Published Paper Details:

Research on effective methods to deal with ever larger data sets has been gaining importance in recent years. The goal of clustering is to organize a data collection into clusters, such that items within each cluster are more similar to each other than to items in other clusters. While supervised clustering assumes that some information is available concerning the membership of data items to predefined classes, unsupervised clustering does not require a priori knowledge of data contents. There are many applications of unsupervised clustering in computer vision, pattern recognition, information retrieval, data mining, etc. The objective of this research work is focused on the ethical cluster creation of smartphone sensors data and analyzed the performance of partition based algorithms. Dataset consist of all the information gathered during the network connection established with wristwatch and smartphone, which needs to be, analyzed the performance of the proposed improved farthest first clustering algorithm.