Learning-based adaptation determination method for problem recognition of self-adaptive software

Kwangsoo Seol, Doo Kwon Baik

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper, we propose a method for identifying the adaptation period when a problem occurs in a system in order to reduce the unnecessary adaptation of self-adaptive software. Consequently, the dangerous situation information is defined, the behavior information at the time of problem occurrence is learned, and the adaptive performance is determined by comparing it with the existing similar situations by using the k-nearest neighbors algorithm. By the use of the proposed method, a situation where an unnecessary adaptation process is performed while running the self-adaptive system could be avoided, system load may be reduced, and service quality may be enhanced.

Original languageEnglish
Title of host publicationProceedings of the 2015 International Conference on Artificial Intelligence, ICAI 2015 - WORLDCOMP 2015
EditorsDavid de la Fuente, Roger Dziegiel, Elena B. Kozerenko, Peter M. LaMonica, Raymond A. Liuzzi, Jose A. Olivas, Todd Waskiewicz, George Jandieri, Hamid R. Arabnia
PublisherCSREA Press
Pages399-400
Number of pages2
ISBN (Electronic)1601324073, 9781601324078
Publication statusPublished - 2019
Event2015 International Conference on Artificial Intelligence, ICAI 2015 - WORLDCOMP 2015 - Las Vegas, United States
Duration: 2015 Jul 272015 Jul 30

Publication series

NameProceedings of the 2015 International Conference on Artificial Intelligence, ICAI 2015 - WORLDCOMP 2015

Conference

Conference2015 International Conference on Artificial Intelligence, ICAI 2015 - WORLDCOMP 2015
Country/TerritoryUnited States
CityLas Vegas
Period15/7/2715/7/30

Keywords

  • Machine learning
  • Problem recognition
  • Self-adaptive software

ASJC Scopus subject areas

  • Artificial Intelligence
  • Software

Fingerprint

Dive into the research topics of 'Learning-based adaptation determination method for problem recognition of self-adaptive software'. Together they form a unique fingerprint.

Cite this