An Embedded Architecture for Efficient Cycle Mining in Database and Knowledge Base Systems

Yi Pan, Jennifer Seltzer, James P. Buckley

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

Abstract

Knowledge discovery in databases has been defined as the non-trivial process of identifying valid, novel, potentially useful, and understandable patterns in data. It has been shown that we need to identify and actively seek cycles out of data, and that to identify and extract these special patterns can help us better understand and control our environment. In this paper, a parallel embedded architecture based on the reconfigurable mesh model is proposed to perform cycle mining efficiently. We show that once a hypergraph is established in a knowledge base system, cycles can be detected in constant time using this architecture. Since the parallel architecture can be readily implemented using FPGA technology, our results not only are of theoretical interest, but also have significant implications for data mining applications in practice.

Original languageEnglish
Title of host publication14th International Conference on Parallel and Distributed Computing Systems 2001, PDCS 2001
EditorsEdwin Sha
PublisherInternational Society for Computers and Their Applications (ISCA)
Pages359-364
Number of pages6
ISBN (Electronic)9781618395740
Publication statusPublished - 2001
Externally publishedYes
Event14th International Conference on Parallel and Distributed Computing Systems, PDCS 2001 - Richardson, United States
Duration: 8 Aug 200110 Aug 2001

Publication series

Name14th International Conference on Parallel and Distributed Computing Systems 2001, PDCS 2001

Conference

Conference14th International Conference on Parallel and Distributed Computing Systems, PDCS 2001
Country/TerritoryUnited States
CityRichardson
Period8/08/0110/08/01

Keywords

  • cycle detection
  • data mining
  • embedded architecture
  • FPGA
  • reconfigurable mesh

Fingerprint

Dive into the research topics of 'An Embedded Architecture for Efficient Cycle Mining in Database and Knowledge Base Systems'. Together they form a unique fingerprint.

Cite this