Density Based Spatial Clustering Application with Noise by Varying Densities

Abstract

Cluster algorithms are used for grouping up of similar points to form a cluster. It has seen mostly in Machine Learning algorithms. The most popular density-based algorithm is DBSCAN. DBSCAN can find the clusters, irrespective of its shapes and sizes of a cluster. DBSCAN algorithm can easily detect the noise in a clustering dataset. In the proposed algorithm we developed a model based on the existing dbscan algorithm. In the developed algorithm we focus mainly on the epsilon parameter value. Whenever the dbscan algorithm fails to form a cluster we increase the epsilon value by half of its original size. We repeat this step until a cluster is formed. Whenever a cluster is newly formed we change existing epsilon parameter value by adding the 10 percent of the previous used epsilon parameter value. We use epsilon for varying the density of a cluster. So, we can use the dbscan algorithm with the varying density values for developing a cluster. We applied this algorithm on the various datasets.