Adaptive hybrid hyperparameter optimization with MRFO and Lévy flight for accurate melanoma classification
Abstract Hyperparameter optimization (HPO) is essential for deep learning in medical image classification, yet standard metaheuristics such as Manta Ray Foraging Optimization (MRFO) often suffer from premature convergence in high-dimensional search spaces. To address these limitations, an enhanced v...
Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2025-06-01
|
| Series: | Journal of King Saud University: Computer and Information Sciences |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s44443-025-00078-3 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849234400169951232 |
|---|---|
| author | Shamsuddeen Adamu Hitham Alhussian Said Jadid Abdulkadir Ayed Alwadin Sallam O. F. Khairy Hussaini Mamman Shamsu Abdullahi Saidu Yahaya Aliyu Garba Dahiru Adamu Aliyu Muhammad Muntasir Yakubu Daniel Tonye Oyefidein |
| author_facet | Shamsuddeen Adamu Hitham Alhussian Said Jadid Abdulkadir Ayed Alwadin Sallam O. F. Khairy Hussaini Mamman Shamsu Abdullahi Saidu Yahaya Aliyu Garba Dahiru Adamu Aliyu Muhammad Muntasir Yakubu Daniel Tonye Oyefidein |
| author_sort | Shamsuddeen Adamu |
| collection | DOAJ |
| description | Abstract Hyperparameter optimization (HPO) is essential for deep learning in medical image classification, yet standard metaheuristics such as Manta Ray Foraging Optimization (MRFO) often suffer from premature convergence in high-dimensional search spaces. To address these limitations, an enhanced variant, MRFO-LF, was proposed by incorporating Lévy flight-based exploration, adaptive step-size decay, and a hybrid stochastic–deterministic search mechanism. This work details the first application of the proposed MRFO-LF to HPO in melanoma classification, a critical task within medical image analysis. The Lévy component enables long-range perturbations, while the adaptive decay mechanism gradually narrows the search scope, and the hybrid strategy balances global versus local exploration without relying on problem-specific heuristics. Experiments were conducted on the ISIC and PH $$ ^2 $$ 2 dermoscopic datasets using DenseNet121, InceptionV3, and VGG19. MRFO-LF attained peak validation accuracies of 99.49% (ISIC) and 100.00% (PH $$ ^2 $$ 2 ) for DenseNet121, with corresponding validation losses of 0.3580 and 0.0015. When compared to MRFO, PSO, and GA, the proposed method improved ISIC accuracy by 0.40%, reduced PH $$ ^2 $$ 2 loss by over 95%, and converged up to 30% faster. Statistical significance was confirmed through ANOVA and paired t-tests ( $$ p < 0.05 $$ p < 0.05 ). These results position MRFO-LF as a reliable and efficient optimizer for complex hyperparameter tuning in medical image classification. |
| format | Article |
| id | doaj-art-905be2c573ae4330894f6285de7a2e7e |
| institution | Kabale University |
| issn | 1319-1578 2213-1248 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | Springer |
| record_format | Article |
| series | Journal of King Saud University: Computer and Information Sciences |
| spelling | doaj-art-905be2c573ae4330894f6285de7a2e7e2025-08-20T04:03:11ZengSpringerJournal of King Saud University: Computer and Information Sciences1319-15782213-12482025-06-0137412110.1007/s44443-025-00078-3Adaptive hybrid hyperparameter optimization with MRFO and Lévy flight for accurate melanoma classificationShamsuddeen Adamu0Hitham Alhussian1Said Jadid Abdulkadir2Ayed Alwadin3Sallam O. F. Khairy4Hussaini Mamman5Shamsu Abdullahi6Saidu Yahaya7Aliyu Garba8Dahiru Adamu Aliyu9Muhammad Muntasir Yakubu10Daniel Tonye Oyefidein11Computer Science Department, Universiti Teknologi PETRONASComputer Science Department, Universiti Teknologi PETRONASComputer Science Department, Universiti Teknologi PETRONASComputer Science Department, Community College, King Saud UniversityCollege of Economics, Management & Information Systems, University of NizwaComputer Science Department, Universiti Teknologi PETRONASComputer Science Department, Universiti Teknologi PETRONASComputer Science Department, Universiti Teknologi PETRONASComputer Science Department, Universiti Teknologi PETRONASIAIICT, Ahmadu Bello UniversityComputer Science Department, Universiti Teknologi PETRONASComputer Science Department, Universiti Teknologi PETRONASAbstract Hyperparameter optimization (HPO) is essential for deep