Two step density-based object-inductive clustering algorithm

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F44555601%3A13440%2F19%3A43894894" target="_blank" >RIV/44555601:13440/19:43894894 - isvavai.cz</a>

Result on the web

<a href="http://ceur-ws.org/Vol-2386/paper10.pdf" target="_blank" >http://ceur-ws.org/Vol-2386/paper10.pdf</a>

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Two step density-based object-inductive clustering algorithm

Original language description

The article includes the results of study into the practical implementation of two-step DBSCAN and OPTICS clustering algorithms in the field of objective clustering of inductive technologies. The architecture of the objective clustering technology was developed founded on the two-step clustering algorithm DBSCAN and OPTICS. The accomplishment of the technology includes the simultaneous data&apos;s clustering on two subsets of the same power by the DBSCAN algorithm, which involve the same number of pairwise objects similar to each other with the subsequent correction of the received clusters by the OPTICS algorithm. The finding the algorithm&apos;s optimal parameters was carried out based on the clustering quality criterion&apos;s maximum value of a complex balance, which is rated as the geometric average of the Harrington desirability indices for clustering quality criteria (internal and external).

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

—

Continuities

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Publication year

2019

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

CEUR Workshop Proceedings

ISBN

—

ISSN

1613-0073

e-ISSN

—

Number of pages

19

Pages from-to

117-135

Publisher name

CEUR-WS

Place of publication

Paris

Event location

Shatsk

Event date

Jun 2, 2019

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—