Clustering uncertain interval data using a new Hausdorff-based metric

Author

Zarandi, M. H Fazel ; Avazbeigi, M. ; Anssari, M.H. ; Turksen, I.B.

Author_Institution

Dept. of Ind. Eng., Amirkabir Univ. of Technol. (AUT), Tehran, Iran

fYear

2010

fDate

12-14 July 2010

Firstpage

1

Lastpage

5

Abstract

This paper presents a new index for measuring interval distances and its related metric. The proposed index and metric are both based on the Hausdorff distance which can be used for clustering uncertain interval data. Then using the new metric, a clustering method is introduced for clustering of intervals. Finally, some experiments are provided to validate the method. Results show that the method can identify appropriate clusters efficiently.

Keywords

data analysis; pattern clustering; uncertainty handling; Hausdorff based metric; interval distance measurement; uncertain interval data clustering; Clustering algorithms; Clustering methods; Data analysis; Extraterrestrial measurements; Industrial engineering; Iterative algorithms; Paper technology; Partitioning algorithms; Pattern recognition; Space exploration; Clustering Interval Data; Hausdorff Distance; Pattern Recognition; Uncertain Interval Data; component;

fLanguage

English

Publisher

ieee

Conference_Titel

Fuzzy Information Processing Society (NAFIPS), 2010 Annual Meeting of the North American

Conference_Location

Toronto, ON

Print_ISBN

978-1-4244-7859-0

Electronic_ISBN

978-1-4244-7857-6

Type

conf

DOI

10.1109/NAFIPS.2010.5548291

Filename

5548291