Smart Tea Farming Untuk Klasifikasi Penyakit Daun Teh Berbasis Mobilenetv3-Small Pada Perangkat Edge
DOI:
https://doi.org/10.31004/joecy.v6i2.10839Keywords:
Tea Leaf, Plant Disease Classification, Convolutional Neural Network, MobileNetV3.Abstract
Tea plants are a strategic plantation commodity in Indonesia; however, their productivity is often hindered by leaf diseases that negatively affect both the quality and quantity of yields. Disease detection is still largely performed manually, making the identification process less efficient and highly dependent on expert knowledge. This study aims to develop a Convolutional Neural Network (CNN) model using the MobileNetV3-Small architecture to classify tea leaf diseases based on image data and to implement it in a mobile application using an Edge-AI approach. The dataset consists of 1,500 tea leaf images divided into five classes: blister blight, red rust, grey blight, brown blight, and healthy leaf. The research stages include data preprocessing, model training, and evaluation using accuracy, precision, recall, and F1-score metrics. The experimental results show that the proposed model achieves an accuracy of 95.33%, precision of 0.95, recall of 0.95, and F1-score of 0.95. These results indicate that the CNN model with the MobileNetV3-Small architecture performs well in classifying tea leaf diseases and has strong potential to be implemented as a data-driven early detection system to support decision-making in the agricultural sector.
References
Habiburrohman, D., & Sukohar, D. A. (2018). Aktivitas Antioksidan dan Antimikrobial pada Polifenol Teh Hijau. In J Agromedicine Unila | (Vol. 5).
Kompas.com. (2025). Mengembalikan kejayaan industri teh Indonesia. Diakses dari https://agri.kompas.com/read/2025/01/05/153423284/mengembalikan-kejayaan-industri-teh-indonesia
Direktorat Jenderal Perkebunan, Outlook Komoditas Perkebunan Teh 2024, Jakarta: Kementerian Pertanian RI, 2024.
Suciani, R., Anugra, D. A., Faisal, E., & Nuswantoro, D. (2025). Deteksi Penyakit Daun Padi Menggunakan Deep Learning dengan Arsitektur CNN Detection Of Rice Leaf Disease Using Deep Learning With CNN Architecture. Journal of Information Technology and Computer Science (INTECOMS), 8(5). https://www.kaggle.com/datasets/nirmals
Ristanti Puji Lusyana Elinda. (2024). Analisis dan Perbandingan Arsitektur VGG16 dan MOBILENETV2 untuk Klasifikasi dan Identifikasi Penyakit Daun Pada Tanaman Cabai Menggunakan CNN.
Bourechak, A., Zedadra, O., Kouahla, M. N., Guerrieri, A., Seridi, H., & Fortino, G. (2023). At the Confluence of Artificial Intelligence and Edge Computing in IoT-Based Applications: A Review and New Perspectives. In Sensors (Vol. 23, Issue 3). MDPI. https://doi.org/10.3390/s23031639
Diah, K., Puspita, A., Nilogiri, A., Oktavianto, H., & Jember, M. (2023). Deteksi Penyakit Daun Teh Menggunakan Metode Convolutional Neural Network (CNN).
Dwijayana Diva Gede, & Wibawa Arta Gede. (2022). Implementasi Transfer Learning Dalam Klasifikasi Penyakit Pada Daun Teh Menggunakan MobileNetV2.
Hardi, N. (2022). Komparasi Algoritma MobileNet Dan Nasnet Mobile Pada Klasifikasi Penyakit Daun Teh. Jurnal Rekayasa Perangkat Lunak, 3(1).
Kurnia Anaga, G., Mahdiyah, U., & Bagus Setiawan, A. (2024). Implementasi Metode Convolutional Neural Network (CNN) Untuk Klasifikasi Penyakit Teh di PT Perkebunan Nusantara XII Sirah Kencong. In Agustus (Vol. 8). Online.
Hidayat, A., Ernawati, T., Bandung, P. T., Pesantren, J., Utara, K. C., Cimahi, K., & Barat, J. (2024). Metode Klasifikasi Algoritma Convolutional Neural Network (CNN) Pada Penyakit Daun Teh.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Ita Setiani

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.







