Klasifikasi Penyakit Tanaman Tomat dan Cabai Menggunakan Transfer Learning MobileNetV2 dengan Visualisasi Grad-CAM
DOI:
https://doi.org/10.65244/jggengineering.v2i2.750Keywords:
Klasifikasi Penyakit Tanaman, Transfer Learning, Mobilenetv2, Grad-CAM, Deep LearningAbstract
Penyakit tanaman merupakan salah satu faktor utama penurunan hasil pertanian pada komoditas tomat dan cabai di Indonesia. Deteksi dini secara manual memerlukan keahlian khusus dan waktu yang lama. Penelitian ini mengusulkan sistem klasifikasi penyakit tanaman berbasis deep learning menggunakan arsitektur MobileNetV2 dengan pendekatan transfer learning. Dataset PlantVillage yang terdiri dari 20.638 gambar daun dengan 15 kelas digunakan sebagai data pelatihan. Model dievaluasi menggunakan metrik accuracy, precision, recall, dan F1-score. Visualisasi Grad-CAM diterapkan untuk menginterpretasikan area fokus model dalam pengambilan keputusan. Hasil eksperimen menunjukkan akurasi sebesar 89,93% pada data uji dengan rata-rata weighted F1-score sebesar 0,90. Visualisasi Grad-CAM membuktikan model mengidentifikasi area terinfeksi secara akurat. Pengujian pada gambar nyata menunjukkan kemampuan model dalam kondisi dunia nyata.
Downloads
References
Agarwal, M., Singh, A., Arjaria, S., Nanda, A., & Gupta, S. (2020). ToLeD: Tomato leaf disease detection using convolution neural network. Procedia Computer Science, 167, 293-301.
Brahimi, M., Arsenovic, M., Laraba, S., Sladojevic, S., Boukhalfa, K., & Moussaoui, A. (2019). Deep learning for plant diseases: Detection and saliency map visualisation. Human and Machine Learning: Visible, Explainable, Trustworthy and Transparent, 93-117.
Ferentinos, K. P. (2018). Deep learning models for plant disease detection and diagnosis. Computers and Electronics in Agriculture, 145, 311-318.
Hughes, D., & Salathé, M. (2015). An open access repository of images on plant health to enable the development of mobile disease diagnostics. arXiv preprint arXiv:1511.08060.
Mohanty, S. P., Hughes, D. P., & Salathé, M. (2016). Using deep learning for image-based plant disease detection. Frontiers in Plant Science, 7, 1419.
Oerke, E. C. (2006). Crop losses to pests. The Journal of Agricultural Science, 144(1), 31-43.
Pan, S. J., & Yang, Q. (2010). A survey on transfer learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345-1359.
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L. C. (2018). MobileNetV2: Inverted residuals and linear bottlenecks. Proceedings of the IEEE CVPR, 4510-4520.
Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., & Batra, D. (2017). Grad-CAM: Visual explanations from deep networks via gradient-based localization. Proceedings of the IEEE ICCV, 618-626.
Tm, P., Pranathi, A., SaiAshritha, K., Chittaragi, N. B., & Koolagudi, S. G. (2018). Tomato leaf disease detection using convolutional neural networks. Proceedings of the 11th International Conference on Contemporary Computing (IC3), 1-5.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Ahmad Robi Faro'id, Agustin Maulidiah, Dea Angelina, Moch. Raditya Priyo Pambudi (Author)
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with Journal of Golden Generation Engineering agree to the following terms:
- Authors retain copyright and grant the Journal of Golden Generation Engineering right of first publication with the work simultaneously This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors can enter into separate, additional contractual arrangements for the non-exclusive distribution of the published version of the work (e.g., post it to an institutional repository or edit it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) before and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
