Incremental Clustering with Special Emphasis on Spatio Temporal Data

Abstract

Today in this age where we talk about terabytes and petabytes of data generation each and every day, there is a need for tools which help in the analysis and processing of this data. Clustering is a type of unsupervised learning in which clusters of different types can be created using various algorithms such as K-Means, DBSCAN, OPTICS, Nearest-neighbor chain and many others. It is a process of creating different partitions to a set of data (or objects) into a set of meaningful sub-classes, called clusters. Density-Based Spatial Clustering of Applications with Noise(DBSCAN) is a density based clustering algorithm used for data clustering.

This algorithm will be used to a special kind of dataset ie spatio-temporal dataset. Here these datasets are used to form clusters and then incremental clustering is performed on them which eventually will add to reducing the time complexity.