Presentation 2021-03-19
A Proposal for Improving the Accuracy of Anomaly Detection by Focusing on Response Time in Web Services
Tatsuo Kumano, Naoyoshi Ohkawa, Hiroshi Fujita, Takuya Yoshikawa, Hitoshi Ueno,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In web services, usability decreases and user satisfaction declines when the response time is longer than usual. Operators need to detect and respond to this situation, because these situations will lead to a loss of customers. To detect an increase in response time, anomaly detection is often used, which automatically recognizes the normal response time using statistical methods. In this presentation, we propose a method of clustering URLs by response time and detecting anomalies for each cluster and evaluate it with the access logs of a commercial environment. As a result, we confirmed that the accuracy of anomaly detection is higher than that of statistical processing for each URL.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) web services / anomaly detection / clustering
Paper # ICM2020-70
Date of Issue 2021-03-11 (ICM)

Conference Information
Committee ICM
Conference Date 2021/3/18(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Online
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Kazuhiko Kinoshita(Tokushima Univ.)
Vice Chair Yoichi Sato(OSL) / Haruo Ooishi(NTT)
Secretary Yoichi Sato(NTT) / Haruo Ooishi(Bosco)
Assistant Tetsuya Uchiumi(Fujitsu Lab.)

Paper Information
Registration To Technical Committee on Information and Communication Management
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Proposal for Improving the Accuracy of Anomaly Detection by Focusing on Response Time in Web Services
Sub Title (in English)
Keyword(1) web services
Keyword(2) anomaly detection
Keyword(3) clustering
Keyword(4)
1st Author's Name Tatsuo Kumano
1st Author's Affiliation Fujitsu Laboratories Ltd.(Fujitsu Labs)
2nd Author's Name Naoyoshi Ohkawa
2nd Author's Affiliation Fujitsu Laboratories Ltd.(Fujitsu Labs)
3rd Author's Name Hiroshi Fujita
3rd Author's Affiliation Fujitsu Laboratories Ltd.(Fujitsu Labs)
4th Author's Name Takuya Yoshikawa
4th Author's Affiliation Cybozu, Inc.(Cybozu)
5th Author's Name Hitoshi Ueno
5th Author's Affiliation Fujitsu Laboratories Ltd.(Fujitsu Labs)
Date 2021-03-19
Paper # ICM2020-70
Volume (vol) vol.120
Number (no) ICM-433
Page pp.pp.58-63(ICM),
#Pages 6
Date of Issue 2021-03-11 (ICM)