http://dx.doi.org/10.1007/978-3-642-37456-2_12">
 

Document Type

Conference Paper

Department/Unit

Department of Computer Science

Title

A unified metric for categorical and numerical attributes in data clustering

Language

English

Abstract

Most of the existing clustering approaches are applicable to purely numerical or categorical data only, but not both. In general, it is a nontrivial task to perform clustering on mixed data composed of numerical and categorical attributes because there exists an awkward gap between the similarity metrics for categorical and numerical data. This paper therefore presents a general clustering framework based on the concept of object-cluster similarity and gives a unified similarity metric which can be simply applied to the data with categorical, numerical, or mixed attributes. Accordingly, an iterative clustering algorithm is developed, whose efficacy is experimentally demonstrated on different benchmark data sets. © Springer-Verlag 2013.

Publication Date

2013

Source Publication Title

17th Pacific-Asia Conference, PAKDD 2013, Gold Coast, Australia, April 14-17, 2013, Proceedings, Part II

Start Page

135

End Page

146

Conference Location

Gold Coast, Australia

Publisher

Springer Berlin Heidelberg

ISBN (print)

9783642374555

ISBN (electronic)

9783642374562

This document is currently not available here.

Share

COinS