A novel priority based data mining algorithm using improved K-means clustering for detecting protein sequence from dataset

This paper presents a novel priority based data mining algorithm using improved K-means clustering for detecting proteins sequence from dataset of frequent item set. The priorities are set depending on the number of hits (counts) from the dataset concurrently using the concept of multiprocessing. Which dynamically changing for a period of time series, a novel algorithm is used for classification and Clustering of the data and explored by improved k-means technique. In this paper protein sequences sample are taken from the Protein Data Bank (PDB). The data taken which has been experimented with the proposed algorithm and the results are tabulated.