Ant system and weighted voting method for multiple classifier systems
Combining multiple classifiers is considered as a general solution for classification tasks. However, there are two problems in combining multiple classifiers: constructing a diverse classifier ensemble; and, constructing an appropriate combiner. In this study, an improved multiple classifier combin...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Institute of Advanced Engineering and Science (IAES)
2018
|
| Subjects: | |
| Online Access: | https://repo.uum.edu.my/id/eprint/27868/1/IJECE%208%206%202018%204705%204712.pdf |
| _version_ | 1825805704738373632 |
|---|---|
| author | Husin, Abdullah Ku-Mahamud, Ku Ruhana |
| author_facet | Husin, Abdullah Ku-Mahamud, Ku Ruhana |
| author_sort | Husin, Abdullah |
| collection | UUM |
| description | Combining multiple classifiers is considered as a general solution for classification tasks. However, there are two problems in combining multiple classifiers: constructing a diverse classifier ensemble; and, constructing an appropriate combiner. In this study, an improved multiple classifier combination scheme is propose. A diverse classifier ensemble is constructed by training them with different feature set partitions. The ant system-based algorithm is used to form the optimal feature set partitions. Weighted voting is used to combine the classifiers’ outputs by considering the strength of the classifiers prior to voting. Experiments were carried out using k-NN ensembles on benchmark datasets from the University of California, Irvine, to evaluate the credibility of the proposed method. Experimental results showed that the proposed method has successfully constructed better k-NN ensembles. Further more the proposed method can be used to develop other multiple classifier systems. |
| first_indexed | 2024-07-04T06:36:37Z |
| format | Article |
| id | uum-27868 |
| institution | Universiti Utara Malaysia |
| language | English |
| last_indexed | 2024-07-04T06:36:37Z |
| publishDate | 2018 |
| publisher | Institute of Advanced Engineering and Science (IAES) |
| record_format | eprints |
| spelling | uum-278682020-11-10T06:00:28Z https://repo.uum.edu.my/id/eprint/27868/ Ant system and weighted voting method for multiple classifier systems Husin, Abdullah Ku-Mahamud, Ku Ruhana QA75 Electronic computers. Computer science Combining multiple classifiers is considered as a general solution for classification tasks. However, there are two problems in combining multiple classifiers: constructing a diverse classifier ensemble; and, constructing an appropriate combiner. In this study, an improved multiple classifier combination scheme is propose. A diverse classifier ensemble is constructed by training them with different feature set partitions. The ant system-based algorithm is used to form the optimal feature set partitions. Weighted voting is used to combine the classifiers’ outputs by considering the strength of the classifiers prior to voting. Experiments were carried out using k-NN ensembles on benchmark datasets from the University of California, Irvine, to evaluate the credibility of the proposed method. Experimental results showed that the proposed method has successfully constructed better k-NN ensembles. Further more the proposed method can be used to develop other multiple classifier systems. Institute of Advanced Engineering and Science (IAES) 2018 Article PeerReviewed application/pdf en https://repo.uum.edu.my/id/eprint/27868/1/IJECE%208%206%202018%204705%204712.pdf Husin, Abdullah and Ku-Mahamud, Ku Ruhana (2018) Ant system and weighted voting method for multiple classifier systems. International Journal of Electrical and Computer Engineering (IJECE), 8 (6). pp. 4705-4712. ISSN 2088-8708 http://doi.org/10.11591/ijece.v8i6.pp4705-4712 doi:10.11591/ijece.v8i6.pp4705-4712 doi:10.11591/ijece.v8i6.pp4705-4712 |
| spellingShingle | QA75 Electronic computers. Computer science Husin, Abdullah Ku-Mahamud, Ku Ruhana Ant system and weighted voting method for multiple classifier systems |
| title | Ant system and weighted voting method for multiple classifier systems |
| title_full | Ant system and weighted voting method for multiple classifier systems |
| title_fullStr | Ant system and weighted voting method for multiple classifier systems |
| title_full_unstemmed | Ant system and weighted voting method for multiple classifier systems |
| title_short | Ant system and weighted voting method for multiple classifier systems |
| title_sort | ant system and weighted voting method for multiple classifier systems |
| topic | QA75 Electronic computers. Computer science |
| url | https://repo.uum.edu.my/id/eprint/27868/1/IJECE%208%206%202018%204705%204712.pdf |
| work_keys_str_mv | AT husinabdullah antsystemandweightedvotingmethodformultipleclassifiersystems AT kumahamudkuruhana antsystemandweightedvotingmethodformultipleclassifiersystems |