affective computing is influenced by many factors, which make the universal models yield unsatisfactory results. Facing the situation that lack of EEG information decoding researches, we first analyzed the impact of different EEG information(individual, session, emotion, trial) to emotion recognition by sample space visualization, sample aggregation phenomenon quantification, and energy pattern analysis on five public datasets. And 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, Individual Emotional Feature Distribution Difference(IEFDD) was found. After analyzing the limitations of traditional modeling approach suffering from IEFDD, we proposed the Weight-based Channel-model Matrix Framework(WCMF). In order to characterize emotional feature distribution patterns reasonably, four weight extraction methods were designed, and the optimal of them is 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, the results showed WCMF had more stable and better emotion recognition ability.


page 1

page 5

page 6

page 10

page 13


Locally temporal-spatial pattern learning with graph attention mechanism for EEG-based emotion recognition

Technique of emotion recognition enables computers to classify human aff...

Identifying Stable Patterns over Time for Emotion Recognition from EEG

In this paper, we investigate stable patterns of electroencephalogram (E...

Multiscale Fractal Analysis of Stimulated EEG Signals with Application to Emotion Classification

Emotion Recognition from EEG signals has long been researched as it can ...

Unsupervised Time-Aware Sampling Network with Deep Reinforcement Learning for EEG-Based Emotion Recognition

Recognizing human emotions from complex, multivariate, and non-stationar...

A new model for the implementation of positive and negative emotion recognition

The large range of potential applications, not only for patients but als...

Structure-Preserving Graph Kernel for Brain Network Classification

This paper presents a novel graph-based kernel learning approach for con...

Please sign up or login with your details

Forgot password? Click here to reset