Analisa Komparatif MobileNetV2 dan EfficientNetB0 Berbasis Fine-Tuning dan Data Augmentation untuk Klasifikasi Penyakit Daun Pisang
DOI:
https://doi.org/10.62712/juktisi.v5i2.1354Keywords:
Penyakit Daun Pisang, Transfer Learning, MobileNetV2, EfficientNetB0, Fine-Tuning, Data AugmentationAbstract
Penyakit daun pisang merupakan salah satu faktor yang dapat menurunkan produktivitas tanaman pisang dan menyebabkan kerugian ekonomi bagi petani. Identifikasi penyakit secara manual memerlukan waktu serta bergantung pada keahlian pengamat, sehingga diperlukan sistem otomatis yang mampu melakukan klasifikasi penyakit secara cepat dan akurat. Penelitian ini bertujuan menganalisis performa model transfer learning MobileNetV2 dan EfficientNetB0 dalam klasifikasi penyakit daun pisang menggunakan dataset BananaLSD yang terdiri atas empat kelas, yaitu Healthy, Cordana, Pestalotiopsis, dan Sigatoka. Penelitian dilakukan melalui delapan skenario eksperimen yang mengombinasikan penerapan fine-tuning dan data augmentation untuk mengetahui pengaruhnya terhadap performa model. Model terbaik selanjutnya dibandingkan menggunakan empat optimizer, yaitu Adam, AdamW, RMSprop, dan SGD. Evaluasi dilakukan menggunakan metrik accuracy, precision, recall, F1-score, serta confusion matrix. Hasil penelitian menunjukkan bahwa kombinasi EfficientNetB0 dengan fine-tuning, data augmentation, dan optimizer Adam menghasilkan performa terbaik dengan nilai accuracy sebesar 97,89%, precision 98,58%, recall 97,89%, dan F1-score 98,00%. Model terbaik kemudian diimplementasikan menggunakan FastAPI dan diintegrasikan dengan aplikasi bergerak berbasis FlutterFlow sehingga mampu melakukan klasifikasi penyakit daun pisang secara real-time. Hasil penelitian menunjukkan bahwa kombinasi arsitektur, strategi pelatihan, dan optimizer yang tepat mampu meningkatkan performa klasifikasi serta menghasilkan prototipe aplikasi yang dapat mendukung identifikasi awal penyakit daun pisang secara cepat, akurat, dan mudah digunakan.
Downloads
References
[1] Badan Pusat Statistik, “Statistik Hortikultura 2025,” Jakarta, Jun. 2026. Accessed: Jun. 29, 2026. [Online]. Available: https://www.bps.go.id/id/publication/2026/06/12/43da5ec30fc7d87985e108a5/statistik-hortikultura-2025.html
[2] N. Jiménez, S. Orellana, B. Mazon-Olivo, W. Rivas-Asanza, and I. Ramírez-Morales, “Detection of Leaf Diseases in Banana Crops Using Deep Learning Techniques,” AI (Switzerland), vol. 6, no. 3, Mar. 2025, doi: 10.3390/ai6030061.
[3] S. E. Arman, Md. Abdullahil Baki Bhuiyan, H. Muhammad Abdullah, S. Islam, T. Tanha Chowdhury, and Md. Arban Hossain, “Bananalsd A Banana Leaf Images Dataset for Classification of Banana Leaf Diseases Using Machine Learning,” Data Brief, vol. 50, p. 109608, Sep. 2023, doi: 10.1016/j.dib.2023.109608.
[4] M. Shoaib et al., “An advanced deep learning models-based plant disease detection: A review of recent research,” 2023, Frontiers Media SA. doi: 10.3389/fpls.2023.1158933.
[5] J. Zhao et al., “A review of plant leaf disease identification by deep learning algorithms,” 2025, Frontiers Media SA. doi: 10.3389/fpls.2025.1637241.
[6] M. Shoaib, A. Sadeghi-Niaraki, F. Ali, I. Hussain, and S. Khalid, “Leveraging deep learning for plant disease and pest detection: a comprehensive review and future directions,” 2025, Frontiers Media SA. doi: 10.3389/fpls.2025.1538163.
[7] M. D. Pratama, R. Gustriansyah, and E. Purnamasari, “Klasifikasi Penyakit Daun Pisang menggunakan Convolutional Neural Network (CNN),” Jurnal Teknologi Terpadu, vol. 10, no. 1, Jul. 2024, doi: 10.54914/jtt.v10i1.1167.
