Rule-Based classification for a case-based system

Riitta Penttinen, Pekka Ala-Siuru, Johan Plomp, Jari Vormisto

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

Abstract

We introduce an architecture for combining rule-based and case-based reasoning in the field of telecommunication network alarm handling. With this approach it is possible to handle alarms from different generations of network equipment or from equipment of different vendors. The architecture consists of: 1) Rule-Based reasoning (RBR) for the pre-processing of alarms and messages, 2) Case-Based reasoning (CBR) to find previous failure cases among the pre-processed alarms and messages and 3) fault diagnosis which is based on these two earlier parts. The alarms and messages are classified into basic classes during the pre-processing phase, in order to avoid dependency on equipment generations and vendors. The CBR part finds new failure cases among incoming alarms and messages based on certain rules.
Original languageEnglish
Title of host publicationSTeP 2000 - millennium of artificial intelligence: 'AI of today'
Subtitle of host publicationSymposium on applications
EditorsHeikki Hyötyniemi
PublisherFinnish Artificial Intelligence Society FAIS
Pages103-111
Volume2
ISBN (Print)951-22-5128-0
Publication statusPublished - 2000
MoE publication typeA4 Article in a conference publication
Event9th Finnish Artificial Intelligence Conference : Millennium of Artificial Intelligence - Espoo, Finland
Duration: 28 Aug 200030 Aug 2000
Conference number: 9

Publication series

SeriesPublications of Finnish Society of Information Processing Science
Volume16
ISSN0782-0089

Conference

Conference9th Finnish Artificial Intelligence Conference
Abbreviated titleSTeP 2000
CountryFinland
CityEspoo
Period28/08/0030/08/00

Fingerprint Dive into the research topics of 'Rule-Based classification for a case-based system'. Together they form a unique fingerprint.

Cite this