Human emotion induction, recognition and visualization

• Main Author: Ji, Xuan
• Other Authors: Olga Sourina
• Format: Final Year Project
• Language: English
• Published: 2011
• Subjects: DRNTU::Engineering::Electrical and electronic engineering::Computer hardware, software and systems; DRNTU::Engineering::Electrical and electronic engineering::Electronic systems::Signal processing
• Online Access: http://hdl.handle.net/10356/45380
• Institution: Nanyang Technological University

In recent years, many researchers have focused on using EEG signals in emotion recognition. This project aims to discover methods to distinguish and recognize emotions represented in a 3D pleasure- arousal-dominance model. A sound and music evoked emotion experiment is designed and used for signal data collection. Emotiv headset is used as the device and Self Assessment Manikin is used as the emotion assessment tool, along with sound stimuli from IADS database. Two hypotheses are proposed regarding the relationship between EEG signals and the dominance dimension of emotion: emotion lateralization in the frontal lobe; beta/alpha signal ratio increase at the frontal lobe and beta value increase at the parietal lobe. Two fractal dimension algorithms: Box Counting algorithms and Higuchi algorithm are used in data processing along with other methods to test out the hypotheses.