Bayesian Hyperparameter Optimization of Lightweight CNNs for Facial Dermatological Classification
DOI:
https://doi.org/10.29207/resti.v10i1.7020Keywords:
bayesian optimization, EfficientNetB3, image classification, mobile application, MobileNetV3Abstract
Convolutional Neural Networks (CNNs) have been widely applied for skin condition classification. However, fair comparisons across lightweight architectures are often hindered by inconsistent hyperparameter settings. This study investigates the performance of two efficient CNN architectures, EfficientNetB3 and MobileNetV3, for facial dermatological classification across seven skin condition categories. To ensure optimal and comparable performance, Bayesian hyperparameter optimization was employed, alongside data augmentation to improve generalization. Experimental results show that EfficientNetB3 achieved the highest accuracy of 91.91%, outperforming MobileNetV3 at 90.44%. Beyond model comparison, this work highlights the novelty of applying Bayesian optimization to achieve fair benchmarking of lightweight CNNs under limited dataset conditions. The best-performing model was further deployed as a mobile application using TensorFlow Lite and Flutter, demonstrating its potential for real-world dermatological support.
Downloads
References
A. N. Mario et al., “Anatomical and Physiological Characteristics of Neonatal and Infant Skin: Effects on Immunity and Dermatitis Prevalence,” JBT, vol. 24, no. 1b, pp. 173–180, Dec. 2024, https://doi.org/10.29303/jbt.v24i1b.7918.
M. A. Heryanto, D. Juananta, A. Sadanareswari, and S. A. Wulandari, “Klasifikasi Jenis Kulit Wajah menggunakan Backpropagation Neural Networks Berbasis GLCM,” ELKOMIKA, vol. 11, no. 3, p. 705, Jul. 2023, https://doi.org/10.26760/elkomika.v11i3.705.
B. Shetty, R. Fernandes, A. P. Rodrigues, R. Chengoden, S. Bhattacharya, and K. Lakshmanna, “Skin lesion classification of dermoscopic images using machine learning and convolutional neural network,” Sci Rep, vol. 12, no. 1, p. 18134, Oct. 2022, https://doi.org/10.1038/s41598-022-22644-9.
J. S. Velasco, J. V. Catipon, E. G. Monilar, V. M. Amon, G. C. Virrey, and L. K. S. Tolentino, “Classification of Skin Disease Using Transfer Learning in Convolutional Neural Networks,” 2023, https://doi.org/10.48550/ARXIV.2304.02852.
M. Tan and Q. V. Le, “EfficientNet: Rethinking model scaling for convolutional neural networks,” 36th International Conference on Machine Learning, ICML 2019, vol. 2019-June, pp. 10691–10700, 2019, https://doi.org/10.48550/arXiv.1905.11946.
Nadya Novalina and Mia Rizkinia, “Implementation of Xception and EfficientNetB3 for COVID-19 Detection on Chest X-Ray Image via Transfer Learning,” IJECBE, vol. 1, no. 2, pp. 97–107, Dec. 2023, https://doi.org/10.62146/ijecbe.v1i2.14.
A. Howard et al., “Searching for mobileNetV3,” Proceedings of the IEEE International Conference on Computer Vision, pp. 1314–1324, 2019, https://doi.org/10.1109/ICCV.2019.00140.
S. Pechetti and B. S. Rao, “Optimized MobileNetV3: a deep learning-based Parkinson’s disease classification using fused images,” PeerJ Computer Science, vol. 9, p. e1702, Nov. 2023, https://doi.org/10.7717/peerj-cs.1702.
Herimanto, Arie Satia Dharma, Junita Amalia, David Largo, and Christin Adelia Pratiwi Sihite, “Performance Analysis of MobileNetV3-based Convolutional Neural Network for Facial Skin Disorder Classification,” J. RESTI (Rekayasa Sist. Teknol. Inf.), vol. 8, no. 6, pp. 701–709, Dec. 2024, https://doi.org/10.29207/resti.v8i6.5982.
F. Adnan, M. J. Awan, A. Mahmoud, H. Nobanee, A. Yasin, and A. M. Zain, “EfficientNetB3-Adaptive Augmented Deep Learning (AADL) for Multi-Class Plant Disease Classification,” IEEE Access, vol. 11, pp. 85426–85440, 2023, https://doi.org/10.1109/ACCESS.2023.3303131.
Q. Liu, X. She, and Q. Xia, “AI based diagnostics product design for osteosarcoma cells microscopy imaging of bone cancer patients using CA-MobileNet V3,” Journal of Bone Oncology, vol. 49, p. 100644, Dec. 2024, https://doi.org/10.1016/j.jbo.2024.100644.
