Clustering using a coarse-grained parallel genetic algorithm: a preliminary study
- 19 November 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 331-338
- https://doi.org/10.1109/camp.1995.521057
Abstract
Genetic algorithms (GA) are useful in solving complex optimization problems. By posing pattern clustering as an optimization problem, GAs can be used to obtain optimal minimum squared error partitions. In order to improve the total execution time, a distributed algorithm has been developed using the divide and conquer approach. Using a standard communication library called PVM, the distributed algorithm has been implemented on a workstation cluster: the GA approach gives better quality clusters for many data sets compared to a standard K-means clustering algorithm. We have achieved a near linear speedup for the distributed implementation.Keywords
This publication has 6 references indexed in Scilit:
- A note on genetic algorithms for large-scale feature selectionPublished by Elsevier ,2003
- Unsupervised image segmentation using a distributed genetic algorithmPattern Recognition, 1994
- Shape analysis using genetic algorithmsPattern Recognition Letters, 1993
- Clustering on a hypercube multicomputerIEEE Transactions on Parallel and Distributed Systems, 1991
- Experiments in projection and clustering by simulated annealingPattern Recognition, 1989
- A VLSI Systolic Architecture for Pattern ClusteringPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1985