Augmentasi Data berbasis GAN dan Ekstraksi Fitur EfficientNetB0 dengan XGBoost untuk Meningkatkan Klasifikasi Penyakit Daun Jagung
Authors
-
Ririn Anugerah Ikasatya
Universitas Bumigora
-
Cahya Apriliani
Universitas Bumigora
-
Fathir Jannatul Firdaus
Universitas Bumigora
-
Gede Yogi Pratama
Universitas Bumigora
DOI:
https://doi.org/10.30812/upgrade.v3i2.6224Keywords:
Corn Leaf Disease, DC-GAN, EfficientNetB0, Image Classification, XGBoostAbstract
Corn leaf diseases are one of the main factors contributing to decreased corn productivity. Manual identification of leaf diseases remains subjective, time-consuming, and highly dependent on individual experience. This study aims to improve the performance of image-based corn leaf disease classification through the integration of data balancing techniques, deep feature extraction, and machine learning-based classification methods. The dataset consists of four classes with an imbalanced distribution, namely Blight with 802 images, Common Rust with 914 images, Gray Leaf Spot with 401 images, and Healthy with 813 images, where Gray
Leaf Spot represents the minority class. Data balancing is performed by generating synthetic images using a convolution-based generative model to increase the number of samples in the minority class. Furthermore, feature extraction is carried out using the EfficientNetB0 architecture, and classification is performed using a gradient boosting-based algorithm. There sults show that the proposed approach improves accuracy from 92.49 percent to 93.29 percent and enhances the model’s ability to recognize the minority class, as indicated by an increase in recall from 69 percent to 78 percent and an improvement in performance balance from 0.76
to 0.84. These findings indicate that the proposed method is effective in improving classification performance, particularly for the minority class, without reducing performance on majority classes.
References
Aisyah, A. S., Nadhiroh, A. Y., and Fajri, F. N. (2025). Klasifikasi Penyakit Daun Jagung Menggunakan Convolutional Neural Network Arsitektur Xception Berbasis Web. AL-ULUM: Multidisciplinary Journal Of Sciences, 01(03):227–237.
Andhika, A. R. and Bayunanda, E. (2025). Studi Literature Review Pemanfaatan Machine Learning dalam Multisektor. Integrative Perspectives of Social and Science Journal (IPSSJ), 2(3):6865–6880.
Andriani, T. and Iqbal, M. (2025). Penggunaan Transfer Learning untuk Peningkatan Akurasi Deteksi Penyakit Tanaman. