International Journal of Image Processing and Pattern Recognition
Comparative Study of Classification Methods Based on Feature Reduced Microarray Gene-Expression Data
Abstract
Abstract Cancer is a very complex and clinical heterogeneous disease. Now a days the research into the diagnosis and treatment of cancer have become an important issue for researchers. Cancer microarray data normally consist of samples having large number of gene expression as features. For better result in cancer classification it is very important to select relevant features. In this paper, five different types of cancer datasets are used such as colon, lymphoma, SRBCT, prostate, and leukemia, and F-Score is used for feature extraction. In my work, different classification techniques are applied on the cancer datasets. The objective of this paper is to diagnose and analyze cancer disease with the help of well-known classifiers like functional link artificial neural network (FLANN), Back-propagation Network (BPN), Kth Nearest Neighbours (KNN), and Radial Basis Function (RBF) and provide comparative study of these four classifiers in terms of their accuracy. Keywords: BPN, feature extraction, F-Score, FLANN, KNNReferences (16)
- Yeh J.Y., Wu T.S., Wu M.C., et al. Applying data mining techniques for cancer classification from gene expression data. International Conference on Convergence Information Technology. 2007.
- de Lima S.M.L., da Silva-Filho A.G., Wellington Pinheiro dos-Santos. A methodology for classification of lesions in mammo-graphies using zernike moments, ELM and SVM neural networks in a multi-kernel approach. IEEE International Conference on Systems, Man, and Cybernetics, 2014.
- Ghosh S., Mondal S., Ghosh B. A Comparative study of breast cancer detection based on SVM and MLP BPN classifier. IEEE Trans. 2014; 5(6): 915–19p.
- Yang X.U., Jia L., Qingmao H., et al. F-score feature selection method may improve texture based liver segmentation strategies. IEEE International Symposium on IT in Medicine and Education, 2008.
- Palacios Pawlovsky A., Nagahashi M. A Method to select a good setting for the KNN algorithm when using it for breast cancer prognosis. 2014 IEEE.
- Mert A., Kilic N., Akan A. Breast cancer classification by using support vector machines with reduced dimension. 53rd International Symposium. ELMAR-2011.
- Mumtaz K., Sheriff S.A., Duraiswamy K. Evaluation of three neural network models using wisconsin breast cancer database. IEEE. 2011.
- Li X., Peng S., Zhan X., et al. Comparison of feature selection methods for multiclass cancer classification based on microarray data. 24th International Conference on Biomedical Engineering and Informatics (BMEI). 2011.
- Mahapatra R., Majhi B., Rout M. Development and performance evaluation of improved classifiers of microarray data. IEEE-International Conference on Advances in Engineering, Science and Management (ICAESM-2012). 2012.
- Jaganathan P., Rajkumar N., Kuppuchamy R. A comparative study of improved F-score with support vector machine and RBF network for breast cancer classification. Int J Machine Learn Comput. 2012; 2(6): 2012.
- Yigit H. A weighting approach for KNN classifier. IEEE. 2013.
- Saravanan V., Mallika R. An effective classification model for cancer diagnosis using micro array Gene expression data. International Conference on Computer Engineering and Technology, ICCET. 2009.
- Vennila G.S., Suresh L.P., Shunmuganathan K.L. Dermoscopic Image Segmentation and Classification using Machine Learning Algorithms. International Conference on Computing, Electronics and Electrical Technologies, ICCEET. 2012.
- Perez M., Marwala T. Microarray data feature selection using hybrid genetic algorithm simulated annealing. IEEE 27th Convention of Electrical and Electronics Engineers in Israel. 2012.
- Li R., Sun Y. Diagnosis of breast tumor using SVM-KNN classifier. Second WRI Global Congress on Intelligent Systems, 2010.
- Breast Cancer Wisconsin (Original) dataset, UCI Machine Language Repository. 1992.