Density-Based Spatial Clustering of Applications with Noise (DBSCAN) is a density-based clustering algorithm, proposed by Martin Ester et al., 1996. The algorithm finds neighbors of data points, within a circle of radius ε, and adds them into same cluster. For any neighbor point, which its ε-neighborhood contains a predefined number of points, the cluster is expanded to contain its neighbors, as well. However, for the unallocated points, if the number of points in the neighborhood is less than predefined threshold, the point is considered to be a noise. So DBSCAN can discriminate the normal and noisy data, too. For more information on DBSCAN, you can refer to the related article on Wikipedia, in this links.
In this post, we are going to share with you, the open-source MATLAB implementation of DBSCAN, which is ready to use in research projects and real-world applications. If you are familiar with MATLAB programming language, you will find easy, to use the provided source codes for DBSCAN.
A sample output of this algorithm follows. In the figure, you can see that DBSCAN successfully determined the data clusters, as well as noisy points. The parameters of algorithm, is show above the figure.
