Parallel Batch K-Means For Big Data Clustering

The application of clustering algorithms is expanding due to the rapid growth of data volumes. Nevertheless, existing algorithms are not always effective because of high computational complexity. A new parallel batch clustering algorithm based on the k-means algorithm is proposed. The proposed algorithm splits a dataset into equal partitions and reduces the exponential growth of computations. The goal is to preserve the characteristics of the dataset while increasing the clustering speed. The centers of the clusters are calculated for each partition, which are merged and also clustered later. The approach to determine the optimal batch size is also considered. The statistical significance of the proposed approach is provided. Six experimental datasets are used to evaluate the effectiveness of the proposed parallel batch clustering. The obtained results are compared with the k-means algorithm. The analysis shows the practical applicability of the proposed algorithm to Big Data.