Hybridised Intelligent Dynamic Model of 3-Satisfiability Fuzzy Logic Hopfield Neural Network
This study presents a new way of increasing 3SAT logic programming’s efficiency in the Hopfield network. A new model of merging fuzzy logic with 3SAT in the Hopfield network is presented called HNN-3SATFuzzy. The hybridised dynamic model can avoid locally minimal solutions and lessen the computing...
Saved in:
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
UPM Press
2023
|
Subjects: | |
Online Access: | http://ir.unimas.my/id/eprint/44793/1/Hybridised%20Intelligent.pdf http://ir.unimas.my/id/eprint/44793/ http://www.pertanika.upm.edu.my/pjst/browse/regular-issue?article=JST-3777-2022 https://doi.org/10.47836/pjst.31.4.06 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
my.unimas.ir.44793 |
---|---|
record_format |
eprints |
spelling |
my.unimas.ir.447932024-05-20T01:32:23Z http://ir.unimas.my/id/eprint/44793/ Hybridised Intelligent Dynamic Model of 3-Satisfiability Fuzzy Logic Hopfield Neural Network Farah Liyana, Azizan Saratha, Sathasivam Majid Khan, Majahar Ali QA Mathematics This study presents a new way of increasing 3SAT logic programming’s efficiency in the Hopfield network. A new model of merging fuzzy logic with 3SAT in the Hopfield network is presented called HNN-3SATFuzzy. The hybridised dynamic model can avoid locally minimal solutions and lessen the computing burden by utilising fuzzification and defuzzification techniques in fuzzy logic. In addressing the 3SAT issue, the proposed hybrid approach can select neuron states between zero and one. Aside from that, unsatisfied neuron clauses will be changed using the alpha-cut method as a defuzzifier step until the correct neuron state is determined. The defuzzification process is a mapping stage that converts a fuzzy value into a crisp output. The corrected neuron state using alpha-cut in the defuzzification stage is either sharpening up to one or sharpening down to zero. A simulated data collection was utilised to evaluate the hybrid techniques’ performance. In the training phase, the network for HNN-3SATFuzzy was weighed using RMSE, SSE, MAE and MAPE metrics. The energy analysis also considers the ratio of global minima and processing period to assess its robustness. The findings are significant because this model considerably impacts Hopfield networks’ capacity to handle 3SAT problems with less complexity and speed. The new information and ideas will aid in developing innovative ways to gather knowledge for future research in logic programming. Furthermore, the breakthrough in dynamic learning is considered a significant step forward in neuro-symbolic integration. UPM Press 2023 Article PeerReviewed text en http://ir.unimas.my/id/eprint/44793/1/Hybridised%20Intelligent.pdf Farah Liyana, Azizan and Saratha, Sathasivam and Majid Khan, Majahar Ali (2023) Hybridised Intelligent Dynamic Model of 3-Satisfiability Fuzzy Logic Hopfield Neural Network. Pertanika Journal of Science & Technology, 31 (4). pp. 1695-1716. ISSN 2231-8526 http://www.pertanika.upm.edu.my/pjst/browse/regular-issue?article=JST-3777-2022 https://doi.org/10.47836/pjst.31.4.06 |
institution |
Universiti Malaysia Sarawak |
building |
Centre for Academic Information Services (CAIS) |
collection |
Institutional Repository |
continent |
Asia |
country |
Malaysia |
content_provider |
Universiti Malaysia Sarawak |
content_source |
UNIMAS Institutional Repository |
url_provider |
http://ir.unimas.my/ |
language |
English |
topic |
QA Mathematics |
spellingShingle |
QA Mathematics Farah Liyana, Azizan Saratha, Sathasivam Majid Khan, Majahar Ali Hybridised Intelligent Dynamic Model of 3-Satisfiability Fuzzy Logic Hopfield Neural Network |
description |
This study presents a new way of increasing 3SAT logic programming’s efficiency in the Hopfield network. A new model of merging fuzzy logic with 3SAT in the Hopfield
network is presented called HNN-3SATFuzzy. The hybridised dynamic model can avoid locally minimal solutions and lessen the computing burden by utilising fuzzification and
defuzzification techniques in fuzzy logic. In addressing the 3SAT issue, the proposed hybrid approach can select neuron states between zero and one. Aside from that, unsatisfied
neuron clauses will be changed using the alpha-cut method as a defuzzifier step until the correct neuron state is determined. The defuzzification process is a mapping stage that converts a fuzzy value into a crisp output. The corrected neuron state using alpha-cut in the defuzzification stage is either sharpening up to one or sharpening down to zero. A simulated data collection was utilised to evaluate the hybrid techniques’ performance. In
the training phase, the network for HNN-3SATFuzzy was weighed using RMSE, SSE, MAE and MAPE metrics. The energy analysis also considers the ratio of global minima
and processing period to assess its robustness. The findings are significant because this model considerably impacts Hopfield networks’ capacity to handle 3SAT problems with less complexity and speed. The new information and ideas will aid in developing innovative ways to gather knowledge for future research in logic programming. Furthermore, the
breakthrough in dynamic learning is considered a significant step forward in neuro-symbolic integration. |
format |
Article |
author |
Farah Liyana, Azizan Saratha, Sathasivam Majid Khan, Majahar Ali |
author_facet |
Farah Liyana, Azizan Saratha, Sathasivam Majid Khan, Majahar Ali |
author_sort |
Farah Liyana, Azizan |
title |
Hybridised Intelligent Dynamic Model of 3-Satisfiability Fuzzy
Logic Hopfield Neural Network |
title_short |
Hybridised Intelligent Dynamic Model of 3-Satisfiability Fuzzy
Logic Hopfield Neural Network |
title_full |
Hybridised Intelligent Dynamic Model of 3-Satisfiability Fuzzy
Logic Hopfield Neural Network |
title_fullStr |
Hybridised Intelligent Dynamic Model of 3-Satisfiability Fuzzy
Logic Hopfield Neural Network |
title_full_unstemmed |
Hybridised Intelligent Dynamic Model of 3-Satisfiability Fuzzy
Logic Hopfield Neural Network |
title_sort |
hybridised intelligent dynamic model of 3-satisfiability fuzzy
logic hopfield neural network |
publisher |
UPM Press |
publishDate |
2023 |
url |
http://ir.unimas.my/id/eprint/44793/1/Hybridised%20Intelligent.pdf http://ir.unimas.my/id/eprint/44793/ http://www.pertanika.upm.edu.my/pjst/browse/regular-issue?article=JST-3777-2022 https://doi.org/10.47836/pjst.31.4.06 |
_version_ |
1800728139706400768 |
score |
13.15806 |