Abstract

Microarray technology can be used for learning number of genes expressions at one time. In recent years, DNA microarray method has a large influence in deciding the informative genes which originates cancer. The important step is the extraction of relevant genes in analyzing microarray cancer data. In this paper, microarray classification is done in two phases. In the first phase, a hybrid approach of principle component analysis is and genetic algorithm is applied on leukemia microarray dataset for extracting relevant features. Feed forward back propagation neural network is used and support vector machine for the classification purpose in the second phase and finally their results are compared.

References

• V. Trevino, F. Falciani and H. Barrera-saldana, “DNA microarrays: A Powerfull Genomic Toolfor Biomedical and Clinical Research”, Molecular Medicine, 13(9-10), 527-541, 2007.
• K. Vaishali, A. Vnayababu, “A Classification of Microarray Gene Expression Data Using Hybrid Soft Computing Approach”, International jounral of Computer Science Issues(IJCSI), 9, 246-255, 2012.
• D. Nguyen, D. Rocke, “Classification of Accute Leukemia Based on Gene Expression from DNA Microarrays Using Partial Least Squares”, Methods for microarray data analysis:papers from CAMDA Springer,109-124, 2001.
• M. Verleysen and D. François, “The Curse of Dimensionality in Data Mining and Time Series Prediction”, 8th international conference on Artificial Neural Networks IWANN,LNCS Springer, 3512, 758-770, 2005.
• M. Kumara, N. K. Rath, A. Swain and S. K. Rath, “Feature Selection and Classification of Microarray Data using MapReduce based ANOVA and K-Nearest Neighbor” , Eleventh International Conference on Communication Networks(ICCN), Procedia Computer Science,54, 301-310, 2015.
• R. Sreepada,S. Vipsita and P. Mohapatra,“An Efficient Approach for Classification of Gene Expression Microarray Data”, Emerging Applications of Information Technology(EAIT) 4th international conference, 344-308,2014.
• S. Sawant and P. Topannavar, “Introduction to Probablistic Neural Network-Used for Image Classification”, International Jounral ofAdvanced Reasearch in Computer Science and Software Engineering(IJARCSSE), 5, 279-283, 2015.
• Jolliffe, I. T., “Principle Component Analysis”, Springer Series in Statistics, Vol 2, 2002.
• A. Eiben, P. Raue and Zs. Ruttkay, “Genetic algorithm with multi-parent recombination”, 866, 78-87, 1994.
• G. Joshi, “Review of Genetic Algorithm:An optimization Technique”, International Jounral of Advanced Research in Computer Science and Software Engineering(IJARCSSE), 4, 802-805, 2014.
• K. Faraoun and A.Rabhi, “Data dimensionality reduction based on Genetic selection on feature subsets”,INFOCOMP journal of computer Science, 6(3),33-46,2007.
• J. Yayad, M. Yadav and A. Jain, “Artificial Neural Network”, International Jounral of Scientific Research and Education, 1, 108-118, 2013.
• O. A. Abdalla, M. N. Zakaria, S. Sulaiman and W. F. W. Ahmad, “A comparision of feed-forward back- propagation and radial basis artificial neural networks”, International Symposium on Information Technology, 2, 994-998, 2010.
• C. Cortes and V. Vapnik, “Support-vector networks”, Machine Learnig(Springer), 20, 273-297, 1995.
• H. Bhavsar and M. Panchal, “A Review of Support Vector Machine for Data Classification”, International Jounral of Advanced Reasearch in Computer Science & Technologies(IJARCET), 1, 185-189, 2012.
• Y. Lee and C. Chao, “A Data Mining Application to Leukemia Microarray Gene Expression Data Analysis”, International Conference on Informatics Cybernetics and Systems (ICICS), Kaohsiung, Taiwan,2003.
• R. Mallika and V. Saravanan, “An svm based classification method for cancer data using minimum microarray gene expressions”, World Academy of Science, Engineering and Technology International Journal of Computer, Electrical, Automation, Control and Information Engineering, 4(2), 266-270, 2010.
• P. G. Kumar, J. Rathinaraja, T. Aruldoss and A. Victoire, “A combined MI-AVR approach for informative gene selection”,2nd International conference on Sustainable Energy and Intelligent System (SEISCON),870-875,2011.
• P.K. Vaishali and A. Vinayababu, “Application of Microarray Technology and Softcomputing in Cancer Biology: A Review",International Journal of Biometrics and Bioinformatics (IJBB), 5(4), 225-233, 2011.
• B. Li, C. Zheng, D. Huang, and L.Zhang, K. Han, “Gene expression data classification using locally linear discriminate embedding”, Computers in Biology and Medicine, 40(10), 802-810,2010.
• X. Zhou, L. Guo, T. Wang and Y. Hu, “Text Feature Selection Based on Class Subspace” IEEE International Conference on Data Mining Workshop,267-273, 2014.
• H. Bu , S. Zheng and F. Qian, “tumer classification byComputer PCA with relief wrapper”, International Conference on Science and Information Technology(ICCSIT), pp. 514-517, 2009.
• J. C. H. Hernandez, B. Duval and J.K. Hao, “A Genetic Embedded Approach for Gene Selection and Classification of Microarray Data, Lecture notes in Computer Science, Springer, 4447, 90-101, 2007.
• E. Darby; T. Nettimi, S. Kodali and L. Shih, “Head and neck cancer metastasis prediction via artificial neural networks”,IEEE workshop on Computational Systems Bioinformatics Conference (CSBW'05),43-44,2005.
• Y. Huang and S. Du, “Weighted Support vector machine for classification with uneven training class size”, Internation Conference on Machine Learning and Cybernetics, 7,4365-4369, 2005.