05-04-2019 | Theoretical advances
DBSCAN
-like clustering method for various data densities
Published in: Pattern Analysis and Applications | Issue 2/2020
Log inActivate our intelligent search to find suitable subject content or patents.
Select sections of text to find matching patents with Artificial Intelligence. powered by
Select sections of text to find additional relevant content using AI-assisted search. powered by
Abstract
DBSCAN
algorithm, which recognizes clusters with various data densities in a given set of data points \({\mathcal {A}}=\{a^i\in {\mathbb {R}}^n:i=1,\dots ,m\}\). First, we define the parameter \(MinPts=\lfloor \ln |{\mathcal {A}}|\rfloor\) and after that, by using a standard procedure from DBSCAN
algorithm, for each \(a\in {\mathcal {A}}\) we determine radius \(\epsilon _a\) of the circle containing MinPts elements from the set \({\mathcal {A}}\). We group the set of all these radii into the most appropriate number (t) of clusters by using Least Squares distance-like function applying SymDIRECT
or SepDIRECT
algorithm. In that way, we obtain parameters \(\epsilon _1>\dots >\epsilon _t\). Furthermore, for parameters \(\{MinPts,\epsilon _1\}\) we construct a partition starting with one cluster and then add new clusters for as long as the isolated groups of at least MinPts data points in some circle with radius \(\epsilon _1\) exist. We follow a similar procedure for other parameters \(\epsilon _2,\dots ,\epsilon _t\). After the implementation of the algorithm, a larger number of clusters appear than can be expected in the optimal partition. Along with defined criteria, some of them are merged by applying a merging process for which a detailed algorithm has been written. Compared to the standard DBSCAN
algorithm, we show an obvious advantage for the case of data with various densities.