A
Artur Starczewski
Researcher at Częstochowa University of Technology
Publications - 17
Citations - 181
Artur Starczewski is an academic researcher from Częstochowa University of Technology. The author has contributed to research in topics: Cluster analysis & Index (economics). The author has an hindex of 5, co-authored 17 publications receiving 123 citations.
Papers
More filters
Journal ArticleDOI
A new validity index for crisp clusters
TL;DR: A new cluster validity index, called the STR index, is defined as the product of two components which determine changes of compactness and separability of clusters during a clustering process, and the maximum value identifies the best clustering scheme.
Book ChapterDOI
Performance Evaluation of the Silhouette Index
Artur Starczewski,Adam Krzyżak +1 more
TL;DR: This article provides the performance evaluation of the Silhouette index, which is based on the so called silhouette width, and two popular hierarchical methods were applied, that is, the complete-linkage and the single- linkage algorithm.
Journal ArticleDOI
A New Method for Automatic Determining of the DBSCAN Parameters
TL;DR: A new method that determines the right values of the parameters for different kinds of clusters is proposed that uses detection of sharp distance increases generated by a function which computes a distance between each element of a dataset and its k-th nearest neighbor.
Book ChapterDOI
Determining the Eps Parameter of the DBSCAN Algorithm
Artur Starczewski,Andrzej Cader +1 more
TL;DR: A new method is proposed to determine the value of eps based on an analysis of the sorted values of the distance function, which has been demonstrated for several different datasets.
Book ChapterDOI
A Modification of the Silhouette Index for the Improvement of Cluster Validity Assessment
Artur Starczewski,Adam Krzyżak +1 more
TL;DR: A modification of the well-known Silhouette validity index, which involves using an additional component in the original index, is proposed and its maximum value identifies the best clustering scheme.