Refining a divisive partitioning algorithm for unsupervised clustering

Authors:
Canasai Kruengkrai;Virach Sornlertlamvanich;Hitoshi Isahara
Affiliations:
Thai Computational Linguistics Laboratory, Communications Research Laboratory, 112 Paholyothin Road, Klong 1, Klong Luang, Pathumthani 12120, Thailand;Thai Computational Linguistics Laboratory, Communications Research Laboratory, 112 Paholyothin Road, Klong 1, Klong Luang, Pathumthani 12120, Thailand;Thai Computational Linguistics Laboratory, Communications Research Laboratory, 112 Paholyothin Road, Klong 1, Klong Luang, Pathumthani 12120, Thailand
Venue:
Design and application of hybrid intelligent systems
Year:
2003

Citing 5
Cited 1

A new approach to unsupervised text summarization

Proceedings of the 24th annual international ACM SIGIR conference on Research and development in information retrieval
Principal Direction Divisive Partitioning

Data Mining and Knowledge Discovery
X-means: Extending K-means with Efficient Estimation of the Number of Clusters

ICML '00 Proceedings of the Seventeenth International Conference on Machine Learning
Pattern Classification (2nd Edition)

Pattern Classification (2nd Edition)
A Bayesian approach to learning Bayesian networks with local structure

UAI'97 Proceedings of the Thirteenth conference on Uncertainty in artificial intelligence

Enhancing principal direction divisive clustering

Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

The Principal Direction Divisive Partitioning (PDDP) algorithm is a fast and scalable clustering algorithm [3]. The basic idea is to recursively split the data set into sub-clusters based on principal direction vectors. However, the PDDP algorithm can yield poot results, especially when cluster structures are not well-separated from one another. Its stopping criterion is based on a heuristic that often tends to overestimate the number of clusters. In this paper, we propose simple and efficient solutions to the problems by refining results from the splitting process, and applying the Bayesian Information Criterion (BIC) to estimate the true number of clusters. This motivates a novel algorithm for unsupervised clustering, which its experimental results on different data sets are very encouraging.