Probabilistic modeling of alarm observation delay in network diagnosis

Authors:
Kazuo Hashimoto;Kazunori Matsumoto;Norio Shiratori
Affiliations:
KDD R&D Laboratories Inc., Oliara, Kamifukuoka-Shi, Saitama;KDD R&D Laboratories Inc., Oliara, Kamifukuoka-Shi, Saitama;Tohoku University, Katahira, Aobaku-ku, Sendai, Japan
Venue:
PRICAI'00 Proceedings of the 6th Pacific Rim international conference on Artificial intelligence
Year:
2000

Citing 7
Cited 0

An assumption-based TMS

Artificial Intelligence
A theory of diagnosis from first principles

Artificial Intelligence
Diagnosing multiple faults

Artificial Intelligence
Using crude probability estimates to guide diagnosis

Artificial Intelligence
A tutorial on learning with Bayesian networks

Learning in graphical models
An Expert System for Real Time Fault Diagnosis of the Italian Telecommunications Network

Proceedings of the IFIP TC6/WG6.6 Third International Symposium on Integrated Network Management with participation of the IEEE Communications Society CNOM and with support from the Institute for Educational Services
High speed and robust event correlation

IEEE Communications Magazine

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper introduces a probabilistic modeling of alarm observation delay, and shows a novel method of model-based diagnosis for time series observation. Firstly, a fault model is defined by associating an event tree rooted by each fault hypothesis with probabilistic variables representing temporal delay. The most probable hypothesis is obtained by selecting one whose AIC (Akaike information criterion) is minimal. It is proved that by simulation that the AIC based hypothesis selection achieves the high precision in diagnosis.