Publication Type : Journal Article
Publisher : Journal of Network and Innovative Computing.
Source : Journal of Network and Innovative Computing, Volume 4, Issue 1, p.164–174 (2016)
Url : https://www.researchgate.net/profile/Arunkumar_Chinnnaswamy/publication/303012519_A_comparative_study_of_hybrid_feature_selection_methods_using_correlation_coefficient_for_microarray_data/links/573553f508ae298602df0e18.pdf
Keywords : Correlation, Feature selection, Fuzzy Rough Set, greedy stepwise, particle swarm optimization
Campus : Coimbatore
School : School of Engineering
Department : Computer Science
Verified : Yes
Year : 2016
Abstract : Feature selection is a key challenge before the process of classification could be performed. The classification accuracy would increase by using a good feature selection method and also at the same time reduces the cost and time involved in the computation. In this study, we applied hybrid methods by using Correlation Based Feature Selection combined with different search algorithms. The classification performance was evaluated using fuzzy rough neural network classifier on the selected gene subsets. The experimental results reveal that majority of the hybrid method selects very few gene subsets and produces much better classification accuracy. The results are validated using traditional approaches like Precision, Recall, F-Score and Region of Characteristic.
Cite this Research Publication : A. Chinnaswamy and Ramakrishnan, S., “A comparative study of hybrid feature selection methods using correlation coefficient for microarray data”, Journal of Network and Innovative Computing, vol. 4, no. 1, pp. 164–174, 2016.