Optimal selection of ensemble classifiers using measures of competence and diversity of base classifiers
In this paper, a new probabilistic model using measures of classifier competence and diversity is proposed. The multiple classifier system (MCS) based on the dynamic ensemble selection scheme was constructed using both developed measures. Two different optimization problems of ensemble selection are...
| Main Authors: | , , |
|---|---|
| Format: | Journal Article |
| Published: |
Elsevier BV
2014
|
| Online Access: | http://hdl.handle.net/20.500.11937/16870 |
| _version_ | 1848749300936343552 |
|---|---|
| author | Lysiak, R. Kurzynski, M. Woloszynski, Tomasz |
| author_facet | Lysiak, R. Kurzynski, M. Woloszynski, Tomasz |
| author_sort | Lysiak, R. |
| building | Curtin Institutional Repository |
| collection | Online Access |
| description | In this paper, a new probabilistic model using measures of classifier competence and diversity is proposed. The multiple classifier system (MCS) based on the dynamic ensemble selection scheme was constructed using both developed measures. Two different optimization problems of ensemble selection are defined and a solution based on the simulated annealing algorithm is presented. The influence of minimum value of competence and diversity in the ensemble on classification performance was investigated. The effectiveness of the proposed dynamic selection methods and the influence of both measures were tested using seven databases taken from the UCI Machine Learning Repository and the StatLib statistical dataset. Two types of ensembles were used: homogeneous or heterogeneous. The results show that the use of diversity positively affects the quality of classification. In addition, cases have been identified in which the use of this measure has the greatest impact on quality. |
| first_indexed | 2025-11-14T07:18:45Z |
| format | Journal Article |
| id | curtin-20.500.11937-16870 |
| institution | Curtin University Malaysia |
| institution_category | Local University |
| last_indexed | 2025-11-14T07:18:45Z |
| publishDate | 2014 |
| publisher | Elsevier BV |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | curtin-20.500.11937-168702017-09-13T15:42:22Z Optimal selection of ensemble classifiers using measures of competence and diversity of base classifiers Lysiak, R. Kurzynski, M. Woloszynski, Tomasz In this paper, a new probabilistic model using measures of classifier competence and diversity is proposed. The multiple classifier system (MCS) based on the dynamic ensemble selection scheme was constructed using both developed measures. Two different optimization problems of ensemble selection are defined and a solution based on the simulated annealing algorithm is presented. The influence of minimum value of competence and diversity in the ensemble on classification performance was investigated. The effectiveness of the proposed dynamic selection methods and the influence of both measures were tested using seven databases taken from the UCI Machine Learning Repository and the StatLib statistical dataset. Two types of ensembles were used: homogeneous or heterogeneous. The results show that the use of diversity positively affects the quality of classification. In addition, cases have been identified in which the use of this measure has the greatest impact on quality. 2014 Journal Article http://hdl.handle.net/20.500.11937/16870 10.1016/j.neucom.2013.01.052 Elsevier BV restricted |
| spellingShingle | Lysiak, R. Kurzynski, M. Woloszynski, Tomasz Optimal selection of ensemble classifiers using measures of competence and diversity of base classifiers |
| title | Optimal selection of ensemble classifiers using measures of competence and diversity of base classifiers |
| title_full | Optimal selection of ensemble classifiers using measures of competence and diversity of base classifiers |
| title_fullStr | Optimal selection of ensemble classifiers using measures of competence and diversity of base classifiers |
| title_full_unstemmed | Optimal selection of ensemble classifiers using measures of competence and diversity of base classifiers |
| title_short | Optimal selection of ensemble classifiers using measures of competence and diversity of base classifiers |
| title_sort | optimal selection of ensemble classifiers using measures of competence and diversity of base classifiers |
| url | http://hdl.handle.net/20.500.11937/16870 |