January 24, 2018, Dr. Piotr Lasek, Density-Based Clustering with Constraints
Abstract: Clustering is one of the most important techniques in both artificial intelligence and data mining. It is used to identify unknown yet interesting and useful patterns or trends in datasets. In recent years a new branch of clustering algorithms has emerged, namely clustering algorithms with constraints. By means of the constraints, it is possible to incorporate background knowledge into clustering algorithms that can lead to better accuracy of clustering results and potentially better performance. Over the last few years, a number of clustering algorithms employing different types of constraints have been proposed and most of them extend existing partitioning and hierarchical approaches. Among density-based methods using constraints, algorithms such as C-DBSCAN, DBCCOM, DB-CluC were proposed. In this presentation, we will focus on instance level constraints called and two density-based algorithms ic-NBC and ic-DBSCAN implemented on top of the well known density-based algorithms.