Self-adaption grey DBSCAN clustering
This work addresses the challenge of parameter tuning in clustering for data mining applications, but it appears incremental as it builds upon existing DBSCAN methods with grey relational techniques.
The paper tackles the problem of parameter selection in DBSCAN clustering by proposing a self-adaption grey DBSCAN algorithm that uses a grey relational matrix for noise identification and automatic parameter tuning, resulting in demonstrated advantages over state-of-the-art methods on several datasets.
Clustering analysis, a classical issue in data mining, is widely used in various research areas. This article aims at proposing a self-adaption grey DBSCAN clustering (SAG-DBSCAN) algorithm. First, the grey relational matrix is used to obtain the grey local density indicator, and then this indicator is applied to make self-adapting noise identification for obtaining a dense subset of clustering dataset, finally, the DBSCAN which automatically selects parameters is utilized to cluster the dense subset. Several frequently-used datasets were used to demonstrate the performance and effectiveness of the proposed clustering algorithm and to compare the results with those of other state-of-the-art algorithms. The comprehensive comparisons indicate that our method has advantages over other compared methods.