[8] Ni. Helmawati and E. Utami, “Analysis for Detecting Banana Leaf Disease Using the CNN Method,” JUITA: Jurnal Informatika, vol. 13, no. 1, pp. 29–36, Mar. 2025, doi: 10.30595/juita.v13i1.24514.
[9] N. Helmawati and E. Utami, “Utilization of the Convolutional Neural Network Method for Detecting Banana Leaf Disease,” Jurnal RESTI, vol. 8, no. 6, pp. 799–805, Dec. 2024, doi: 10.29207/resti.v8i6.6140.
[10] C. Nastitie, I. Handayani, and U. T. Yogyakarta, “PERBANDINGAN METODE MOBILENETV2 DAN EFFICIENTNETB0 UNTUK KLASIFIKASI JENIS PISANG COMPARISON OF MOBILENETV2 AND EFFICIENTNETB0 METHODS FOR BANANA TYPE CLASSIFICATION,” Journal of Information Technology and Computer Science (INTECOMS), vol. 8, no. 6, pp. 1990–1999, Nov. 2025, doi: 10.31539/0240cx09.
[11] M. Syifa Aryanta, C. A. Sari, and H. Rachmawanto, “A Banana Disease Detection Using MobileNetV2 Model Based on Adam Optimizer,” Journal of Applied Informatics and Computing (JAIC), vol. 9, no. 4, pp. 1207–1218, Aug. 2025, doi: 10.30871/jaic.v9i4.9870.
[12] H. Ali, N. Shifa, R. Benlamri, A. A. Farooque, and R. Yaqub, “A fine tuned EfficientNet-B0 convolutional neural network for accurate and efficient classification of apple leaf diseases,” Sci. Rep., vol. 15, no. 1, p. 25732, 2025, doi: 10.1038/s41598-025-04479-2.
[13] Y. Ferdi, “Data Augmentation through Background Removal for Apple Leaf Disease Classification Using the MobileNetV2 Model,” ArXiv, Jun. 2024, doi: 10.48550/arXiv.2412.01854.
[14] M. F. Aulia, M. K. Gibran, N. S. A. Sitorus, A. Nugroho, N. Faiza, and H. A. R. Siregar, “Transfer Learning Implementation with MobileNetV2 for Cassava Leaf Disease Detection,” JURNAL TEKNOLOGI DAN OPEN SOURCE, vol. 8, no. 1, pp. 352–361, Jun. 2025, doi: 10.36378/jtos.v8i1.4442.
[15] S. E. Thio and J. Susilo, “Identifikasi Pemilahan Sampah Berbasis Algoritma Transfer Learning CNN Menggunakan MobileNetV2 dan EfficientNetB0,” bit-Tech, vol. 8, no. 1, pp. 25–32, Aug. 2025, doi: 10.32877/bt.v8i1.1900.
[16] B. Fadhil Mohammad and A. Dijah Rahajoe, “Optimizing CNN-Based Transfer Learning through Fine-Tuning and Adaptive Augmentation for Chili Plant Disease Detection,” SISFO Jurnal Ilmiah, vol. 10, no. 1, pp. 306–315, 2026, doi: 10.29103/sisfo.
[17] Z. R. Mair, R. Heriansyah, and L. O. H. S. Sagala, “Performance Comparison of Adam and SGD Optimizers in Transfer Learning Based CNN for Banana Leaf Disease Classification,” Jurnal Sains, Nalar, dan Aplikasi Teknologi Informasi, vol. 5, no. 1, pp. 8–15, Jan. 2026, doi: 10.20885/snati.v5.i1.43901.
[18] N. Uly, H. Hendry, and A. Iriani, “CNN-RNN Hybrid Model for Diagnosis of COVID-19 on X-Ray Imagery,” Digital Zone: Jurnal Teknologi Informasi dan Komunikasi, vol. 14, no. 1, pp. 57–67, May 2023, doi: 10.31849/digitalzone.v14i1.13668.
[19] A. I. R. H. Barat, W. S. Astuti, D. Hartama, A. P. Windarto, and A. Wanto, “ENHANCED FLOWER IMAGE CLASSIFICATION USING MOBILENETV2 WITH OPTIMIZED PERFORMANCE,” JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer), vol. 11, no. 1, pp. 180–191, Aug. 2025, doi: 10.33480/jitk.v11i1.6497.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Wadzifa Wadzifa, Deasy Purwaningtias, Ali Mustopa
This work is licensed under a Creative Commons Attribution 4.0 International License.
