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

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.