A Comparative Study on Cancer Prediction Methodology Using Clustering Algorithms

Abstract

Data mining is a search for relationship and patterns that   exist in large database. Clustering is an important data mining technique. Because of the complexity and the high dimensionality of data, classification of a disease samples remains a challenge. Hierarchical clustering and partitioning clustering is useful for classification of samples. In this paper, we make a comparative study of two clustering methods namely Sparse KMeans, and Fast Clustering Algorithms to classify the cancer dataset. Comparative analysis of clustering algorithms is also carried out using four different dataset Breast cancer, Colon, Leukemia and Lung cancer. The performance of algorithms depends on the Correctly classified clusters and the Average accuracy of data. The final outcome of this work is suitable to analyses the behavior of cancer in the department of oncology in cancer centers. Ultimate goal of this research work is to find out which type of dataset and algorithm will be most suitable for analysis of cancer data.