Article Sidebar

Submitted
June 12, 2025
Published
September 30, 2025
Download
pdf
Statistic
Read Counter : 2 Download : 1

Main Article Content

Abstract

Accurate classification of acne types is essential for determining the appropriate treatment. This study developed an automatic detection system based on Android using an ensemble Deep Learning approach and partial layer optimization to address the visual similarity challenges among different acne types. MobileNet and EfficientNetB0 were used as base models, then combined using majority voting and weighted averaging techniques. The dataset used consisted of 6,875 acne images that underwent preprocessing and augmentation. To improve efficiency and prevent overfitting, early layers of the models were frozen, and fine-tuning was applied only to the top layers. The best-performing model was then converted into TensorFlow Lite (TFLite) format and integrated into an Android application. The application allows users to classify acne in real time using either the camera or gallery. Evaluation results showed that the ensemble model offered better accuracy and stability compared to individual models, with fast inference times on Android devices. This system provides a practical and accurate solution for both general users and medical professionals in detecting acne types.

Keywords

Acne detection Deep Learning Ensemble learning Partial layer optimization TensorFlow Lite Android

Article Details

References

  1. Agustiani, S., Aryanti, R., Khotimatul Wildah, S., Arifin, Y. T., Marlina, S., & Misriati, T. (2024). Optimisasi Model Deep Learning untuk Deteksi Penyakit Daun Tebu dengan Fine-Tuning MobileNetV2. Journal of Informatics Management and Information Technology, 4(4), 150–157. https://doi.org/10.47065/jimat.v4i4.411
  2. Bhargavi, M., Renugadevi, R., Sivabalan, S., Phani, P., Ganesh, J., & Bhanu, K. (2023). Ensemble Learning for Skin Lesion Classification: A Robust Approach for Improved Diagnostic Accuracy (ELSLC). 3rd International Conference on Innovative Mechanisms for Industry Applications, ICIMIA 2023 - Proceedings, 390–395. https://doi.org/10.1109/ICIMIA60377.2023.10425888
  3. Bismi, W., Dwiza, R., & Sri, H. (2021). Classification of Myopia Eye Diseases Using (Vol. 15, Issue 2).
  4. Bismi, W., Novianti, D., & Qomaruddin, M. (2024). Analisis Perbandingan Klasifikasi Citra Genus Panthera dengan Pendekatan Deep learning Model MobileNet. Jurnal Informatika Dan Rekayasa Perangkat Lunak, 6(1). https://publikasiilmiah.unwahas.ac.id/JINRPL/article/view/9037/pdf
  5. Bismi, W., Riana, D., & Hewiz, A. S. (2024). Disease Identification on Fig Leaf Images Using Deep Learning Method. International Journal of Advanced Science Computing and Engineering, 6(2), 57–63. https://doi.org/10.62527/ijasce.6.2.203
  6. David, R., Duke, J., Jain, A., Reddi, V. J., Jeffries, N., & Li, J. (2021). Tensorflow Lite Micro: Embedded Machine Learning On Tinyml Systems. MLSys Proceedings, 1–9.
  7. De, A., Mishra, N., & Chang, H. T. (2024). An approach to the dermatological classification of histopathological skin images using a hybridized CNN-DenseNet model. PeerJ Computer Science, 10. https://doi.org/10.7717/peerj-cs.1884
  8. DermNet. (2025). “Acne Affecting the Face Image,.” DermNet New Zealand Trust. https://dermnetnz.org/topics/acne-face-images
