Cover Image

Optimizing Hyperparameters for Improved Melanoma Classification using Metaheuristic Algorithm

Melanoma, a prevalent and formidable skin cancer, necessitates early detection for improved survival rates. The rising incidence of melanoma poses significant challenges to healthcare systems worldwide. While deep neural networks offer the potential for precise melanoma classification, the optimizat...

Full description

Saved in:
Bibliographic Details
Main Authors: Adamu, S., Alhussian, H., Aziz, N., Abdulkadir, S.J., Alwadin, A., Imam, A.A., Garba, A., Saidu, Y.
Format: Article
Published: Science and Information Organization 2023
Online Access:http://scholars.utp.edu.my/id/eprint/38030/
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85175302308&doi=10.14569%2fIJACSA.2023.0141057&partnerID=40&md5=d2ffdb41787f04daf0b44b7e882c780b
Tags: Add Tag
No Tags, Be the first to tag this record!
id oai:scholars.utp.edu.my:38030
record_format eprints
spelling oai:scholars.utp.edu.my:380302023-12-11T03:01:43Z http://scholars.utp.edu.my/id/eprint/38030/ Optimizing Hyperparameters for Improved Melanoma Classification using Metaheuristic Algorithm Adamu, S. Alhussian, H. Aziz, N. Abdulkadir, S.J. Alwadin, A. Imam, A.A. Garba, A. Saidu, Y. Melanoma, a prevalent and formidable skin cancer, necessitates early detection for improved survival rates. The rising incidence of melanoma poses significant challenges to healthcare systems worldwide. While deep neural networks offer the potential for precise melanoma classification, the optimization of hyperparameters remains a major obstacle. This paper introduces a groundbreaking approach that harnesses the Manta Rays Foraging Optimizer (MRFO) to empower melanoma classification. MRFO efficiently fine-tunes hyperparameters for a Convolutional Neural Network (CNN) using the ISIC 2019 dataset, which comprises 776 images (438 melanoma, 338 non-melanoma). The proposed cost-effective DenseNet121 model surpasses other optimization methods in various metrics during training, testing, and validation. It achieves an impressive accuracy of 99.26, an AUC of 99.56, an F1 score of 0.9091, a precision of 94.06, and a recall of 87.96. Comparative analysis with EfficientB1, EfficientB7, EfficientNetV2B0, NesNetLarge, ResNet50, VGG16, and VGG19 models demonstrates its superiority. These findings underscore the potential of the novel MRFO-based approach in achieving superior accuracy for melanoma classification. The proposed method has the potential to be a valuable tool for early detection and improved patient outcomes. © (2023) All Rights Reserved. Science and Information Organization 2023 Article NonPeerReviewed Adamu, S. and Alhussian, H. and Aziz, N. and Abdulkadir, S.J. and Alwadin, A. and Imam, A.A. and Garba, A. and Saidu, Y. (2023) Optimizing Hyperparameters for Improved Melanoma Classification using Metaheuristic Algorithm. International Journal of Advanced Computer Science and Applications, 14 (10). pp. 531-540. ISSN 2158107X https://www.scopus.com/inward/record.uri?eid=2-s2.0-85175302308&doi=10.14569%2fIJACSA.2023.0141057&partnerID=40&md5=d2ffdb41787f04daf0b44b7e882c780b 10.14569/IJACSA.2023.0141057 10.14569/IJACSA.2023.0141057 10.14569/IJACSA.2023.0141057
institution Universiti Teknologi Petronas
building UTP Resource Centre
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Teknologi Petronas
content_source UTP Institutional Repository
url_provider http://eprints.utp.edu.my/
description Melanoma, a prevalent and formidable skin cancer, necessitates early detection for improved survival rates. The rising incidence of melanoma poses significant challenges to healthcare systems worldwide. While deep neural networks offer the potential for precise melanoma classification, the optimization of hyperparameters remains a major obstacle. This paper introduces a groundbreaking approach that harnesses the Manta Rays Foraging Optimizer (MRFO) to empower melanoma classification. MRFO efficiently fine-tunes hyperparameters for a Convolutional Neural Network (CNN) using the ISIC 2019 dataset, which comprises 776 images (438 melanoma, 338 non-melanoma). The proposed cost-effective DenseNet121 model surpasses other optimization methods in various metrics during training, testing, and validation. It achieves an impressive accuracy of 99.26, an AUC of 99.56, an F1 score of 0.9091, a precision of 94.06, and a recall of 87.96. Comparative analysis with EfficientB1, EfficientB7, EfficientNetV2B0, NesNetLarge, ResNet50, VGG16, and VGG19 models demonstrates its superiority. These findings underscore the potential of the novel MRFO-based approach in achieving superior accuracy for melanoma classification. The proposed method has the potential to be a valuable tool for early detection and improved patient outcomes. © (2023) All Rights Reserved.
format Article
author Adamu, S.
Alhussian, H.
Aziz, N.
Abdulkadir, S.J.
Alwadin, A.
Imam, A.A.
Garba, A.
Saidu, Y.
spellingShingle Adamu, S.
Alhussian, H.
Aziz, N.
Abdulkadir, S.J.
Alwadin, A.
Imam, A.A.
Garba, A.
Saidu, Y.
Optimizing Hyperparameters for Improved Melanoma Classification using Metaheuristic Algorithm
author_facet Adamu, S.
Alhussian, H.
Aziz, N.
Abdulkadir, S.J.
Alwadin, A.
Imam, A.A.
Garba, A.
Saidu, Y.
author_sort Adamu, S.
title Optimizing Hyperparameters for Improved Melanoma Classification using Metaheuristic Algorithm
title_short Optimizing Hyperparameters for Improved Melanoma Classification using Metaheuristic Algorithm
title_full Optimizing Hyperparameters for Improved Melanoma Classification using Metaheuristic Algorithm
title_fullStr Optimizing Hyperparameters for Improved Melanoma Classification using Metaheuristic Algorithm
title_full_unstemmed Optimizing Hyperparameters for Improved Melanoma Classification using Metaheuristic Algorithm
title_sort optimizing hyperparameters for improved melanoma classification using metaheuristic algorithm
publisher Science and Information Organization
publishDate 2023
url http://scholars.utp.edu.my/id/eprint/38030/
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85175302308&doi=10.14569%2fIJACSA.2023.0141057&partnerID=40&md5=d2ffdb41787f04daf0b44b7e882c780b
_version_ 1787138257557913600
score 13.222552

Similar Items