English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Cross-dataset emotion recognition as an extremely challenging task in thefield of EEG-based affective computing is influenced by many factors, whichmakes the universal models yield unsatisfactory results. Facing the situationthat lacks EEG information decoding research, we first analyzed the impact ofdifferent EEG information(individual, session, emotion and trial) for emotionrecognition by sample space visualization, sample aggregation phenomenaquantification, and energy pattern analysis on five public datasets. Based onthese phenomena and patterns, we provided the processing methods andinterpretable work of various EEG differences. Through the analysis ofemotional feature distribution patterns, the Individual Emotional FeatureDistribution Difference(IEFDD) was found, which was also considered as the mainfactor of the stability for emotion recognition. After analyzing thelimitations of traditional modeling approach suffering from IEFDD, theWeight-based Channel-model Matrix Framework(WCMF) was proposed. To reasonablycharacterize emotional feature distribution patterns, four weight extractionmethods were designed, and the optimal was the correction T-test(CT) weightextraction method. Finally, the performance of WCMF was validated oncross-dataset tasks in two kinds of experiments that simulated differentpractical scenarios, and the results showed that WCMF had more stable andbetter emotion recognition ability.

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