Presentation	2009-07-09 Extension of Maximum Likelihood Algorithm for Fault Analysis of Large-scale Systems Toshio TONOUCHI,
PDF Download Page	PDF download Page Link
Abstract(in Japanese)	(See Japanese page)
Abstract(in English)	We proposed, in previous paper, a new root cause analysis method in which fault propagation models are calculated with maximum likelihood analysis. In this method, however, learning of fault propagation patterns and analysis with the propagation model takes time with O(N^2) where N is product of the number of components and faults. We propose, in this paper, a new maximum likelihood analysis algorithm. The algorithm assumes the probability of fault propagation among types of fault components and that of fault propagation among components are independent. In the proposed algorithm, the learning phase and the analysis phase take O(1) times.
Keyword(in Japanese)	(See Japanese page)
Keyword(in English)	Fault Analysis / Fourier Analysis / access pattern
Paper #	ICM2009-16
Date of Issue

Conference Information
Committee	ICM
Conference Date	2009/7/2(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	Information and Communication Management(ICM)
Language	JPN
Title (in Japanese)	(See Japanese page)
Sub Title (in Japanese)	(See Japanese page)
Title (in English)	Extension of Maximum Likelihood Algorithm for Fault Analysis of Large-scale Systems
Sub Title (in English)
Keyword(1)	Fault Analysis
Keyword(2)	Fourier Analysis
Keyword(3)	access pattern
1st Author's Name	Toshio TONOUCHI
1st Author's Affiliation	Service Platform Research Laboratories, NEC Corporation()
Date	2009-07-09
Paper #	ICM2009-16
Volume (vol)	vol.109
Number (no)	120
Page	pp.pp.-
#Pages	6
Date of Issue