Data mining techniques can be used by Health organizations to predict different types of Cancer disease using individual Gene expression data. By using DNA (Deoxyribo Nucleic Acid) Microarray technology, thousands of genes can be articulated simultaneously. The objective of this research is to look closer on the classification issues in handling microarray data by introducing Semi-Supervised KNN (K-Nearest Neighbor) algorithm and Particle Swarm Optimization (PSO) as feature selection to cluster large amount of genetic microarray data. Also, using the predicted type of cancer, the severity level of cancer is diagnosed. Classifier performance is evaluated and it is shown in pie-chart and graph with improved accuracy. The proposed Semi-supervised learning method provides 10% improved accuracy in predicting cancer than the existing Supervised and unsupervised learning methods.

Medical Data Mining, Cancer Prediction, Gene sequence, Clustering, Classification

[1] B. Jaison, G. Chilambuchelvan, K. Nirmal, “A hybrid approach for gene selection and classification using support vector machine”, International Arab Journal Information Technology, Vol.12, issue.6A, pp.695-700, 2015.
[2] P. M. Booma , S. Prabhakaran, “Classification of genes for disease identification using data mining techniques”,Journal of Theoretical and Applied Information Technology, vol.83, issue.3, pp.399-414, 2016.
[3] L. George, S. Asha ,W. Haibo , D.F. Michael , R.M. Stephen , N.C.S. Natalie , S. Elaine, R. Timothy, E.T. John, M. Anant, “Supervised Multi-view Canonical Correlation Analysis (sMVCCA): Integrating Histologic and proteomic features for predicting Recurrent prostate cancer”, IEEE transactions on Medical Imaging,vol.34,issue.1, pp.284-297,2015.
[4] A. Hasseeb, H. Jingyu, X. Yong, A. Russul, “ Lung Cancer Prediction from Microarray data by Gene expression programming”, IET Systems Biology,vol.10,issue.5, pp.168-178, 2016.
[5] Liu, Jin-Xing, Yong Xu, Chun-Hou Zheng, Heng Kong, Zhi-Hui Lai , “RPCA-Based Tumor Classification Using Gene Expression Data”,IEEE/ACM Transactions on Computational Biology and Bioinformatics (TCBB) ,vol.12,issue.4, pp.964-970, 2015.
[6] R. Nagpal, R. Shrivas, “Cancer Classification Using Elitism PSO Based Lezy IBK on Gene Expression Data”, International Journal of Scientific and Technical Advancements, vol.1, issue.4, pp.19-23, 2015.
[7] A. Natarajan, R. Bala Subramanian , “A Fuzzy Parallel Island Model Multi Objective Genetic Algorithm Gene Feature Selection for Microarray Classification”, International Journal of Applied Engineering Research, Vol.11, issue.4, pp.2761-2770, 2016.
[8] H. Park, Y. Shiraishi, S. Imoto, S. Miyano, “A novel Adaptive Penalized Logistic Regression for uncovering biomarker associated with Anti-cancer drug sensitivity”, IEEE/ACM transactions on Computational Biology and Bioinformatics, vol.14, issue.4, pp.771-782, 2017.
[9] N. Songyot, “Gene selection using interaction information for Microarray-based Cancer classification”, IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology, 2016.
[10] P. Thangaraju , R. Mehala, “Novel Classification Based Approaches over Cancer Diseases”, International Journal of Advanced Research in Computer and Communication Engineering, vol.4, issue.3, pp.294-297, 2015.
[11] R. Anupriya, P. Saranya , R. Deepika , “Mining Health Data in Multimodal Data Series for Disease Prediction”, International Journal of Scientific Research in Computer Science and Engineering ,Vol.6, Issue.2, pp. 96-99, 2018.
[12] Pramod Pardeshi and Ujwala Patil , “Fuzzy Association Rule Mining- A Survey”,International Journal of Scientific Research in Computer Science and Engineering ,Vol.5, Issue.6, pp.13-18, 2017.