Rough K-means Based On Mapreduce

Transcript

Clustering has been the one of the most used mining methodology. With the advent of sensor technologies, the Internet of things, and rising social data, the era of the big data is upon us and scaling the current set of clustering algorithms is one of the fields primarily researched on. In this paper, we pro- pose a parallel rough K-means algorithm based on MapReduce proposed by Lingras et. al and present you with the preliminary experiments done with synthetic data.