EEG-Based Emotion Recognition with Combined Fuzzy Inference via Integrating Weighted Fuzzy Rule Inference and Interpolation

Fangyi Li*, Fusheng Yu, Liang Shen*, Hexi Li, Xiaonan Yang, Qiang Shen

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

Abstract

Emotions play a significant role in shaping psychological activities, behaviour, and interpersonal communication. Reflecting this importance, automated emotion classification has become a vital research area in artificial intelligence. Electroencephalogram (EEG)-based emotion recognition is particularly promising due to its high temporal resolution and resistance to manipulation. This study introduces an advanced fuzzy inference algorithm for EEG data-driven emotion recognition, effectively addressing the ambiguity of emotional states. By combining adaptive fuzzy rule generation, feature evaluation, and weighted fuzzy rule interpolation, the proposed approach achieves accurate emotion classification while handling incomplete knowledge. Experimental results demonstrate that the integrated fuzzy system outperforms state-of-the-art techniques, offering improved recognition accuracy and robustness under uncertainty.

Original languageEnglish
Article number166
JournalMathematics
Volume13
Issue number1
DOIs
Publication statusPublished - 05 Jan 2025

Keywords

  • EEG data
  • emotion recognition
  • fuzzy inference
  • fuzzy rule interpolation
  • fuzzy systems integration

Fingerprint

Dive into the research topics of 'EEG-Based Emotion Recognition with Combined Fuzzy Inference via Integrating Weighted Fuzzy Rule Inference and Interpolation'. Together they form a unique fingerprint.

Cite this