Title

Sporadic Fuzzy Temporal Associations

Document Type

Article

Publication Date

2005

Find this in a Library

Catalog Record

Abstract

The objective of data mining is to discover relationships among the data in a database. Temporal information can be used to provide a linear ordering on the occurrence of events, to determine inter-event relevance, and to link events in a data stream. The use of event linking extends the type of relationships that can be discovered. Standard market-basket analysis identifies co-occurrence in single transactions. Linking permits the discovery of relationships that occur among groups of events rather than strictly within a single event. Events may be linked by the source of the information, by relevancy constraints, and by duration. In this paper, we examine modifications to the a priori data mining algorithm suitable for identifying relationships in temporal data defined using event linking and fuzzy relevance constraints.

Comments

Presented at Conference of the North American Fuzzy Information Processing Society, Ann Arbor, 2005.

DOI

10.1109/NAFIPS.2005.1548630