Feature Selection Based on Dragonfly Optimization for Psoriasis Classification
Keywords:
skin disease, Deep Learning, Dragonfly Optimization Algorithm, feature selectionAbstract
Due to their efficiency and higher disease detection accuracy than traditional methods, metaheuristic algorithms are prominent in healthcare data analysis. The Dragonfly Algorithm (DFA) uses wrapper feature selection to find illness categorization features. DFA was used to pick features and recognize skin illnesses using CNN, VGG19, and EfficientNet-B2 classifiers. The classifier's accuracy using a given set of features from the training dataset determined the Dragonflies' fitness value in each iteration. The experimental study showed DFA's precision and little loss. Two EfficientNet-B2 and VGG19-based CNN models were created in tandem to analyze performance. DermNet NZ and ISIC 2019 were used to train these models. Disease taxonomy helped the models classify. Both datasets classified all eight skin illnesses with an average accuracy of 88.5% and 0.0003 loss. This shows that Deep Learning can classify a wide range of skin conditions with near-human accuracy and reproducibility. These models can also help clinicians perform large-scale screenings utilizing clinical or dermoscopic images for real-time skin disease diagnosis, improving healthcare practices and patient outcomes. This work advances skin disease diagnostics and shows the medical potential of Deep learning.
Downloads
References
Alcon, J.F., Ciuhu, C., ten Kate, W., Heinrich, A., Uzunbajakava, N., Krekels, G., Siem, D. and de Haan, G. (2009) Automatic Imaging System with Decision Support for Inspection of Pigmented Skin Lesions and Melanoma Diagnosis. IEEE Journal of Selected Topics in Signal Processing, 3, 14-25. https://doi.org/10.1109/JSTSP.2008.2011156.
Marín, C., Alférez, G.H., Córdova, J. and González, V. (2015) Detection of Melanoma through Image Recognition and Artificial Neural Networks. World Congress on Medical Physics and Biomedical Engineering, Toronto, 7-12 June 2015, Vol. 51, 832-835. https://doi.org/10.1007/978-3-319-19387-8_204
Pattem, Sampurnima & Thatavarti, Satish. (2023). Identification of duplicate parts of hyper spectral images based on fuzzy by dimensionality reduction techniques. Soft Computing. 1-12. 10.1007/s00500-023-08574-2.
Shu, Wenhao & Yan, Zhenchao & Yu, Jianhui & Qian, Wenbin. (2022). Information gain-based semi-supervised feature selection for hybrid data. Applied Intelligence. 53. 10.1007/s10489-022-03770-3.
Qiao W, Yang Z (2019) Solving large-scale function optimization problem by using a new metaheuristic algorithm based on quantum dolphin swarm algorithm. IEEE Access 7:138972–138989. https://doi.org/10.1109/ACCESS.2019.2942169
Kaul S, Kumar Y (2021) Nature-inspired metaheuristic algorithms for constraint handling: challenges, issues, and research perspective. In: Kulkarni AJ, Mezura-Montes E, Wang Y, Gandomi AH, Krishnasamy G (eds) Constraint handling in metaheuristics and applications. Springer, Singapore. https:// doi.org/10.1007/978-981-33-6710-4_3
Bennett R, Logue J, Liu D, Reeder R, Janosko K et al (2020) Kikwit Ebola virus disease progression in the rhesus monkey animal model. Viruses 12(7):1–14. https://doi.org/10.3390/v1207 0753
Hajihashemi V, Hassani Z, Dehmajnoonie I, Borna K (2019) Hybrid algorithms of whale optimization algorithm and k-nearest neighbor to predict the liver disease. EAI Endorsed Trans Context-Aware Syst Appl 6(16):156838. https://doi.org/10.4108/eai. 13-7-2018.156838
Dermnet. Kaggle. Available online: https://www.kaggle.com/datasets/shubhamgoel27/dermnet (accessed on 20 June 2023).
ISIC Challenge. Available online: https://challenge.isic-archive.com/landing/2019/ (accessed on 21 June 2023).
Verma, Anurag & Pal, Saurabh & Tiwari, B. (2020). Skin disease prediction using ensemble methods and a new hybrid feature selection technique. Iran Journal of Computer Science. 3. 10.1007/s42044-020-00058-y.
Verma, Anurag & Pal, Saurabh & Kumar, Surjeet & Tiwari, B. (2019). Comparison of skin disease prediction by feature selection using ensemble data mining techniques. Informatics in Medicine Unlocked. 16. 100202. 10.1016/j.imu.2019.100202.
Abikoye, Oluwakemi & Komolafe, R & Aro, Taye. (2019). Performance evaluation of feature selection algorithms on skin disease prediction. 4. 337-342.
Ramya, P. & Sathiyabhama, B.. (2023). Skin Cancer Prediction using Enhanced Genetic Algorithm with Extreme Learning Machine. Journal of Trends in Computer Science and Smart Technology. 5. 1-13. 10.36548/jtcsst.2023.1.001.
Sahu, Shreya & Das, Pranesh & Jose a, Binu. (2023). A New Framework for Disease Prediction: Using Dimensionality Reduction and Feature Selection. 10.1007/978-981-19-9858-4_32.
Baireddy, Ravinder & Nagaraja, R. (2022). A hybrid particle swarm optimization with multi-objective clustering for dermatologic diseases diagnosis. Journal of Intelligent Systems. 31. 876-890. 10.1515/jisys-2022-0028.
Mirjalili, Seyedali. (2015). Dragonfly algorithm: A new meta-heuristic optimization technique for solving single-objective, discrete, and multi-objective problems. Neural Computing and Applications. 27. 10.1007/s00521-015-1920-1.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.