Presentation 2004/12/10
An Emotion Spectrum Analysis Method of EEG Signals
Hajime KITAHARA, Masahiro NAKAGAWA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The state of mind of human being is closely related to the brain functional activities. Hence the features of the state of mind are considered to appear in the complexity of EEG potential dynamics. In practice, on the basis of the spatio-temporal dynamics of EEG, Musha proposed the emotion spectrum analysis method, ESAM , for abbreviation. In his approach, EEG features were extracted from the cross-correlation coefficients of EEGs measured through ten EEG electrodes in the θ, α, and β frequency bands so as to extract the fundamental emotions such as anger, joy, sadness, and relaxation. In this paper, prior to EEG analyses by means of the Emotion Spectrum Analysis Method, we perform Independent Component Analysis for EEG signals. In addition we shall evaluate the relationship between the input vector characteristics and emotion output in terms of an emotion matrix. We shall examine the relations between the measured location and the resultant emotions. As results, the improvement in the recognition accuracy up to 23[%] -51[%] is found be carried out by means of the Independent Component Analysis. When subjects imagine four fundamental emotions, one may find the relation between the measured location on the basis of F_4, T_3, and O_1 and the emotions through the constructed emotion matrix.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Emotion / EEG / Emotional information Analysis / Independent Component Analysis / Emotion Spectrum Analysis Method
Paper # HIP2004-80
Date of Issue

Conference Information
Committee HIP
Conference Date 2004/12/10(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Human Information Processing (HIP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) An Emotion Spectrum Analysis Method of EEG Signals
Sub Title (in English)
Keyword(1) Emotion
Keyword(2) EEG
Keyword(3) Emotional information Analysis
Keyword(4) Independent Component Analysis
Keyword(5) Emotion Spectrum Analysis Method
1st Author's Name Hajime KITAHARA
1st Author's Affiliation Faculty of Engineering, Nagaoka University of Technology()
2nd Author's Name Masahiro NAKAGAWA
2nd Author's Affiliation Faculty of Engineering, Nagaoka University of Technology
Date 2004/12/10
Paper # HIP2004-80
Volume (vol) vol.104
Number (no) 526
Page pp.pp.-
#Pages 6
Date of Issue