Presentation 1999/1/21
Estimation and Integration of Sensory Inputs using a Bayesian Method.
Satoshi SUGIURA, Hiromi TAKEUCHI, Koichiro YAMAUCHI, Naohiro ISHII,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we show the mathematical interpretation of our previous system that we have proposed before, and introduce a new resognition algorithm according to the new interpretation. This system consists of several parts in order to recognize objects correctly by using several sensors. "Forward Network" receives inputs from corresponding sensor. "Integrating Unit" integrates the outputs of all Forward Networks. And "Backward Network" receives inputs from Integrating Unit and reconstructs the sensory informations as its outputs. In the recognition phase, the system get a correct output by modifying the inputs of Forward Networks, the output of Integrating Unit and the confidence of the sensory informations repeatedly to maximize a likelihood function, which can be derived by a Bayesian method. In the computer simulation, we confirm the recognition capability of the system.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Neural Network / Sensory Fusion / Bayesian Estimation
Paper # NC98-70
Date of Issue

Conference Information
Committee NC
Conference Date 1999/1/21(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) Estimation and Integration of Sensory Inputs using a Bayesian Method.
Sub Title (in English)
Keyword(1) Neural Network
Keyword(2) Sensory Fusion
Keyword(3) Bayesian Estimation
1st Author's Name Satoshi SUGIURA
1st Author's Affiliation Department of Intelligence and Computer Science, Nagoya Institute of Technology()
2nd Author's Name Hiromi TAKEUCHI
2nd Author's Affiliation Department of Intelligence and Computer Science, Nagoya Institute of Technology
3rd Author's Name Koichiro YAMAUCHI
3rd Author's Affiliation Department of Intelligence and Computer Science, Nagoya Institute of Technology
4th Author's Name Naohiro ISHII
4th Author's Affiliation Department of Intelligence and Computer Science, Nagoya Institute of Technology
Date 1999/1/21
Paper # NC98-70
Volume (vol) vol.98
Number (no) 526
Page pp.pp.-
#Pages 8
Date of Issue