Comparative Study of ANFIS-Based Wrapper Model for Classification of Cancer and Normal Genes on Microarray Gene Expression Data
Sarita Chauhan1, Aakashdeep Sharma2, Abhishek Brahmabhatt3, Namrata Singh4, Puneet Sharma5
1Sarita Chauhan, Asst. Prof., M L V Textile and Engineering College Bhilwara, India.
2Aakash Deep Sharma, Under Graduate, B.Tech Student, M L V Textile and Engineering College Bhilwara, India.
3Abhishek Brahmabhatt, Under Graduate, B.Tech Student, M L V Textile and Engineering College Bhilwara, India.
4Namrata Singh, Under Graduate, B.Tech Student, M L V Textile and Engineering College Bhilwara, India.
5Puneet Sharma, Under Graduate, B.Tech Student, M L V Textile and Engineering College Bhilwara, India.
Manuscript received on March 29, 2015. | Revised Manuscript received on April 02, 2015. | Manuscript published on April 15, 2015. | PP: 17-21 | Volume-3 Issue-5, April 2015. | Retrieval Number: E0841043515/2015©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Published By: Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: A novel way to enhance the performance of a model that combines genetic algorithms and neuro fuzzy logic for feature selection and classification is proposed. This research work involves designing a framework that incorporates genetic algorithm with neuro fuzzy for feature selection and classification on the training dataset. It aims for reducing several medical errors and provides better prediction of diseases. Medical diagnosis of diseases is an important and difficult task, and a proposed method performs feature selection and parameters setting in an evolutionary way. The wrapper approach to feature subset selection is used in this paper because of the accuracy. The performance of the ANFIS classifier was evaluated in terms of training performance and classification accuracy. The objective of this research is to simultaneously optimize the parameters and feature subset without degrading the ANFIS classification accuracy. ANFIS is compared with three other classifiers which are Support Vector Machine (SVM), K-Nearest Neighbour (KNN) and Classification And Regression Trees (CART). ANFIS gives the best results for original data of all the datasets and the predictions for noisy data are adequate in comparison with three others classifiers.
Keywords: ZANFIS; Feature Selection; Cancer Classification.