A measure of competence based on random classification for dynamic ensemble selection
In this paper, a measure of competence based on random classification (MCR) for classifier ensembles is presented. The measure selects dynamically (i.e. for each test example) a subset of classifiers from the ensemble that perform better than a random classifier. Therefore, weak (incompetent) classi...
| Main Authors: | , , , |
|---|---|
| Format: | Journal Article |
| Published: |
Elsevier
2012
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/20.500.11937/36540 |
| _version_ | 1848754798623457280 |
|---|---|
| author | Woloszynski, Tomasz Kurzynski, M. Podsiadlo, Pawel Stachowiak, Gwidon |
| author_facet | Woloszynski, Tomasz Kurzynski, M. Podsiadlo, Pawel Stachowiak, Gwidon |
| author_sort | Woloszynski, Tomasz |
| building | Curtin Institutional Repository |
| collection | Online Access |
| description | In this paper, a measure of competence based on random classification (MCR) for classifier ensembles is presented. The measure selects dynamically (i.e. for each test example) a subset of classifiers from the ensemble that perform better than a random classifier. Therefore, weak (incompetent) classifiers that would adversely affect the performance of a classification system are eliminated. When all classifiers in the ensemble are evaluated as incompetent, the classification accuracy of the system can be increased by using the random classifier instead. Theoretical justification for using the measure with the majority voting rule is given. Two MCR based systems were developed and their performance was compared against six multiple classifier systems using data sets taken from the UCI Machine Learning Repository and Ludmila Kuncheva Collection. The systems developed had typically the highest classification accuracies regardless of the ensemble type used (homogeneous or heterogeneous). |
| first_indexed | 2025-11-14T08:46:08Z |
| format | Journal Article |
| id | curtin-20.500.11937-36540 |
| institution | Curtin University Malaysia |
| institution_category | Local University |
| last_indexed | 2025-11-14T08:46:08Z |
| publishDate | 2012 |
| publisher | Elsevier |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | curtin-20.500.11937-365402017-09-13T15:28:25Z A measure of competence based on random classification for dynamic ensemble selection Woloszynski, Tomasz Kurzynski, M. Podsiadlo, Pawel Stachowiak, Gwidon Random classification Competence measure Multiple classifier system Dynamic ensemble selection In this paper, a measure of competence based on random classification (MCR) for classifier ensembles is presented. The measure selects dynamically (i.e. for each test example) a subset of classifiers from the ensemble that perform better than a random classifier. Therefore, weak (incompetent) classifiers that would adversely affect the performance of a classification system are eliminated. When all classifiers in the ensemble are evaluated as incompetent, the classification accuracy of the system can be increased by using the random classifier instead. Theoretical justification for using the measure with the majority voting rule is given. Two MCR based systems were developed and their performance was compared against six multiple classifier systems using data sets taken from the UCI Machine Learning Repository and Ludmila Kuncheva Collection. The systems developed had typically the highest classification accuracies regardless of the ensemble type used (homogeneous or heterogeneous). 2012 Journal Article http://hdl.handle.net/20.500.11937/36540 10.1016/j.inffus.2011.03.007 Elsevier restricted |
| spellingShingle | Random classification Competence measure Multiple classifier system Dynamic ensemble selection Woloszynski, Tomasz Kurzynski, M. Podsiadlo, Pawel Stachowiak, Gwidon A measure of competence based on random classification for dynamic ensemble selection |
| title | A measure of competence based on random classification for dynamic ensemble selection |
| title_full | A measure of competence based on random classification for dynamic ensemble selection |
| title_fullStr | A measure of competence based on random classification for dynamic ensemble selection |
| title_full_unstemmed | A measure of competence based on random classification for dynamic ensemble selection |
| title_short | A measure of competence based on random classification for dynamic ensemble selection |
| title_sort | measure of competence based on random classification for dynamic ensemble selection |
| topic | Random classification Competence measure Multiple classifier system Dynamic ensemble selection |
| url | http://hdl.handle.net/20.500.11937/36540 |