Authors:
Olga Sourina
and
Yisi Liu
Affiliation:
Nanyang Technological University, Singapore
Keyword(s):
EEG, Fractal dimension, SVM, Emotion recognition, Music stimuli.
Related
Ontology
Subjects/Areas/Topics:
Applications and Services
;
Biomedical Engineering
;
Biomedical Signal Processing
;
Computer Vision, Visualization and Computer Graphics
;
Medical Image Detection, Acquisition, Analysis and Processing
;
Physiological Processes and Bio-Signal Modeling, Non-Linear Dynamics
Abstract:
Emotion recognition from EEG could be used in many applications as it allows us to know the “inner” emotion regardless of the human facial expression, behaviour, or verbal communication. In this paper, we proposed and described a novel fractal dimension (FD) based emotion recognition algorithm using an Arousal-Valence emotion model. FD values calculated from the EEG signal recorded from the corresponding brain lobes are mapped to the 2D emotion model. The proposed algorithm allows us to recognize emotions that could be defined by arousal and valence levels. Only 3 electrodes are needed for the emotions recognition. Higuchi and box-counting algorithms were used for the EEG analysis and comparison. Support Vector Machine classifier was applied for arousal and valence levels recognition. The proposed method is a subject dependent one. Experiments with music and sound stimuli to induce human emotions were realized. Sound clips from the International Affective Digitized Sounds (IADS) data
base were used in the experiments.
(More)