Emotion Recognition from Physiological Signals Using Ensembled Machine Learning Strategy

The field of emotion recognition by physiological signal analysis is the subject of the proposed study. Its primary objective is to evaluate how effectively various classifiers predict two important emotional variables: valence and arousal. Three distinct classifiers are used in the study: kELM (Kernel Extreme Learning Machine), nELM (Neural Extreme Learning Machine), and sSOM (Simplified Self-Organising Map) in order to give a comprehensive comparison analysis. The script contributes to the advancement of emotion perception by carefully contrasting the capabilities of multiple classifiers. By using the dataset, the research hopes to clarify the benefits and drawbacks of each classifier and contribute to the development of more dependable and precise emotion identification algorithms. The suggested study focuses on the area of physiological signal processing for emotion identification. Its main goal is to assess how well different classifiers perform in predicting valence and arousal, two crucial emotional variables.