Presentation 2007-06-14
The EEG Analysis by Using a Neural Network in Listening to Music
Takahiro OGAWA, Stephen KARUNGARU, Yasue MITSUKURA, Minoru FUKUMI, Norio AKAMATSU,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Recent, stress causes venous illnesses. In order to solve such a problem, researchers have studied about the music therapy. Music used in the music therapy is of verious types, therefore it takes a patient and therapist long time to select the music. If the music is easily selectable, the music therapy can be carried out effectively. In this paper, we discuss an influence by the music for humans. First we measure the EEG(electroencephalogram) while listening to the music. Next, we create a data matrix based on appearance rate of frequency ingredients. Thirdly, we extract features from the data matrix by the PCA(principal component analysis) and the KPCA(kernel principal component analysis). Finally, we verify the EEG patterns based on the feature vectors by the NN(neural network). We compare accuracy of the PCA and the KPCA by recognition rate of a neural network. In order to examine whether the proposal system is effective, we try computer simulations for the EEG classification. From the results of computer simulations, it is suggested that feature extraction by using the KPCA,is effective compared to the PCA.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) electroencephalogram / principal component analysis / canonical discriminant analysis / neural network
Paper # NC2007-9
Date of Issue

Conference Information
Committee NC
Conference Date 2007/6/7(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 Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) The EEG Analysis by Using a Neural Network in Listening to Music
Sub Title (in English)
Keyword(1) electroencephalogram
Keyword(2) principal component analysis
Keyword(3) canonical discriminant analysis
Keyword(4) neural network
1st Author's Name Takahiro OGAWA
1st Author's Affiliation University of Tokushima()
2nd Author's Name Stephen KARUNGARU
2nd Author's Affiliation University of Tokushima
3rd Author's Name Yasue MITSUKURA
3rd Author's Affiliation Tokyo University of Agriculture and Technology
4th Author's Name Minoru FUKUMI
4th Author's Affiliation University of Tokushima
5th Author's Name Norio AKAMATSU
5th Author's Affiliation University of Tokushima
Date 2007-06-14
Paper # NC2007-9
Volume (vol) vol.107
Number (no) 92
Page pp.pp.-
#Pages 5
Date of Issue