Presentation 1999/5/27
Deterioration Detection with Local Stationary Models for Telecommunication Network
Kazunori MATSUMOTO, Kazuo HASHIMOTO, Keiko AOKI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we deal with the degradation detection problem. for telecommunication network gateways. The time series to be monitored is non-stationary but almost periodic (pseudo-periodic). The authors propose a technique called "optimization of partition model" which generates local stationary models for a pseudo-periodic time series. The optimization is based on the minimal AIC principle. The technique called SPRT is also applied to make efficient decisions. By experiments using real traffic data, the proposed method of optimization and that of incremental update are evaluated in comparison with the conventional method. The result shows the proposed method is effective and makes more precises decision than the conventional one.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Deterioration Detection / Sequential Probability Ratio Test (SPRT) / Akaike's Information Criterion (AIC) / Local Stationary
Paper # AI99-1
Date of Issue

Conference Information
Committee AI
Conference Date 1999/5/27(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) Deterioration Detection with Local Stationary Models for Telecommunication Network
Sub Title (in English)
Keyword(1) Deterioration Detection
Keyword(2) Sequential Probability Ratio Test (SPRT)
Keyword(3) Akaike's Information Criterion (AIC)
Keyword(4) Local Stationary
1st Author's Name Kazunori MATSUMOTO
1st Author's Affiliation KDD Research and Development Laboratories Inc.()
2nd Author's Name Kazuo HASHIMOTO
2nd Author's Affiliation KDD Research and Development Laboratories Inc.
3rd Author's Name Keiko AOKI
3rd Author's Affiliation KDD Research and Development Laboratories Inc.
Date 1999/5/27
Paper # AI99-1
Volume (vol) vol.99
Number (no) 95
Page pp.pp.-
#Pages 8
Date of Issue