Presentation 2010-06-15
Inference of Multiple Absorbtion Bands for Reflectance Spectra Using Exchange Monte Carlo Method
Kenji NAGATA, Seiji SUGITA, Masato OKADA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) It is essential to establish the method to deconvolute spectral data into some bands in order to analyze the chemical properties of matter. For the establishment, we have two fundamental problems. One is the determination of the number of bands without heuristics. The other is to avoid the solution of parameters to trap the local minima due to the hierarchy and the nonlinearity of the model. In this paper, we propose the new method of spectral deconvolution based on Bayesian learning with the exchange Monte Carlo method, and experimentally show its effectiveness by applying the synthetic data, and the reflectance spectral data of Olivine.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Spectroanalysis / Spectral Deconvolution / Exchange Monte Carlo Method / Bayesian Learning
Paper # IBISML2010-18
Date of Issue

Conference Information
Committee IBISML
Conference Date 2010/6/7(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 Information-Based Induction Sciences and Machine Learning (IBISML)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Inference of Multiple Absorbtion Bands for Reflectance Spectra Using Exchange Monte Carlo Method
Sub Title (in English)
Keyword(1) Spectroanalysis
Keyword(2) Spectral Deconvolution
Keyword(3) Exchange Monte Carlo Method
Keyword(4) Bayesian Learning
1st Author's Name Kenji NAGATA
1st Author's Affiliation Graduate School of Frontier Sciences, The University of Tokyo()
2nd Author's Name Seiji SUGITA
2nd Author's Affiliation Graduate School of Frontier Sciences, The University of Tokyo
3rd Author's Name Masato OKADA
3rd Author's Affiliation Graduate School of Frontier Sciences, The University of Tokyo:RIKEN Brain Science Institute
Date 2010-06-15
Paper # IBISML2010-18
Volume (vol) vol.110
Number (no) 76
Page pp.pp.-
#Pages 6
Date of Issue