Presentation 1996/2/2
Initial Conditions Determination for Estimation of Multiple Sources
Hisashi KANDA, Yoshikazu MIYANAGA, Koji TOCHINAI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This report considers initial conditions determination and the relation between accuracy of estimation and SNR on the maximum likelihood estimation of multiple sources. The maximum likelihood estimation is noted for high resolution and high accuracy of estimation. But this method can not lead to the global minimum because of fall into local minimum. This report proposed the effective determination for initial conditions and some experiments were performed in the simulation. In the former case, the angle of two signal sources is more than 4 deg, Although the result of new determination of initial conditions indicates that it is high accuracy of estimation.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Maximum likelihood estimation / Non-linear optimizing problem / Source localization / Initial conditions problem
Paper # NC95-98
Date of Issue

Conference Information
Committee NC
Conference Date 1996/2/2(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) Initial Conditions Determination for Estimation of Multiple Sources
Sub Title (in English)
Keyword(1) Maximum likelihood estimation
Keyword(2) Non-linear optimizing problem
Keyword(3) Source localization
Keyword(4) Initial conditions problem
1st Author's Name Hisashi KANDA
1st Author's Affiliation Faculty of Engineering, Hokkaido University()
2nd Author's Name Yoshikazu MIYANAGA
2nd Author's Affiliation Faculty of Engineering, Hokkaido University
3rd Author's Name Koji TOCHINAI
3rd Author's Affiliation Faculty of Engineering, Hokkaido University
Date 1996/2/2
Paper # NC95-98
Volume (vol) vol.95
Number (no) 505
Page pp.pp.-
#Pages 7
Date of Issue