Presentation 2000/10/12
Statistical analysis methods for Magnetoencephalography data
Yoichiro Matsuno, Shigeyuki Ohba, Shin Ishii,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) MEG(Magnetoencephalography)is a non-aggressive method to measure brain activities. Because brain activities are likely to be extremely weak, noise removal is necessary. The decomposition of the measured magnetic field signals into signals evoked by brain activities, the terrestrial magnetism, the noise from the power supply, the device noise, and so on, can be done by the independent component analysis(ICA). Although MEG data often become high dimensional, there is a difficulty for ICA to deal with the high dimensional data. This report discusses dimension reduction methods as preprocesses of ICA. They are based on the probabilistic principal component analysis. As for the dimension reduction, we use the minimum description length(MDL)standard and the VBPCA(variational Bayes principal component analysis)method. These two methods are experimentally compared.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Independent component analysis / Principal component analysis / Magnetoencephalography / Variational Bayes method / Dimension reduction
Paper # PRMU2000-94,NC2000-59
Date of Issue

Conference Information
Committee PRMU
Conference Date 2000/10/12(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 Pattern Recognition and Media Understanding (PRMU)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Statistical analysis methods for Magnetoencephalography data
Sub Title (in English)
Keyword(1) Independent component analysis
Keyword(2) Principal component analysis
Keyword(3) Magnetoencephalography
Keyword(4) Variational Bayes method
Keyword(5) Dimension reduction
1st Author's Name Yoichiro Matsuno
1st Author's Affiliation Nara Institute of Science and Technology()
2nd Author's Name Shigeyuki Ohba
2nd Author's Affiliation Nara Institute of Science and Technology
3rd Author's Name Shin Ishii
3rd Author's Affiliation Nara Institute of Science and Technology:CREST, Japan Science and Technology Corporation
Date 2000/10/12
Paper # PRMU2000-94,NC2000-59
Volume (vol) vol.100
Number (no) 359
Page pp.pp.-
#Pages 8
Date of Issue