Publication Type : Conference Proceedings
Publisher : 10th International Conference on Intelligent Systems and Control (ISCO), 2016 , IEEE.
Source : 10th International Conference on Intelligent Systems and Control (ISCO), 2016 , IEEE, Volume 15, Number 2, Karpagam College of Engineering, Coimbatore, India, p.414-419 (2016)
Url : http://ieeexplore.ieee.org/abstract/document/7726921/
Keywords : correlation coefficient, Feature selection, Fuzzy Rough Set, Quick Reduct
Campus : Coimbatore
School : School of Engineering
Department : Computer Science
Verified : Yes
Year : 2016
Abstract : In this study, we applied a novel method by using correlation coefficient filter for dimensionality reduction followed by fuzzy rough quick reduct algorithm for feature selection. The classification performance was evaluated using the gene subsets obtained from correlation based filter and our proposed method. Later we compared the results with other traditional classifier techniques. After suitable experimental analysis, it has been found that our proposed method has a two-fold advantage namely selection of much lesser number of genes compared to correlation coefficient and improved classifier accuracy in majority of the cases. This approach also reduces the number of misclassifications that might occur in other approaches.
Cite this Research Publication : A. Chinnaswamy and Ramakrishnan, S., “A hybrid approach to feature selection using correlation coefficient and fuzzy rough quick reduct algorithm applied to cancer microarray data”, 10th International Conference on Intelligent Systems and Control (ISCO), 2016 , vol. 15. IEEE, Karpagam College of Engineering, Coimbatore, India, pp. 414-419, 2016.