• ROSY MISHRA
• Seema Baghel
• Rosan Patel
• Monali Patel

The clustering of dataset has become a challenging issue in the field of health analytics. Existing k-means clustering algorithms requires scalable solutions to manage large datasets. The goal of the present work is to detect the number of non-informative or meaningless variable present in a data set but cluster select those variable which have some meaning as well as important variable. It is based on genetic algorithm that help us to make the data easy to understand. We use these procedure in K-means by using Silhouette plot as the function of genetic algorithm. The main problem with it is when we use these method in the real data and re-apply at that time do not know a prior what the real cluster structure is that means whether it is a number and composition of the groups. These work leads to the evolution of the silhouette values that is built by the application of k-means any meaningless or non-informative variable is added to the original data set in both literature as well as high dimension data. These procedure is also added to the real data set. The methodology is applied to different genomic data set like lung cancer, brain tumor, normal tumor, diabetes and kidney gene expression data set.

clustering, k-means, silhouette plot, PCA, Genomic Datasets

"Coherent Knowledge Discovery in Health Care Using Genomic k-Means Clustering", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.5, Issue 3, page no.1288-1294, March-2018, Available :http://www.jetir.org/papers/JETIR1803245.pdf

"Coherent Knowledge Discovery in Health Care Using Genomic k-Means Clustering", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.5, Issue 3, page no. pp1288-1294, March-2018, Available at : http://www.jetir.org/papers/JETIR1803245.pdf