Klasifikasi Penyakit Daun Bawang Menggunakan Algoritma CNN Xception
DOI:
https://doi.org/10.29407/inotek.v8i1.5011Abstract
Daun bawang (Allium fistulosum) merupakan komoditas penting dalam pertanian, namun produktivitasnya sering terhambat oleh penyakit. Deteksi dini penyakit daun bawang sangat penting untuk mengurangi dampak negatifnya. Penelitian ini menggunakan metode Convolutional Neural Network (CNN) arsitektur Xception untuk klasifikasi penyakit daun bawang. Data dikumpulkan, model dilatih dengan parameter seperti batch size 16, epoch 100, dropout 0,2, learning rate 0,00001, dan optimizer Adam. Hasil pelatihan menunjukkan akurasi training 100% dan validasi 95%. Evaluasi dengan confusion matrix menunjukkan akurasi 100% pada data uji. Model Xception terbukti efektif dalam klasifikasi penyakit daun bawang merah, dengan akurasi tinggi dan kemampuan generalisasi yang baik. Hasil ini menunjukkan potensi penerapan AI dalam meningkatkan produktivitas pertanian melalui deteksi dini penyakit tanaman.
Keywords:
Daun Bawang, Klasifikasi, CNN, Xception##plugins.themes.default.displayStats.downloads##
References
M. I. Wahid, A. Lawi, dan A. M. A. Siddik, “Perbandingan Kinerja Model Ensembled Transfer Learning Pada Klasifikasi Penyakit Daun Tomat,” in Seminar Nasional Teknik Elektro dan Informatika (SNTEI), 2023, hal. 286–291.
F. F. Masaugi, F. Yanto, E. Budianita, S. Sanjaya, dan F. Syafria, “Deep Learning Menggunakan Algoritma Xception dan Augmentasi Flip Pada Klasifikasi Kematangan Sawit,” KLIK Kaji. Ilm. Inform. dan Komput., vol. 4, no. 6, hal. 2918–2927, 2024.
M. T. A. S. Ahmad dan B. Sugiarto, “Implementasi Convolutional Neural Network (CNN) untuk Klasifikasi Ikan Cupang Berbasis Mobile,” Digit. Transform. Technol., vol. 3, no. 2, hal. 792–803, 2023.
S. Sriyati, A. Setyanto, dan E. E. Luthfi, “Literature Review: Pengenalan Wajah Menggunakan Algoritma Convolutional Neural Network,” J. Teknol. Inf. Dan Komun., vol. 8, no. 2, 2020.
N. D. Girsang, “Literature study of convolutional neural network algorithm for batik classification,” Brill. Res. Artif. Intell., vol. 1, no. 1, hal. 1–7, 2021.
J. Lu, L. Tan, dan H. Jiang, “Review on convolutional neural network (CNN) applied to plant leaf disease classification,” Agriculture, vol. 11, no. 8, hal. 707, 2021.
J. Hang, D. Zhang, P. Chen, J. Zhang, dan B. Wang, “Classification of plant leaf diseases based on improved convolutional neural network,” Sensors, vol. 19, no. 19, hal. 4161, 2019.
R. Mawarni, R. Wulanningrum, dan R. Helilintar, “Implementasi Metode CNN Pada Klasifikasi Penyakit Jagung,” in Prosiding SEMNAS INOTEK (Seminar Nasional Inovasi Teknologi), 2023, hal. 1256–1263.
F. Chollet, “Xception: Deep learning with depthwise separable convolutions,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2017, hal. 1251–1258.
L. Dang, P. Pang, dan J. Lee, “Depth-wise separable convolution neural network with residual connection for hyperspectral image classification,” Remote Sens., vol. 12, no. 20, hal. 3408, 2020.
R. Radikto, D. I. Mulyana, M. A. Rofik, dan M. O. Z. Zakaria, “Klasifikasi Kendaraan pada Jalan Raya menggunakan Algoritma Convolutional Neural Network (CNN),” J. Pendidik. Tambusai, vol. 6, no. 1, hal. 1668–1679, 2022.
Downloads
Published
Issue
Section
License
Copyright (c) 2024 M. Farij Amrulloh, Danar Putra Pamungkas
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Copyright on any article is retained by the author(s).
- The author grants the journal, right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work’s authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal’s published version of the work (e.g., post it to an institutional repository or publish 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) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
- The article and any associated published material is distributed under the Creative Commons Attribution-ShareAlike 4.0 International License
