Hypothesis oriented cluster analysis in data mining by visualization

Ke Bing Zhang*, Mehmet A. Orgun, Kang Zhang, Yihao Zhang

*Corresponding author for this work

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

5 Citations (Scopus)

Abstract

Cluster analysis is an important, technique that has been used in data mining. However, cluster analysis provides numerical feedback making it hard for users to understand the results better; and also most, of the clustering algorithms are not suitable for dealing with arbitrarily shaped data distributions of datasets. While visualization techniques have been proven to be effective in data mining, their use in cluster analysis is still a major challenge, especially in data mining applications with high-dimensional and huge datasets. This paper introduces a novel approach, Hypothesis Oriented Verification and Validation by Visualization, named HOV3, which projects datasets based on given hypotheses by visualization in 2D space. Since HOV3 approach is more goal-oriented, it can assist, the user in discovering more precise cluster information from high-dimensional datasets efficiently and effectively.

Original languageEnglish
Title of host publicationProceedings of the AVI '06 - Working Conference on Advanced Visual Interfaces 2006
EditorsAugusto Celentano, Piero Mussio
Place of PublicationNew York
PublisherACM
Pages254-257
Number of pages4
Volume2006
ISBN (Print)1595933530, 9781595933539
DOIs
Publication statusPublished - 2006
EventAVI '06 - Working Conference on Advanced Visual Interfaces 2006 - Venezia, Italy
Duration: 23 May 200626 May 2006

Other

OtherAVI '06 - Working Conference on Advanced Visual Interfaces 2006
CountryItaly
CityVenezia
Period23/05/0626/05/06

Fingerprint Dive into the research topics of 'Hypothesis oriented cluster analysis in data mining by visualization'. Together they form a unique fingerprint.

Cite this