AI And IoT Based E-Dermatology System for Facial Skin Condition Analysis and Skincare Recommendation
DOI:
https://doi.org/10.33795/jartel.v16i3.10899Keywords:
E-Dermatology, facial skin condition, Fuzzy Logic, IoT, Moisture Click sensor, skincare recommendation, YOLOv8Abstract
Facial skin problems are among the most common health issues experienced by the Indonesian population, while access to affordable and reachable dermatological consultation remains limited. This study develops an AI- and IoT-based E-Dermatology system that integrates a YOLOv8 object detection model to identify facial skin conditions, a Fuzzy Logic algorithm to classify severity a nd determine skincare recommendations, and an ESP32-based Moisture Click sensor connected through the MQTT protocol to measure facial skin moisture in real time. The system is intended to help users independently monitor facial skin condition without requiring specialized medical expertise. Testing results show that the YOLOv8 model achieved a precision of 0.862, a recall of 0.812, and a mAP@50 of 0.865, with the best-performing training weights reaching a peak precision of 0.878; the Fuzzy Logic algorithm reached a 100% match rate against scikit-fuzzy validation across 10 classification test scenarios, supported by a membership-function-level validation that matched scikit-fuzzy on 100% of tested points for the triangular function and 90% for the trapezoidal function; the Moisture Click sensor obtained an accuracy of 80.91% with a MAPE of 19.09% compared to a commercial instrument, and a MAPE of 1.24% compared to a clinical image-based skin analyzer; and User Acceptance Testing on 20 respondents produced satisfaction scores between 93% and 97% across all functionality aspects. These results indicate that the proposed AI- and IoT-based E-Dermatology system is feasible and effective as a self-service tool for facial skin analysis and skincare recommendation
References
A. Prameswari, "Riset Membuktikan Ini Masalah Kulit Paling Sering Dialami Orang Indonesia," Wolipop – Detikcom.
M. Lusiana, S. St, and M. T. Pd, Buku Ajar Perawatan Kulit Wajah.
A. Goldust, M. Goldust, and U. Wollina, "Periorbital Hyperpigmentation—Dark Circles under the Eyes; Treatment Suggestions and Combining Procedures," Cosmetics, pp. 1-12, 2021, doi: 10.3390/cosmetics8020026.
A. A. Hania, "Mengenal Artificial Intelligence, Machine Learning, Neural Network, dan Deep Learning."
F. Sudana Putra, D. Otomatis Jerawat Wajah, and M. P. Kurniawan, "Deteksi Otomatis Jerawat Wajah Menggunakan Metode Convolutional Neural Network (CNN)," JIFOTECH (J. Inf. Technol.), vol. 1, no. 2, 2021.
C. D. Sinaulan and A. Hantara, "Model Klasifikasi Permasalahan Kulit Wajah Menggunakan Metode Support Vector Machine," J. Pendidik. dan Kewirausahaan, vol. 9, no. 1, pp. 297-308, Oct. 2021, doi: 10.47668/pkwu.v9i1.246.
J. Li et al., "Development and validation of an artificial intelligence-powered acne grading system incorporating lesion identification," Front. Med., vol. 10, 2023, doi: 10.3389/fmed.2023.1255704.
V. Marshalia and D. M. Fathurahman, "Perancangan Pemanfaatan IoT dan Machine Learning Untuk Sistem Monitoring Kesehatan Kulit Wajah Berjerawat," 2024.
R. S. Sinta Puspito Rini, "Aplikasi Pendeteksi Masalah Kulit Wajah Menggunakan Algoritma CNN Berbasis Android," J. Kreat. Teknol. dan Komput., vol. 16, p. 28, 2025.
M. S. E.-Sayed Amer, "Enhanced Model for Classifying Skin Diseases Using YOLO Technique," Int. J. Res. Sci. Innov., vol. XII, no. XV, pp. 645-654, 2025, doi: 10.51244/ijrsi.2025.121500058p.
D. P. Panagoulias, E. Tsoureli-Nikita, M. Virvou, and G. A. Tsihrintzis, "Dermacen analytica: A novel methodology integrating multi-modal large language models with machine learning in dermatology," Int. J. Med. Inform., vol. 199, p. 105898, 2025, doi: 10.1016/j.ijmedinf.2025.105898.
A. S. Dite Arum, U. Nurannisa, and R. Alamsyah Putra, "Sistem Pendukung Keputusan Pemilihan Serum Avoskin yang Sesuai dengan Kebutuhan Kulit Wajah Menggunakan Logika Fuzzy," 2023.
J. S. Eka Nindiya, Miftakhul Maulidina, and M. Dewi Manikta Puspitasari, "Rancang Bangun Alat Pendeteksi Tipe Kulit Wajah Berbasis ESP32 Dengan Sensor Cahaya TSL2561," 2026.
Ade Rahayu, "Metode Penelitian dan Pengembangan (R&D): Pengertian, Jenis dan Tahapan," DIAJAR J. Pendidik. dan Pembelajaran, vol. 4, no. 3, pp. 459-470, 2025, doi: 10.54259/diajar.v4i3.5092.
"ESP32-C3-MINI-1 Datasheet," Version 2.0, Espressif Systems.
T. Click and T. Click, "Moisture Click."
A. Ma'arif, "Buku Ajar Pemrograman Lanjut Bahasa Pemrograman Python," Univ. Ahmad Dahlan, p. 62, 2020.
P. M. Swamidass, "Mean Absolute Percentage Error (MAPE)," Encycl. Prod. Manuf. Manag., vol. 3, pp. 462-462, 2025, doi: 10.1007/1-4020-0612-8_580.
M. H. Alfayyadh and H. Aprilianto, "Sistem Pengenalan Wajah Untuk Akses Data Dengan Metode Local Binary Pattern Histogram," Progresif
J. Ilm. Komput., vol. 17, no. 1, p. 47, 2021, doi: 10.35889/progresif.v17i1.572.
Y. A. R. L. Altien J. Rindengan, Buku Sistem Fuzzy. CV. Patra Media Grafindo Bandung, 2024.
M. Prabacita, "Surat Validasi Sistem Pakar oleh Radiance Rejuvenation and Anti-Aging Center," 2026.
