Enhanced bisecting k-means clustering using intermediate cooperation

Authors:
R. Kashef;M. S. Kamel
Affiliations:
University of Waterloo, Electrical and Computer Engineering Department, Waterloo, Canada;University of Waterloo, Electrical and Computer Engineering Department, Waterloo, Canada
Venue:
Pattern Recognition
Year:
2009

Citing 16
Cited 5

Multidimensional data clustering utilizing hybrid search strategies

Pattern Recognition
Automatic text processing: the transformation, analysis, and retrieval of information by computer

Automatic text processing: the transformation, analysis, and retrieval of information by computer
Elements of information theory

Elements of information theory
Using MPI: portable parallel programming with the message-passing interface

Using MPI: portable parallel programming with the message-passing interface
Data clustering: a review

ACM Computing Surveys (CSUR)
Partitioning-based clustering for Web document categorization

Decision Support Systems - Special issue on WITS '97
A vector space model for automatic indexing

Communications of the ACM
Principal Direction Divisive Partitioning

Data Mining and Knowledge Discovery
Performance Evaluation of Some Clustering Algorithms and Validity Indices

IEEE Transactions on Pattern Analysis and Machine Intelligence
Cluster ensembles: a knowledge reuse framework for combining partitionings

Eighteenth national conference on Artificial intelligence
Consensus Clustering: A Resampling-Based Method for Class Discovery and Visualization of Gene Expression Microarray Data

Machine Learning
Combining Partitional and Hierarchical Algorithms for Robust and Efficient Data Clustering with Cohesion Self-Merging

IEEE Transactions on Knowledge and Data Engineering
Document Clustering Using Locality Preserving Indexing

IEEE Transactions on Knowledge and Data Engineering
A parallel hybrid web document clustering algorithm and its performance study

The Journal of Supercomputing - Special issue: Parallel and distributed processing and applications
Cumulative Voting Consensus Method for Partitions with Variable Number of Clusters

IEEE Transactions on Pattern Analysis and Machine Intelligence
Survey of clustering algorithms

IEEE Transactions on Neural Networks

Cooperative clustering

Pattern Recognition
An improved sequential clustering algorithm

AICI'11 Proceedings of the Third international conference on Artificial intelligence and computational intelligence - Volume Part I
Cooperative clustering for software modularization

Journal of Systems and Software
High performance genetic algorithm based text clustering using parts of speech and outlier elimination

Applied Intelligence
CRUDAW: a novel fuzzy technique for clustering records following user defined attribute weights

AusDM '12 Proceedings of the Tenth Australasian Data Mining Conference - Volume 134

Quantified Score

Hi-index	0.01

Visualization

Abstract

Bisecting k-means (BKM) is very attractive in many applications as document-retrieval/indexing and gene expression analysis problems. However, in some scenarios when a fraction of the dataset is left behind with no other way to re-cluster it again at each level of the binary tree, a ''refinement'' is needed to re-cluster the resulting solutions. Current approaches to refine the clustering solutions produced by the BKM employ end-result enhancement using k-means (KM) clustering. In this hybrid model, KM waits for the former BKM to finish its clustering and then it takes the final set of centroids as initial seeds for a better refinement. In this paper, a cooperative bisecting k-means (CBKM) clustering algorithm is presented. The CBKM concurrently combines the results of the BKM and KM at each level of the binary hierarchical tree using cooperative and merging matrices. Undertaken experimental results show that the CBKM achieves better clustering quality than that of KM, BKM, and single linkage (SL) algorithms with comparable time performance over a number of artificial, text documents, and gene expression datasets.