TY - JOUR

T1 - Model and Method for Constructing a Heterogeneous Cluster Ensemble

AU - Berikov, V. B.

N1 - Публикация для корректировки.

PY - 2022

Y1 - 2022

N2 - We consider the problem of data clustering using a heterogeneous ensemble with the use ofa co-association matrix. A probabilistic model is stated that takes into account the correlation ofevaluation functions with the help of which relationships are found between the characteristics ofthe ensemble and the quality indicators of the final solution. An expression for the optimalweights of basic algorithms for which the upper bound on the clustering error probability estimateis minimal is found. An experimental study of the proposed method has been carried out showingthe method to be advantageous over a number of similar methods.

AB - We consider the problem of data clustering using a heterogeneous ensemble with the use ofa co-association matrix. A probabilistic model is stated that takes into account the correlation ofevaluation functions with the help of which relationships are found between the characteristics ofthe ensemble and the quality indicators of the final solution. An expression for the optimalweights of basic algorithms for which the upper bound on the clustering error probability estimateis minimal is found. An experimental study of the proposed method has been carried out showingthe method to be advantageous over a number of similar methods.

KW - cluster analysis

KW - cluster ensemble model

KW - co-association matrix

KW - ensemble of algorithms

KW - optimal weights of algorithms

UR - https://www.mendeley.com/catalogue/070a757b-7f86-30f6-aaf3-c93b98bd6063/

U2 - 10.1134/S00051179220120086

DO - 10.1134/S00051179220120086

M3 - Article

VL - 83

SP - 1944

EP - 1958

JO - Automation and Remote Control

JF - Automation and Remote Control

SN - 0005-1179

IS - 12

ER -