Data Mining by Clustering in Very Large Relational Databases

Grant number: DP0663196

Abstract

Many commercial and governmental entities possess very large relational data that cannot be feasibly analyzed by today's computers, e.g., gene expression data, product usage databases and telecommunication call records. The clustering tools developed in this project will have a significant benefit on many business processes that involve clustering this type of data, such as fraud detection and market segmentation.

Related publications (7)

Scholarly works icon

Enhanced visual analysis for cluster tendency assessment and data partitioning

L Wang, X Geng, J Bezdek, C Leckie, R Kotagiri

2010-09-01

Visual methods have been widely studied and used in data cluster analysis. Given a pairwise dissimilarity matrix D of a set of n o..

Scholarly works icon

Approximate spectral clustering

L Wang, C Leckie, K Ramamohanarao, J Bezdek

2009-07-23

While spectral clustering has recently shown great promise, computational cost makes it infeasible for use with large data sets. T..

Scholarly works icon

Automatically Determining the Number of Clusters in Unlabeled Data Sets

Liang Wang, Christopher Leckie, Kotagiri Ramamohanarao, James Bezdek

2009-03-01

One of the major problems in cluster analysis is the determination of the number of clusters in unlabeled data, which is a basic i..

Scholarly works icon

SpecVAT: Enhanced visual cluster analysis

W Liang, G Xin, J Bezdek, C Leckie, R Kotagiri

2008-12-01

Given a pairwise dissimilarity matrix D of a set of objects, visual methods such as the VAT algorithm (for visual analysis of clus..

Scholarly works icon

Moving shape dynamics: A signal processing perspective

L Wang, X Geng, C Leckie, R Kotagiri

2008-09-23

This paper provides a new perspective on human motion analysis, namely regarding human motions in video as general discrete time s..

Scholarly works icon

Characteristic-based descriptors for motion sequence recognition

L Wang, X Wang, C Leckie, K Ramamohanarao

2008-06-09

This paper proposes an approach based on characteristic descriptors for recognition of articulated and deformable human motions fr..

Scholarly works icon

Approximate clustering in very large relational data

JC Bezdek, RJ Hathaway, JM Huband, C Leckie, R Kotagiri

2006-08-01

Different extensions of fuzzy c-means (FCM) clustering have been developed to approximate FCM clustering in very large (unloadable..

University of Melbourne Researchers