Artificial fish swarm optimization for multilayer network learning in classification problems
Nature-Inspired Computing (NIC) has always been a promising tool to enhance neural network learning. Artificial Fish Swarm Algorithm (AFSA) as one of the NIC methods is widely used for optimizing the global searching of ANN.In this study, we applied the AFSA method to improve the Multilayer Perceptr...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Universiti Utara Malaysia Press
2012
|
| Subjects: | |
| Online Access: | https://repo.uum.edu.my/id/eprint/23945/1/JICT%20%2011%202012%2037%2053.pdf |
| _version_ | 1825805018132905984 |
|---|---|
| author | Hasan, Shafaatunnur Tan, Swee Quo Shamsuddin, Siti Mariyam |
| author_facet | Hasan, Shafaatunnur Tan, Swee Quo Shamsuddin, Siti Mariyam |
| author_sort | Hasan, Shafaatunnur |
| collection | UUM |
| description | Nature-Inspired Computing (NIC) has always been a promising tool to enhance neural network learning. Artificial Fish Swarm Algorithm (AFSA) as one of the NIC methods is widely used for optimizing the global searching of ANN.In this study, we applied the AFSA method to improve the Multilayer Perceptron (MLP) learning for promising accuracy in various classification problems.The parameters of AFSA: AFSA prey, AFSA swarm and AFSA follow are implemented on the MLP network for improving the accuracy of various classification datasets from UCI machine learning. The results are compared to other NIC methods, i.e., Particle Swarm Optimization (PSO) and Differential Evolution (DE), in which AFSA gives better accuracy with feasible performance for all datasets. |
| first_indexed | 2024-07-04T06:25:03Z |
| format | Article |
| id | uum-23945 |
| institution | Universiti Utara Malaysia |
| language | English |
| last_indexed | 2024-07-04T06:25:03Z |
| publishDate | 2012 |
| publisher | Universiti Utara Malaysia Press |
| record_format | eprints |
| spelling | uum-239452018-05-06T23:42:29Z https://repo.uum.edu.my/id/eprint/23945/ Artificial fish swarm optimization for multilayer network learning in classification problems Hasan, Shafaatunnur Tan, Swee Quo Shamsuddin, Siti Mariyam QA75 Electronic computers. Computer science Nature-Inspired Computing (NIC) has always been a promising tool to enhance neural network learning. Artificial Fish Swarm Algorithm (AFSA) as one of the NIC methods is widely used for optimizing the global searching of ANN.In this study, we applied the AFSA method to improve the Multilayer Perceptron (MLP) learning for promising accuracy in various classification problems.The parameters of AFSA: AFSA prey, AFSA swarm and AFSA follow are implemented on the MLP network for improving the accuracy of various classification datasets from UCI machine learning. The results are compared to other NIC methods, i.e., Particle Swarm Optimization (PSO) and Differential Evolution (DE), in which AFSA gives better accuracy with feasible performance for all datasets. Universiti Utara Malaysia Press 2012 Article PeerReviewed application/pdf en https://repo.uum.edu.my/id/eprint/23945/1/JICT%20%2011%202012%2037%2053.pdf Hasan, Shafaatunnur and Tan, Swee Quo and Shamsuddin, Siti Mariyam and UNSPECIFIED (2012) Artificial fish swarm optimization for multilayer network learning in classification problems. Journal of Information and Communication Technology, 11. pp. 37-53. ISSN 2180-3862 http://jict.uum.edu.my/index.php/previous-issues/140-journal-of-information-and-communication-technology-jict-vol-11-2012 |
| spellingShingle | QA75 Electronic computers. Computer science Hasan, Shafaatunnur Tan, Swee Quo Shamsuddin, Siti Mariyam Artificial fish swarm optimization for multilayer network learning in classification problems |
| title | Artificial fish swarm optimization for multilayer network learning in classification problems |
| title_full | Artificial fish swarm optimization for multilayer network learning in classification problems |
| title_fullStr | Artificial fish swarm optimization for multilayer network learning in classification problems |
| title_full_unstemmed | Artificial fish swarm optimization for multilayer network learning in classification problems |
| title_short | Artificial fish swarm optimization for multilayer network learning in classification problems |
| title_sort | artificial fish swarm optimization for multilayer network learning in classification problems |
| topic | QA75 Electronic computers. Computer science |
| url | https://repo.uum.edu.my/id/eprint/23945/1/JICT%20%2011%202012%2037%2053.pdf |
| work_keys_str_mv | AT hasanshafaatunnur artificialfishswarmoptimizationformultilayernetworklearninginclassificationproblems AT tansweequo artificialfishswarmoptimizationformultilayernetworklearninginclassificationproblems AT shamsuddinsitimariyam artificialfishswarmoptimizationformultilayernetworklearninginclassificationproblems AT artificialfishswarmoptimizationformultilayernetworklearninginclassificationproblems |