Efficient Clustering of Dataset Based on Differential Evolution
A novel approach to combining feature selection and clustering is presented. It uses selection of weighted Principal Components for features selection and automatic clustering based on Improved DE for clustering in order to reduce the complexity of high dimensional datasets and speed up the DE clustering process. We report significant improvements in total runtime. Moreover, the clustering accuracy of the dimensionality reduction DE clustering algorithm is comparable to the one that uses full dimensional datasets. The efficiency of this approach has been demonstrated with some real life datasets.
KeywordsClustering PCs Dimension DE
Unable to display preview. Download preview PDF.
- 1.Ben-Dor, A., Friedman, N., Yakhini, Z.: Class discovery in gene expression data. In: Procs. RECOMB, pp. 31–38 (2001)Google Scholar
- 2.Law, M.H., Jain, A.K., Figueiredo, M.A.T.: Feature selection in mixture-based clustering. In: Advances in Neural Information Processing Systems, vol. 15 (2003) (to appear)Google Scholar
- 3.Heydebreck, A.V., Huber, W., Poustka, A., Vingron, M.: Identifying splits with clear separation: A new class discovery method for gene expression data. Bioinformatics 17 (2001)Google Scholar
- 4.Kim, S.B., Rattakorn, P.: Unsupervised Feature Selection Using Weighted Principal Components (2010)Google Scholar
- 5.Das, S., Konar, A., Braham, A.: Automatic Clustering Using an Improved Differential Evolution Algorithm. IEEE Transactions on Systems, Man, and Cybernetics—Part a: Systems and Humans 38(1) (January 2008)Google Scholar
- 6.Boutsidis, C., Mahoney, M.W., Drineas: Unsupervised Feature Selection for Principal Components Analysis. In: KDD 2008, Las Vegas, Nevada, USA, August 24-27 (2008)Google Scholar