Acne Severity Classification Study Using Convolutional Neural Network Algorithm with MobileNetV2 Architecture
Kajian Klasifikasi Tingkat Keparahan Jerawat Menggunakan Algoritma Convolutional Neural Network
DOI:
https://doi.org/10.29244/ijsa.v8i2p112-128Keywords:
acne vulgaris, classification, CNN, mobilenetv2, severityAbstract
Data classification is a key technique in machine learning that maps patterns and features of input data into a target class. Significant developments in data classification occur in deep learning with neural networks and Convolutional Neural Networks (CNN) that are able to extract image features automatically. CNN can classify the level of a condition based on image data, one of which is the severity of acne. Acne (acne vulgaris) is a common skin disease with varying severity. This study aims to apply the CNN MobileNetV2 model to classify acne severity based on acne input images. The data consists of 1457 acne images at 4 severity levels divided into 80% training data and 20% test data. MobileNetV2 was used as a feature extractor through transfer learning. Fine-tuning and classification were performed using fully connected layers with ReLU and softmax activation functions. The model was evaluated with a confusion matrix and classification report. The model with a combination of hyperparameter batch size 16 and a learning rate of 0.00001 was the best model that achieved 87.29% accuracy with 89% precision, 84% recall, and 86% F1 score for classifying acne severity.
Downloads
References
Achmad, Y.F., Yulfitri, A., & Ulum, M.B. (2021). Identifikasi jenis jerawat berdasarkan tekstur menggunakan GLCM dan backpropagation. Jurnal SAINTIKOM (Jurnal Sains Manajemen Informatika dan Komputer). 20(2): 139-146.
Alzubaidi, L., Zhang, J., Humaidi, A.J., Al-Dujaili, A., Duan, Y., Al-Shamma, O., Santamaria, J., Fadhel, M.A., Al-Amidie, M., & Farhan, L. (2021). Review of deep learning: concepts, CNN architectures, challenges, applications, future directions. Journal of Big Data. 8(53): 2-74.
Becker, M., Wild, T., & Zouboulis, C.C. (2017). Objective assessment of acne. Clin Dermatol. 35(2): 147-155.
Beikmohammadi, A., & Faez, K. (2018). Leaf classification for plant recognition with deep transfer learning. Irian Conference on Signal Processing and Intelligent Systems (ICSPIS). 21-26. doi: http://dx.doi.org/10.1109/ICSPIS.2018.8700547.
Hadianti, S., Sastypratiwi, H., & Sukamto, A.S. (2015). Sistem pakar diagnosis jenis jerawat pada wajah menggunakan metode k-means clustering. Jurnal Sistem Dan Teknologi Informasi. 3(3): 1-5.
Han, J., Pei, J., & Tong, H. (2011). Data Mining: Concepts and Techniques. 3rd ed. Cambridge(US): Morgan kaufmann.
Hasanah, R.L., & Hasan, M. (2022). Deteksi lesi acne vulgaris pada citra jerawat wajah menggunakan metode k-means clustering. Indonesian Journal on Software Engineering (IJSE). 8(1): 46-51.
Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., & Adam, H. (2017). MobileNets: efficient convolutional neural networks for mobile vision applications. doi: https://doi.org/10.48550/arXiv.1704.04861.
Jordan, M.I., & Mitchell, T.M. (2015). Machine learning: trends, perspectives, and prospects. Science. 349(6245): 255-260.
Kang, G., Liu, K., Hou, B., & Zhang, N. (2017). 3D multi-view convolutional neural networks for lung nodule classification. PLOS ONE. 12(11): 1-21.
Kohavi, R., & Provost, F. (1998). On applied research in machine learning. Machine Learning Boston. 30(1): 1-6.
LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature. 521(7553): 436-444.
Melisa, M., LB, P.L., & Irawati, I. (2022). Sistem pakar pendiagnosa jenis jerawat pada wajah berbasis web menggunakan metode certainty factor. Buletin Sistem Informasi dan Teknologi Islam (BUSITI). 3(1): 79-85.
Okoro, E., Ogunbiyi, A., & George, A. (2016). Prevalence and pattern of acne vulgaris among adolescents in ibadan, south-west nigeria. Journal of the Egyptian Women’s Dermatologic Society. 13(1): 7-12.
Ramadhani, M., Suprayogi, S., & Dyah, H.B. (2018). Klasifikasi jenis jerawat berdasarkan tekstur dengan menggunakan metode GLCM. e-Proceeding of Engineering. 5(1): 870-876.
Rianto, R., & Listianto, D.R. (2023). Convolutional neural network untuk mengklasifikasi tingkat keparahan jerawat. AITI: Jurnal Teknologi Informasi. 20(2): 167-176.
Rochmawanti, O., Utaminingrum, F., & Bachtiar, F.A. (2021). Analisis performa pre-trained model convolutional neural network dalam mendeteksi penyakit tuberculosis. Jurnal Teknologi Infomasi dan Ilmu Komputer (JTIIK). 8(4): 805-814.
Shorten, C., & Khoshgoftaar, T.M. (2019). A survey on image data augmentation for deep learning. Journal of Big Data. 6(60): 1-48.
Sibero, H.T., Sirajudin, A., & Anggraini, D.I. (2019). Prevalensi dan gambaran epidemiologi akne vulgaris di provinsi lampung. Jurnal Kedokteran UNILA. 3(2): 309-312.
Yudianto, M.R.A., Kusrini, & Fatta, H.A. (2020). Analisis pengaruh tingkat akurasi klasifikasi citra wayang dengan algoritma convolutional neural network. 4(2): 182-190.