Exploring a Q-learning-based chaotic naked mole rat algorithm for S-box construction and optimization
This paper introduces a new variant of the metaheuristic algorithm based on the naked mole rat (NMR) algorithm, called the Q-learning naked mole rat algorithm (QL-NMR), for substitution box construction and optimization. Unlike most competing works (which typically integrate a single chaotic map int...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English English |
| Published: |
Springer Science and Business Media Deutschland GmbH
2023
|
| Subjects: | |
| Online Access: | http://umpir.ump.edu.my/id/eprint/40759/ http://umpir.ump.edu.my/id/eprint/40759/1/Exploring%20a%20Q-learning-based%20chaotic%20naked%20mole%20rat%20algorithm.pdf http://umpir.ump.edu.my/id/eprint/40759/2/Exploring%20a%20Q-learning-based%20chaotic%20naked%20mole%20rat%20algorithm%20for%20S-box%20construction%20and%20optimization_ABS.pdf |
| _version_ | 1848826138412974080 |
|---|---|
| author | Kamal Zuhairi, Zamli Din, Fakhrud Alhadawi, Hussam S. |
| author_facet | Kamal Zuhairi, Zamli Din, Fakhrud Alhadawi, Hussam S. |
| author_sort | Kamal Zuhairi, Zamli |
| building | UMP Institutional Repository |
| collection | Online Access |
| description | This paper introduces a new variant of the metaheuristic algorithm based on the naked mole rat (NMR) algorithm, called the Q-learning naked mole rat algorithm (QL-NMR), for substitution box construction and optimization. Unlike most competing works (which typically integrate a single chaotic map into a particular metaheuristic algorithm), QL-NMR assembles five chaotic maps (i.e., Chebyshev, logistic, circle, Singer, and sinusoidal) as part of the algorithm itself. Using a Q-learning table, QL-NMR remembers the historical performance of each chaotic map during the S-box construction process allowing just-in-time adaptive selection based on its current performance. Experimental results for 8 × 8 S-box generation demonstrate that the proposed QL-NMR gives competitive performance against other existing works, particularly in terms of nonlinearity and strict avalanche criteria. To further demonstrate the effectiveness of our proposed work, we have subjected the QL-NMR for image segmentation using multilevel thresholding. The results confirm that QL-NMR gives better performance than its predecessor NMR. Finally, QL-NMR S-box also outperformed NMR S-box in image encryption. |
| first_indexed | 2025-11-15T03:40:03Z |
| format | Article |
| id | ump-40759 |
| institution | Universiti Malaysia Pahang |
| institution_category | Local University |
| language | English English |
| last_indexed | 2025-11-15T03:40:03Z |
| publishDate | 2023 |
| publisher | Springer Science and Business Media Deutschland GmbH |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | ump-407592024-05-28T07:57:32Z http://umpir.ump.edu.my/id/eprint/40759/ Exploring a Q-learning-based chaotic naked mole rat algorithm for S-box construction and optimization Kamal Zuhairi, Zamli Din, Fakhrud Alhadawi, Hussam S. QA75 Electronic computers. Computer science QA76 Computer software T Technology (General) TA Engineering (General). Civil engineering (General) This paper introduces a new variant of the metaheuristic algorithm based on the naked mole rat (NMR) algorithm, called the Q-learning naked mole rat algorithm (QL-NMR), for substitution box construction and optimization. Unlike most competing works (which typically integrate a single chaotic map into a particular metaheuristic algorithm), QL-NMR assembles five chaotic maps (i.e., Chebyshev, logistic, circle, Singer, and sinusoidal) as part of the algorithm itself. Using a Q-learning table, QL-NMR remembers the historical performance of each chaotic map during the S-box construction process allowing just-in-time adaptive selection based on its current performance. Experimental results for 8 × 8 S-box generation demonstrate that the proposed QL-NMR gives competitive performance against other existing works, particularly in terms of nonlinearity and strict avalanche criteria. To further demonstrate the effectiveness of our proposed work, we have subjected the QL-NMR for image segmentation using multilevel thresholding. The results confirm that QL-NMR gives better performance than its predecessor NMR. Finally, QL-NMR S-box also outperformed NMR S-box in image encryption. Springer Science and Business Media Deutschland GmbH 2023-05 Article PeerReviewed pdf en http://umpir.ump.edu.my/id/eprint/40759/1/Exploring%20a%20Q-learning-based%20chaotic%20naked%20mole%20rat%20algorithm.pdf pdf en http://umpir.ump.edu.my/id/eprint/40759/2/Exploring%20a%20Q-learning-based%20chaotic%20naked%20mole%20rat%20algorithm%20for%20S-box%20construction%20and%20optimization_ABS.pdf Kamal Zuhairi, Zamli and Din, Fakhrud and Alhadawi, Hussam S. (2023) Exploring a Q-learning-based chaotic naked mole rat algorithm for S-box construction and optimization. Neural Computing and Applications, 35 (14). pp. 10449-10471. ISSN 0941-0643. (Published) https://doi.org/10.1007/s00521-023-08243-3 https://doi.org/10.1007/s00521-023-08243-3 |
| spellingShingle | QA75 Electronic computers. Computer science QA76 Computer software T Technology (General) TA Engineering (General). Civil engineering (General) Kamal Zuhairi, Zamli Din, Fakhrud Alhadawi, Hussam S. Exploring a Q-learning-based chaotic naked mole rat algorithm for S-box construction and optimization |
| title | Exploring a Q-learning-based chaotic naked mole rat algorithm for S-box construction and optimization |
| title_full | Exploring a Q-learning-based chaotic naked mole rat algorithm for S-box construction and optimization |
| title_fullStr | Exploring a Q-learning-based chaotic naked mole rat algorithm for S-box construction and optimization |
| title_full_unstemmed | Exploring a Q-learning-based chaotic naked mole rat algorithm for S-box construction and optimization |
| title_short | Exploring a Q-learning-based chaotic naked mole rat algorithm for S-box construction and optimization |
| title_sort | exploring a q-learning-based chaotic naked mole rat algorithm for s-box construction and optimization |
| topic | QA75 Electronic computers. Computer science QA76 Computer software T Technology (General) TA Engineering (General). Civil engineering (General) |
| url | http://umpir.ump.edu.my/id/eprint/40759/ http://umpir.ump.edu.my/id/eprint/40759/ http://umpir.ump.edu.my/id/eprint/40759/ http://umpir.ump.edu.my/id/eprint/40759/1/Exploring%20a%20Q-learning-based%20chaotic%20naked%20mole%20rat%20algorithm.pdf http://umpir.ump.edu.my/id/eprint/40759/2/Exploring%20a%20Q-learning-based%20chaotic%20naked%20mole%20rat%20algorithm%20for%20S-box%20construction%20and%20optimization_ABS.pdf |