Density-based spatial clustering of applications with noise (DBSCAN)is a well-known data clustering algorithm that is commonly used in data mining and machine learning. If you are interested to know its usage, this document helps.
Based on a set of points (let’s think in a bidimensional space as exemplified in the figure), DBSCAN groups together points that are close to each other based on a distance measurement (usually Euclidean distance) and a minimum number of points. It also marks as outliers the points that are in low-density regions.
What’s nice about DBSCAN is that you don’t have to specify the number of clusters to use it. All you need is a function to calculate the distance between values and some guidance for what amount of distance is considered “close”
Clusters formed are arbitrary in shape contrary to vanilla k-means which forms only convex shape
DBScan clustering efficiently handles outliers and noisy datasets.
DBScan algorithm is good for anomaly detection data. It locates regions of high density that are separated from one another by regions of low density.
DBSCan Clustering can not efficiently handle high dimensional datasets
DBScan clustering does not work very well for data points with varying density
??
This colab gives example where DBSCAN is able to cluster example non-convex shape where k-means and hierarchical models couldn't
https://en.wikipedia.org/wiki/DBSCAN
https://www.kdnuggets.com/2020/04/dbscan-clustering-algorithm-machine-learning.html
https://towardsdatascience.com/how-dbscan-works-and-why-should-i-use-it-443b4a191c80
https://www.geeksforgeeks.org/difference-between-k-means-and-dbscan-clustering/
https://images.app.goo.gl/Sz5t5iw2xdpBfybD8
https://www.researchgate.net/figure/Description-of-the-proposed-algorithm-ANN-artificial-neural-network-DBSCAN_fig3_328066898
https://images.app.goo.gl/RmFvgRswY7BFgBae7
https://colab.research.google.com/drive/1yYsmQV_JWJaGNd1M6XjOqWPKj1PufT-I?usp=sharing
https://www.analyticsvidhya.com/blog/2020/09/how-dbscan-clustering-works/
https://youtu.be/AxARUMZh0sk?t=1645