EEG Based Emotion Detection by Using Modified Tunicate Swarm Optimization Algorithm

In recent years, the rapid development of computer applications for automatic classification of human emotions-based Electroencephalography (EEG) has significant attention from researchers.However, existing techniques have not adequately addressed the contextinformation inherent in EEG signals.To address the issue, this research utilized an automated model for enhancing EEG-based emotion recognition.The Modified Tunicate Swarm Optimization Algorithm (MTSOA) improves EEG-based emotion recognition by enhancing context information management.It improves signal processing, resulting in more accurate emotional state detection.This overcomes fundamental difficulties and improves the algorithm efficacy in extracting relevant emotional data from EEG signals for more robust emotion detection systems.MTSOA is used for feature selection in emotion detection because of its capacity to navigate complex search spaces effectively.Because of its capacity to effectively explore parameter spaces, the Rat Swarm Optimization Algorithm (RSOA) is used in emotion recognition to choose hyperparameters.According to the results the suggested method better outcomes for arousal of 89.58%, and valence of 92.29% which was significantly higher than the ensemble median empirical mode decomposition (MEEMD), CNN with SVM, and Kernel matrix+DNN methods.