Optimal Dual Similarity Noise-free Clusters Using Dynamic Minimum Spanning Tree

Clustering is a process of discovering groups of objects such that the objects of the same group are similar, and objects belonging to different groups are dissimilar. A number of clustering algorithms exist that can solve the problem of clustering, but most of them are very sensitive to their input parameters. Minimum Spanning Tree clustering algorithm is capable of detecting clusters with irregular boundaries. Detecting outlier in database (as unusual objects) is a big desire. In data mining detection of anomalous pattern in data is more interesting than detecting inliers. In this paper we propose a Minimum Spanning Tree based clustering algorithm for noise-free or pure clusters. The algorithm constructs hierarchy from top to bottom. At each hierarchical level, it optimizes the number of cluster, from which the proper hierarchical structure of underlying dataset can be found. The algorithm uses a new cluster validation criterion based on the geometric property of data partition of the data set in order to find the proper number of clusters at each level. The algorithm works in two phases. The first phase of the algorithm produces subtrees(noise-free clusters). The second phase converts the subtrees into dendrogram. The key feature of our algorithm is it finds noise-free/error-free clusters for a given dataset without using any input parameters. The key feature of the algorithm is it uses both divisive and agglomerative approaches to find optimal Dual similarity noise-free clusters.