Open Access Open Access  Restricted Access Subscription Access
Open Access Open Access Open Access  Restricted Access Restricted Access Subscription Access

Calculation of Mean Data on Gini Relationship by Data Mining Method


Affiliations
1 Department of Computer Engineering, Yasouj Branch, Islamic Azad University, Yasouj, Iran, Islamic Republic of
     

   Subscribe/Renew Journal


Data clustering is one of the main tasks of data mining which have to show the hidden patterns in unlabeled data. Due to inherent complexity and weakness of basic clusterings, a considerable amount of research has nowadays turned to ensemble based clusterings. Because of effectiveness of weighting in classifier ensemble it is expected that the usage of weighting can be effective in clustering ensemble. In classifier ensemble, the vote of each classifier is related to its accuracy. There, the accuracy of each classifier is approximated by testing the classifier over a test data set, but the accuracy of clustering can't be approximated at all; because it lacks supervision and also a well-known measure for estimation of accuracy. Here, research test the leukemia data using the Gini relation on meta-hierarchical algorithms and use the data mining relation to evaluate the accuracy of the algorithms over other algorithms.


Keywords

Gini Relation, Data Mining, Cluster Algorithm, Ensemble Based Clusterings.
User
Subscription Login to verify subscription
Notifications
Font Size

Abstract Views: 245

PDF Views: 1




  • Calculation of Mean Data on Gini Relationship by Data Mining Method

Abstract Views: 245  |  PDF Views: 1

Authors

Maysam Toghraee
Department of Computer Engineering, Yasouj Branch, Islamic Azad University, Yasouj, Iran, Islamic Republic of

Abstract


Data clustering is one of the main tasks of data mining which have to show the hidden patterns in unlabeled data. Due to inherent complexity and weakness of basic clusterings, a considerable amount of research has nowadays turned to ensemble based clusterings. Because of effectiveness of weighting in classifier ensemble it is expected that the usage of weighting can be effective in clustering ensemble. In classifier ensemble, the vote of each classifier is related to its accuracy. There, the accuracy of each classifier is approximated by testing the classifier over a test data set, but the accuracy of clustering can't be approximated at all; because it lacks supervision and also a well-known measure for estimation of accuracy. Here, research test the leukemia data using the Gini relation on meta-hierarchical algorithms and use the data mining relation to evaluate the accuracy of the algorithms over other algorithms.


Keywords


Gini Relation, Data Mining, Cluster Algorithm, Ensemble Based Clusterings.