Presentation	1998/9/24 A Fault Diagnosis based on Alarm Propagation Model Kazuo HASHIMOTO, Kazunori MATSUMOTO,
PDF Download Page	PDF download Page Link
Abstract(in Japanese)	(See Japanese page)
Abstract(in English)	Exsisting diagnosis methods have not succeed in developping a fault-model of alarm propagation, because of the unstable alarm arrivals. This paper presents a new model-based diagnosis of network faults. First, a precise fault-model of alarm propagation is developped by introducing time delay of alarm propagation/detection. Second, a method of identifying the most probable fault hyhothesis is proposed. The method calculates the log-likelihood of each fault hyhothesis, and identifies the fault whose Akaike information criterion is the minimum. Finally, the decision time of the proposed and conventional methods is compared using simulation.
Keyword(in Japanese)	(See Japanese page)
Keyword(in English)	Model Based Diagnosis / Alarm Correlation / Akaike Information Criterion
Paper #	AI98-35
Date of Issue

Conference Information
Committee	AI
Conference Date	1998/9/24(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	Artificial Intelligence and Knowledge-Based Processing (AI)
Language	JPN
Title (in Japanese)	(See Japanese page)
Sub Title (in Japanese)	(See Japanese page)
Title (in English)	A Fault Diagnosis based on Alarm Propagation Model
Sub Title (in English)
Keyword(1)	Model Based Diagnosis
Keyword(2)	Alarm Correlation
Keyword(3)	Akaike Information Criterion
1st Author's Name	Kazuo HASHIMOTO
1st Author's Affiliation	KDD R&D Laboratories, INC.()
2nd Author's Name	Kazunori MATSUMOTO
2nd Author's Affiliation	KDD R&D Laboratories, INC.
Date	1998/9/24
Paper #	AI98-35
Volume (vol)	vol.98
Number (no)	296
Page	pp.pp.-
#Pages	8
Date of Issue