Research on Clustering Analysis of Big Data

Abstract

Data quantity of Big Data was too big to be processed with traditional clustering analysis technologies. Time consuming was long, problem of computability existed with traditional technologies. Having analyzed on k-means clustering algorithm, a new algorithm was proposed. Parallelizing part of k-means was found. The algorithm was improved with the method of redesigning flow with MapReduce framework. Problems mentioned above were solved. Experiments show that new algorithm is feasible and effective.