An efficient clustering algorithm of minimum Spanning Tree

In this researched paper, a clustering algorithm to discover clusters of unusual shapes and densities. Hierarchical and Density based ways are implemented for constructing minimum Spanning Tree; the MST can be divided into two segments. In the first segment, local density is guesstimate at every data point. In the subsequent segment, hierarchical ways are used by combining clusters according to the calculated cluster distance based to go-beyond in distribution of data objects. The recommended method improvises the efficiency of clustering result, where the data is distributed in different shapes and density; it leads to better clustering efficiency. This approach presents a clustering algorithm that is inspired by MST. In this algorithm, a new method for construction which reduces the computational complexity compared with traditional MST construction methods.