Adapting and enhancing mussels wandering optimization algorithm for supervised training of neural networks

Membangunkan kaedah latihan yang cekap untuk Rangkaian Neural (NN) dalam mencapai kejituan yang tinggi adalah satu cabaran. Tambahan pula, latihan NN masih lagi memerlukan masa yang lama. Algoritma Pengoptimuman Perayauan Kupang (MWO) ialah satu algoritma pengoptimuman metaheuristik yang baru dan...

Full description

Saved in:
Bibliographic Details
Main Author: Abusnaina, Ahmed A. A.
Format: Thesis
Language:English
Published: 2015
Subjects:
Online Access:http://eprints.usm.my/35580/1/PhD_Thesis_Abusnaina_Adapting_and__Enhancing_MWO_Algorithm_for_Supervised_Trainnig_of_NN_%281%29.pdf
http://eprints.usm.my/35580/
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Universiti Sains Malaysia
Language: English
id my.usm.eprints.35580
record_format eprints
spelling my.usm.eprints.35580 http://eprints.usm.my/35580/ Adapting and enhancing mussels wandering optimization algorithm for supervised training of neural networks Abusnaina, Ahmed A. A. QA75.5-76.95 Electronic computers. Computer science Membangunkan kaedah latihan yang cekap untuk Rangkaian Neural (NN) dalam mencapai kejituan yang tinggi adalah satu cabaran. Tambahan pula, latihan NN masih lagi memerlukan masa yang lama. Algoritma Pengoptimuman Perayauan Kupang (MWO) ialah satu algoritma pengoptimuman metaheuristik yang baru dan telah diinspirasikan secara ekologi oleh tingkah laku pegerakan kupang. Objektif utama bagi tesis ini adalah untuk mencapai prestasi yang terbaik dalam penumpuan masa latihan dan ketepatan pengelasan untuk pengelasan corak dengan mengusulkan kaedah latihan penyeliaan yang baru untuk Rangkaian Neural Buatan (ANN) yang berasaskan penggunaan algoritma MWO. Mempertingkatkan prestasi, terutamanya dalam kejituan pengelasan yang membawa kepada perkenalan versi MWO yang telah di adaptasi; dikenali sebagai algoritma Peningkatan-MWO (E-MWO). Developing efficient training method for Neural Networks (NN) in terms of high accuracy is a challenge. In addition, training NN is still highly-time consuming. The Mussels Wandering Optimization (MWO) is a recent metaheuristic optimization algorithm inspired ecologically by mussels movement behavior. The major objective of this thesis is to achieve better performance in terms of convergence training time and classification accuracy for pattern classification by proposing new supervised training methods for Artificial Neural Networks (ANN) based on the MWO algorithm. Increasing the performance, especially in terms of classification accuracy led to an adapted version of the MWO; known as Enhanced-MWO (E-MWO) algorithm. 2015-04 Thesis NonPeerReviewed application/pdf en http://eprints.usm.my/35580/1/PhD_Thesis_Abusnaina_Adapting_and__Enhancing_MWO_Algorithm_for_Supervised_Trainnig_of_NN_%281%29.pdf Abusnaina, Ahmed A. A. (2015) Adapting and enhancing mussels wandering optimization algorithm for supervised training of neural networks. PhD thesis, Universiti Sains Malaysia.
institution Universiti Sains Malaysia
building Hamzah Sendut Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Sains Malaysia
content_source USM Institutional Repository
url_provider http://eprints.usm.my/
language English
topic QA75.5-76.95 Electronic computers. Computer science
spellingShingle QA75.5-76.95 Electronic computers. Computer science
Abusnaina, Ahmed A. A.
Adapting and enhancing mussels wandering optimization algorithm for supervised training of neural networks
description Membangunkan kaedah latihan yang cekap untuk Rangkaian Neural (NN) dalam mencapai kejituan yang tinggi adalah satu cabaran. Tambahan pula, latihan NN masih lagi memerlukan masa yang lama. Algoritma Pengoptimuman Perayauan Kupang (MWO) ialah satu algoritma pengoptimuman metaheuristik yang baru dan telah diinspirasikan secara ekologi oleh tingkah laku pegerakan kupang. Objektif utama bagi tesis ini adalah untuk mencapai prestasi yang terbaik dalam penumpuan masa latihan dan ketepatan pengelasan untuk pengelasan corak dengan mengusulkan kaedah latihan penyeliaan yang baru untuk Rangkaian Neural Buatan (ANN) yang berasaskan penggunaan algoritma MWO. Mempertingkatkan prestasi, terutamanya dalam kejituan pengelasan yang membawa kepada perkenalan versi MWO yang telah di adaptasi; dikenali sebagai algoritma Peningkatan-MWO (E-MWO). Developing efficient training method for Neural Networks (NN) in terms of high accuracy is a challenge. In addition, training NN is still highly-time consuming. The Mussels Wandering Optimization (MWO) is a recent metaheuristic optimization algorithm inspired ecologically by mussels movement behavior. The major objective of this thesis is to achieve better performance in terms of convergence training time and classification accuracy for pattern classification by proposing new supervised training methods for Artificial Neural Networks (ANN) based on the MWO algorithm. Increasing the performance, especially in terms of classification accuracy led to an adapted version of the MWO; known as Enhanced-MWO (E-MWO) algorithm.
format Thesis
author Abusnaina, Ahmed A. A.
author_facet Abusnaina, Ahmed A. A.
author_sort Abusnaina, Ahmed A. A.
title Adapting and enhancing mussels wandering optimization algorithm for supervised training of neural networks
title_short Adapting and enhancing mussels wandering optimization algorithm for supervised training of neural networks
title_full Adapting and enhancing mussels wandering optimization algorithm for supervised training of neural networks
title_fullStr Adapting and enhancing mussels wandering optimization algorithm for supervised training of neural networks
title_full_unstemmed Adapting and enhancing mussels wandering optimization algorithm for supervised training of neural networks
title_sort adapting and enhancing mussels wandering optimization algorithm for supervised training of neural networks
publishDate 2015
url http://eprints.usm.my/35580/1/PhD_Thesis_Abusnaina_Adapting_and__Enhancing_MWO_Algorithm_for_Supervised_Trainnig_of_NN_%281%29.pdf
http://eprints.usm.my/35580/
_version_ 1643708537278300160