Analysis And ImplementationOf K-Mean And K-Medoids Algorithm For Large Dataset To Increase Scalability And Efficiency

Abstract

The experiments are pursued on both synthetic in data sets are real. The synthetic data sets which we used for our experiments were generated using the procedure. We refer to readers to it for more details to the generation of large data sets. We report experimental results on two synthetic more data sets in this data set; the average transaction of size and its average maximal potentially frequent item set its size are set, while the number of process in the large dataset is set. It is a sparse of dataset. The frequent item sets are short and also numerous data sets to cluster. The second synthetic data set we used is. The average transaction size and average maximal potentially frequent item set size of set to 30 and 32 respectively. There exist exponentially numerous frequent item data sets in this data set when the support based on threshold goes down. There are also pretty long frequent item sets as well as a large number of short frequent item sets in it. It process of contains abundant mixtures of short and long frequent data item sets.