Universiti Teknologi Malaysia Institutional Repository

Weighted Kernel K-means algorithm for clustering spatial data

Md. Sap, Mohd. Noor and Awan, A. Majid (2004) Weighted Kernel K-means algorithm for clustering spatial data. Jurnal Teknologi Maklumat, 16 (2). pp. 137-156. ISSN 0128-3790

[img] PDF
381Kb

Abstract

This paper presents a method for unsupervised partitioning of data using kernel methods which offer strength to deal with complex data non-linearly separable in input space. This work is based on the notion that a non-linear data transformation into some high dimensional feature space increases the possibility of linear separability of the patterns in the transformed space. Therefore, it simplifies exploration of the associated structure in the data. Kernel methods implicitly perform a n on-linear mapping oft he input data into a high dimensional feature sp ace by replacing the inner products with an appropriate positive definite function. Firstly, in this paper, selective kernel-based clustering techniques are analyzed, the shortcomings are identified especially for spatial data analysis and future directions are laid out. Finally, we present a robust weighted kernel k-means algorithm incorporating spatial constraints for clustering spatial data as a case study. The proposed algorithm can effectively handle noise, outliers and auto-correlation in the spatial data.

Item Type:Article
Uncontrolled Keywords:clustering algorithms, K-means, Kernel methods, spatial data, unsupervised learning
Subjects:Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions:Computer Science and Information System (Formerly known)
ID Code:3430
Deposited By: Mrs Rozilawati Dollah @ Md Zain
Deposited On:24 May 2007 05:17
Last Modified:11 May 2011 04:39

Repository Staff Only: item control page