Multi-core Clustering of Categorical Data using Open MP

The processing power of computing devices has increased with number of available cores. This paper presents an approach towards clustering of categorical data on multi-core platform. K-modes algorithm is used for clustering of categorical data which uses simple dissimilarity measure for distance computation. The multi-core approach aims to achieve speedup in processing. Open Multi Processing (OpenMP) is used to achieve parallelism in k-modes algorithm. OpenMP is a shared memory API that uses thread approach using the fork-join model. The dataset used for experiment is Congressional Voting Dataset collected from UCI repository. The dataset contains votes of members in categorical format provided in CSV format. The experiment is performed for increased number of clusters and increasing size of dataset.