aalto1 untyped-item.component.html

Emotion recognition based on physiological signal

Loading...
Thumbnail Image

URL

Journal Title

Journal ISSN

Volume Title

Sähkötekniikan korkeakoulu | Master's thesis

Department

Mcode

ELEC3029

Language

en

Pages

59+4

Series

Abstract

This research focuses on emotion recognition based on physiological signals, specifically electroencephalogram (EEG) signals and heart rate data. Utilizing virtual reality (VR) technology to evoke genuine emotional responses, the study collected data from 14 subjects across different countries. The primary objective was to evaluate emotion classification algorithms, analyzing their accuracy in various scenarios. Employing machine learning and deep learning, including support vector machines (SVM) and deep learning models, the results demonstrated significant accuracy, reaching up to 88% in single dimensions (arousal or valence) and 84% in dual dimensions (arousal and valence together as labels). Multi-feature combinations, especially in deep learning models, enhanced sentiment classification. Identified areas for improvement include the quality of VR stimuli, additional physiological signals, and refined experimental procedures. Future research will explore algorithm stacking and integration methods to further enhance emotion recognition accuracy.

Description

Supervisor

Xiao, Yu

Thesis advisor

Xiao, Yu

Other note

Citation

Endorsement

Review

Supplemented By

Referenced By