  9. Durgabhavani, B., Chandana, B., Sandhyarani, Lavanya, G., Srikanth, G., & Bhaskar, N. (2023). Classification of Skin Disease using CNN. 2023 International Conference on Evolutionary Algorithms and Soft Computing Techniques, EASCT 2023. https://doi.org/10.1109/EASCT59475.2023.10393477
  10. Fadlilah, U., Mahamad, A. K., & Handaga, B. (2021). The Development of Android for Indonesian Sign Language Using Tensorflow Lite and CNN: An Initial Study. Journal of Physics: Conference Series, 1858(1). https://doi.org/10.1088/1742-6596/1858/1/012085
  11. Fajarendra, Y. iza. (2025). PENGGUNAAN ENSEMBLE LEARNING UNTUK KLASIFIKASI TINGKAT RISIKO ABRASI BERBASIS CITRA SATELIT SENTINEL-2. UIN Sunan Kalijaga Yogyakarta.
  12. Isa, N. A. M., & Mangshor, N. N. A. (2021). Acne Type Recognition for Mobile-Based Application Using YOLO. Journal of Physics: Conference Series, 1962(1). https://doi.org/10.1088/1742-6596/1962/1/012041
  13. Javaid, S., & Ubaid, M. T. (2024). Skin Disease Detection Using Transfer Learning. 2024 International Visualization, Informatics and Technology Conference (IVIT), 122–127. https://doi.org/10.1109/IVIT62102.2024.10692509
  14. Kaya, Y., & Gürsoy, E. (2023). A MobileNet-based CNN model with a novel fine-tuning mechanism for COVID-19 infection detection. Soft Computing, 27(9), 5521–5535. https://doi.org/10.1007/s00500-022-07798-y
  15. Liu, S., Fan, Y., Duan, M., Wang, Y., Su, G., Ren, Y., Huang, L., & Zhou, F. (2022). AcneGrader: An ensemble pruning of the deep learning base models to grade acne. Skin Research and Technology, 28(5), 677–688. https://doi.org/10.1111/srt.13166
  16. Muhaba, K. A., Dese, K., Aga, T. M., Zewdu, F. T., & Simegn, G. L. (2022). Automatic skin disease diagnosis using deep learning from clinical image and patient information. Skin Health and Disease, 2(1). https://doi.org/10.1002/ski2.81
  17. Ramadhani, F., Rahardiantoro, S., & Masjkur, M. (2024). Acne Severity Classification Study Using Convolutional Neural Network Algorithm with MobileNetV2 Architecture. Indonesian Journal of Statistics and Its Applications, 8(2), 112–128. https://doi.org/10.29244/ijsa.v8i2p112-128
  18. Riaz, S., Naeem, A., Malik, H., Naqvi, R. A., & Loh, W. K. (2023). Federated and Transfer Learning Methods for the Classification of Melanoma and Nonmelanoma Skin Cancers: A Prospective Study. In Sensors (Basel, Switzerland) (Vol. 23, Issue 20). https://doi.org/10.3390/s23208457
  19. Sudana Putra, F., Otomatis Jerawat Wajah, D., & Kurniawan, M. P. (2021). Deteksi Otomatis Jerawat Wajah Menggunakan Metode Convolutional Neural Network (CNN). JIFOTECH (JOURNAL OF INFORMATION TECHNOLOGY, 1(2).
  20. Tanantong, T., Chalarak, N., Pandecha, P., Tanantong, K., & Srijiranon, K. (2024). MOBILE-BASED DEEP LEARNING FRAMEWORK FOR CLASSIFYING COMMON SKIN DISEASES IN THAILAND. ICIC Express Letters, Part B: Applications, 15(5), 495–503. https://doi.org/10.24507/icicelb.15.05.495
  21. TensorFlow Lite Guide. (2022). TensorFlow. https://www.tensorflow.org/lite/guide
  22. Tutiani, & Wati, S. (2022). Implementation of Convolutional Neural Network (CNN) in Android-Based Acne Detection Applications. 2022 International Conference on Information Technology Research and Innovation (ICITRI), 151–155. https://doi.org/10.1109/ICITRI56423.2022.9970231
  23. Wahyudi, M., Bismi, W., Firmansyah, Raharjo, M., Pujiastuti, L., & Untung, R. (2023). Gender Recognition Based on Face Image Using Deep Learning Method. 11th International Conference on Cyber and IT Service Management (CITSM), 1–6. https://doi.org/10.1109/CITSM60085.2023.10455315