A density-based clustering algorithm and experiments on student dataset with noises using Rough set theory
Bidipto Chakraborty, Kunal Chakma, Anjan Mukherjee · 2016
ST-DBSCAN is an extension of the traditional density based clustering algorithm DBSCAN. This algorithm is proposed for clustering spatio-temporal datasets. Spatio-temporal data refers to data which is stored as temporal slices of the spatial dataset. Here the spatial part of data identifies the location in data space and the temporal part of data represents the state in time. ST-DBSCAN can cluster data based on their spatial and temporal attributes and assigns data points to different clusters. ST-DBSCAN finds the clusters as crisp set. Since the crisp sets have a well-defined boundary, it becomes very difficult to find the accurate clusters. Our proposed algorithm, Rough-ST-DBSCAN, clusters data points as Rough Sets. Rough Sets are formal approximations of Crisp Sets in terms of a pair of sets which give the lower and the upper approximation of the original set. The lower approximation will be represented by a cluster that will contain the data points that must belong to the cluster and the upper approximation will be represented by a cluster boundary that will contain the data points that may belong to the cluster. So this proposed Rough-ST-DBSCAN algorithm can cluster data points based on their spatial and temporal density and also can determine the type of belongingness to a specific cluster.