Cover Image

A flexible enhanced fuzzy min-max neural network for pattern classification

In this paper, the existing enhanced fuzzy min–max (EFMM) neural network is improved with a flexible learning procedure for undertaking pattern classification tasks. Four new contributions are introduced. Firstly, a new training strategy is proposed for avoiding the generation of unnecessary overlap...

Full description

Saved in:
Bibliographic Details
Main Authors: Alhroob, Essam, Mohammed, Mohammed Falah, Al Sayaydeh, Osama Nayel, Hujainah, Fadhl, Ngahzaifa, Ab Ghani, Lim, Chee Peng
Format: Article
Language:English
English
Published: Elsevier 2024
Subjects:
QA75 Electronic computers. Computer science
Online Access:http://umpir.ump.edu.my/id/eprint/41060/1/A%20flexible%20enhanced%20fuzzy%20min-max%20neural%20network_ABST.pdf
http://umpir.ump.edu.my/id/eprint/41060/2/A%20flexible%20enhanced%20fuzzy%20min-max%20neural%20network%20for%20pattern%20classification.pdf
http://umpir.ump.edu.my/id/eprint/41060/
https://doi.org/10.1016/j.eswa.2024.124030
https://doi.org/10.1016/j.eswa.2024.124030
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.ump.umpir.41060
record_format eprints
spelling my.ump.umpir.410602024-04-24T06:20:24Z http://umpir.ump.edu.my/id/eprint/41060/ A flexible enhanced fuzzy min-max neural network for pattern classification Alhroob, Essam Mohammed, Mohammed Falah Al Sayaydeh, Osama Nayel Hujainah, Fadhl Ngahzaifa, Ab Ghani Lim, Chee Peng QA75 Electronic computers. Computer science In this paper, the existing enhanced fuzzy min–max (EFMM) neural network is improved with a flexible learning procedure for undertaking pattern classification tasks. Four new contributions are introduced. Firstly, a new training strategy is proposed for avoiding the generation of unnecessary overlapped regions between hyperboxes of different classes. The learning phase is simplified by eliminating the contraction procedure. Secondly, a new flexible expansion procedure is introduced. It eliminates the use of a user-defined parameter (expansion coefficient) to determine the hyperbox sizes. Thirdly, a new overlap test rule is applied during the test phase to identify the containment cases and activate the contraction procedure (if necessary). Fourthly, a new contraction procedure is formulated to overcome the containment cases and avoid the data distortion problem. Both the third and fourth contributions are important for preventing the catastrophic forgetting issue and supporting the stability-plasticity principle pertaining to online learning. The performance of the proposed model is evaluated with benchmark data sets. The results demonstrate its efficiency in handling pattern classification tasks, outperforming other related models in online learning environments. Elsevier 2024 Article PeerReviewed pdf en http://umpir.ump.edu.my/id/eprint/41060/1/A%20flexible%20enhanced%20fuzzy%20min-max%20neural%20network_ABST.pdf pdf en http://umpir.ump.edu.my/id/eprint/41060/2/A%20flexible%20enhanced%20fuzzy%20min-max%20neural%20network%20for%20pattern%20classification.pdf Alhroob, Essam and Mohammed, Mohammed Falah and Al Sayaydeh, Osama Nayel and Hujainah, Fadhl and Ngahzaifa, Ab Ghani and Lim, Chee Peng (2024) A flexible enhanced fuzzy min-max neural network for pattern classification. Expert Systems with Applications, 251 (124030). pp. 1-13. ISSN 0957-4174. (Published) https://doi.org/10.1016/j.eswa.2024.124030 https://doi.org/10.1016/j.eswa.2024.124030
institution Universiti Malaysia Pahang Al-Sultan Abdullah
building UMPSA Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Malaysia Pahang Al-Sultan Abdullah
content_source UMPSA Institutional Repository
url_provider http://umpir.ump.edu.my/
language English
English
topic QA75 Electronic computers. Computer science
spellingShingle QA75 Electronic computers. Computer science
Alhroob, Essam
Mohammed, Mohammed Falah
Al Sayaydeh, Osama Nayel
Hujainah, Fadhl
Ngahzaifa, Ab Ghani
Lim, Chee Peng
A flexible enhanced fuzzy min-max neural network for pattern classification
description In this paper, the existing enhanced fuzzy min–max (EFMM) neural network is improved with a flexible learning procedure for undertaking pattern classification tasks. Four new contributions are introduced. Firstly, a new training strategy is proposed for avoiding the generation of unnecessary overlapped regions between hyperboxes of different classes. The learning phase is simplified by eliminating the contraction procedure. Secondly, a new flexible expansion procedure is introduced. It eliminates the use of a user-defined parameter (expansion coefficient) to determine the hyperbox sizes. Thirdly, a new overlap test rule is applied during the test phase to identify the containment cases and activate the contraction procedure (if necessary). Fourthly, a new contraction procedure is formulated to overcome the containment cases and avoid the data distortion problem. Both the third and fourth contributions are important for preventing the catastrophic forgetting issue and supporting the stability-plasticity principle pertaining to online learning. The performance of the proposed model is evaluated with benchmark data sets. The results demonstrate its efficiency in handling pattern classification tasks, outperforming other related models in online learning environments.
format Article
author Alhroob, Essam
Mohammed, Mohammed Falah
Al Sayaydeh, Osama Nayel
Hujainah, Fadhl
Ngahzaifa, Ab Ghani
Lim, Chee Peng
author_facet Alhroob, Essam
Mohammed, Mohammed Falah
Al Sayaydeh, Osama Nayel
Hujainah, Fadhl
Ngahzaifa, Ab Ghani
Lim, Chee Peng
author_sort Alhroob, Essam
title A flexible enhanced fuzzy min-max neural network for pattern classification
title_short A flexible enhanced fuzzy min-max neural network for pattern classification
title_full A flexible enhanced fuzzy min-max neural network for pattern classification
title_fullStr A flexible enhanced fuzzy min-max neural network for pattern classification
title_full_unstemmed A flexible enhanced fuzzy min-max neural network for pattern classification
title_sort flexible enhanced fuzzy min-max neural network for pattern classification
publisher Elsevier
publishDate 2024
url http://umpir.ump.edu.my/id/eprint/41060/1/A%20flexible%20enhanced%20fuzzy%20min-max%20neural%20network_ABST.pdf
http://umpir.ump.edu.my/id/eprint/41060/2/A%20flexible%20enhanced%20fuzzy%20min-max%20neural%20network%20for%20pattern%20classification.pdf
http://umpir.ump.edu.my/id/eprint/41060/
https://doi.org/10.1016/j.eswa.2024.124030
https://doi.org/10.1016/j.eswa.2024.124030
_version_ 1822924291705929728
score 13.235362

Similar Items