International Journal of Emerging Technology and Advanced Engineering (IJETAE)
In the high dimensional data set having features selection involves identifying a subset of the most useful features that produce compatible results as the original entire set of features. A fast algorithm may be evaluated from both the ability concerns the time required to find a subset of features and the value is required to the quality of the subset of features. Fast clustering based feature selection is proposed for fast clustering in high dimensional data. In this cluster can be divided into number of subset and in the second step relatively independent classes of subset data can be producing as independent and finally the fast clustering can be performed based on the minimum spanning tree method can be produced as fast clustering in the datasets.