learning in medical image classification, yet standard metaheuristics such as Manta Ray Foraging Optimization (MRFO) often suffer from premature convergence in high-dimensional search spaces. To address these limitations, an enhanced variant, MRFO-LF, was proposed by incorporating Lévy flight-based exploration, adaptive step-size decay, and a hybrid stochastic–deterministic search mechanism. This work details the first application of the proposed MRFO-LF to HPO in melanoma classification, a critical task within medical image analysis. The Lévy component enables long-range perturbations, while the adaptive decay mechanism gradually narrows the search scope, and the hybrid strategy balances global versus local exploration without relying on problem-specific heuristics. Experiments were conducted on the ISIC and PH $$ ^2 $$ 2 dermoscopic datasets using DenseNet121, InceptionV3, and VGG19. MRFO-LF attained peak validation accuracies of 99.49% (ISIC) and 100.00% (PH $$ ^2 $$ 2 ) for DenseNet121, with corresponding validation losses of 0.3580 and 0.0015. When compared to MRFO, PSO, and GA, the proposed method improved ISIC accuracy by 0.40%, reduced PH $$ ^2 $$ 2 loss by over 95%, and converged up to 30% faster. Statistical significance was confirmed through ANOVA and paired t-tests ( $$ p < 0.05 $$ p < 0.05 ). These results position MRFO-LF as a reliable and efficient optimizer for complex hyperparameter tuning in medical image classification.https://doi.org/10.1007/s44443-025-00078-3Melanoma classificationHyperparameter optimizationMRFO-LFDeep learningMedical imaging |
| spellingShingle | Shamsuddeen Adamu Hitham Alhussian Said Jadid Abdulkadir Ayed Alwadin Sallam O. F. Khairy Hussaini Mamman Shamsu Abdullahi Saidu Yahaya Aliyu Garba Dahiru Adamu Aliyu Muhammad Muntasir Yakubu Daniel Tonye Oyefidein Adaptive hybrid hyperparameter optimization with MRFO and Lévy flight for accurate melanoma classification Journal of King Saud University: Computer and Information Sciences Melanoma classification Hyperparameter optimization MRFO-LF Deep learning Medical imaging |
| title | Adaptive hybrid hyperparameter optimization with MRFO and Lévy flight for accurate melanoma classification |
| title_full | Adaptive hybrid hyperparameter optimization with MRFO and Lévy flight for accurate melanoma classification |
| title_fullStr | Adaptive hybrid hyperparameter optimization with MRFO and Lévy flight for accurate melanoma classification |
| title_full_unstemmed | Adaptive hybrid hyperparameter optimization with MRFO and Lévy flight for accurate melanoma classification |
| title_short | Adaptive hybrid hyperparameter optimization with MRFO and Lévy flight for accurate melanoma classification |
| title_sort | adaptive hybrid hyperparameter optimization with mrfo and levy flight for accurate melanoma classification |
| topic | Melanoma classification Hyperparameter optimization MRFO-LF Deep learning Medical imaging |
| url | https://doi.org/10.1007/s44443-025-00078-3 |
| work_keys_str_mv | AT shamsuddeenadamu adaptivehybridhyperparameteroptimizationwithmrfoandlevyflightforaccuratemelanomaclassification AT hithamalhussian adaptivehybridhyperparameteroptimizationwithmrfoandlevyflightforaccuratemelanomaclassification AT saidjadidabdulkadir adaptivehybridhyperparameteroptimizationwithmrfoandlevyflightforaccuratemelanomaclassification AT ayedalwadin adaptivehybridhyperparameteroptimizationwithmrfoandlevyflightforaccuratemelanomaclassification AT sallamofkhairy adaptivehybridhyperparameteroptimizationwithmrfoandlevyflightforaccuratemelanomaclassification AT hussainimamman adaptivehybridhyperparameteroptimizationwithmrfoandlevyflightforaccuratemelanomaclassification AT shamsuabdullahi adaptivehybridhyperparameteroptimizationwithmrfoandlevyflightforaccuratemelanomaclassification AT saiduyahaya adaptivehybridhyperparameteroptimizationwithmrfoandlevyflightforaccuratemelanomaclassification AT aliyugarba adaptivehybridhyperparameteroptimizationwithmrfoandlevyflightforaccuratemelanomaclassification AT dahiruadamualiyu adaptivehybridhyperparameteroptimizationwithmrfoandlevyflightforaccuratemelanomaclassification AT muhammadmuntasiryakubu adaptivehybridhyperparameteroptimizationwithmrfoandlevyflightforaccuratemelanomaclassification AT danieltonyeoyefidein adaptivehybridhyperparameteroptimizationwithmrfoandlevyflightforaccuratemelanomaclassification |