K. DeVoe, G. Takahashi, E. Tarshizi, and A. Sacker, “Evaluation of the precision and accuracy in the classification of breast histopathology images using the MobileNetV3 model,” Journal of Pathology Informatics, vol. 15, no. April, p. 100377, 2024, https://doi.org/10.1016/j.jpi.2024.100377.
B. Shahriari, K. Swersky, Z. Wang, R. P. Adams, and N. De Freitas, “Taking the human out of the loop: A review of Bayesian optimization,” Proceedings of the IEEE, vol. 104, no. 1, pp. 148–175, 2016, https://doi.org/10.1109/JPROC.2015.2494218.
E. Hassan, M. Y. Shams, N. A. Hikal, and S. Elmougy, “The effect of choosing optimizer algorithms to improve computer vision tasks: a comparative study,” Multimed Tools Appl, vol. 82, no. 11, pp. 16591–16633, May 2023, https://doi.org/10.1007/s11042-022-13820-0.
Y. I. Sulistya, E. T. Br Bangun, and D. A. Tyas, “CNN Ensemble Learning Method for Transfer learning: A Review,” Ilk. J. Ilm., vol. 15, no. 1, pp. 45–63, Apr. 2023, https://doi.org/10.33096/ilkom.v15i1.1541.45-63.
A. Hosna, E. Merry, J. Gyalmo, Z. Alom, Z. Aung, and M. A. Azim, “Transfer learning: a friendly introduction,” J Big Data, vol. 9, no. 1, p. 102, Oct. 2022, https://doi.org/10.1186/s40537-022-00652-w.
M. A. Adi, Agus Khumaidi, Mohammad Basuki Rahmat, Dimas Pristovani Riananda, Muhammad Khoirul Hasin, and Didik Sukoco, “Implementasi Sistem Deteksi Titik Api Pada area graving dock Menggunakan YOLOv5,” ELK, vol. 11, no. 2, pp. 473–482, Jul. 2024, https://doi.org/10.33795/elkolind.v11i2.5233.
P. P. Ray, “A review on TinyML: State-of-the-art and prospects,” Journal of King Saud University - Computer and Information Sciences, vol. 34, no. 4, pp. 1595–1623, Apr. 2022, https://doi.org/10.1016/j.jksuci.2021.11.019.
M. M. Effendi, A. Turmudi, and A. Arwan, “Design of Mask Detection Application Using Tensorflow Lite based on Android Mobile,” CNAHPC, vol. 6, no. 3, pp. 1265–1277, Jul. 2024, https://doi.org/10.47709/cnahpc.v6i3.4329.
M. Szczepanik and M. Kędziora, “State Management and Software Architecture Approaches in Cross-platform Flutter Applications:,” in Proceedings of the 15th International Conference on Evaluation of Novel Approaches to Software Engineering, Prague, Czech Republic: SCITEPRESS - Science and Technology Publications, 2020, pp. 407–414. https://doi.org/10.5220/0009411604070414.
Varinia Azkarin, Rangga Gelar Guntara, and Oding Herdiana, “Development of a REST API for Human Resource Information System for Employee Referral Management Domain Using the Express JS Framework and Node.js,” JSRET, vol. 2, no. 3, pp. 1085–1094, Jul. 2023, https://doi.org/10.58526/jsret.v2i3.199.
M. Wicha and B. Pańczyk, “Performance analysis of REST API technologies using Spring and Express.js examples,” Journal of Computer Sciences Institute, vol. 29, no. June, pp. 352–359, 2023, https://doi.org/10.35784/jcsi.3796.
S. J. Putri, D. G. P. Putri, and W. H. N. Putra, “Analisis Komparasi pada Teknik Black Box Testing (Studi Kasus: Website Lars),” Journal of Internet and Software Engineering, vol. 5, no. 1, pp. 23–28, 2024, https://doi.org/10.22146/jise.v5i1.9446.
N. Srivastava, U. Kumar, and Dr. P. Singh, “Software and Performance Testing Tools,” J. Infor. Electr. Electron. Eng., vol. 2, no. 1, pp. 1–12, Jan. 2021, https://doi.org/10.54060/JIEEE/002.01.001
Downloads
Published
Issue
Section
License
Copyright in each article belongs to the author
- The author acknowledges that the RESTI Journal (System Engineering and Information Technology) is the first publisher to publish with a license Creative Commons Attribution 4.0 International License.
- Authors can enter writing separately, arrange the non-exclusive distribution of manuscripts that have been published in this journal into other versions (eg sent to the author's institutional repository, publication in a book, etc.), by acknowledging that the manuscript has been published for the first time in the RESTI (Rekayasa Sistem dan Teknologi Informasi) journal ;





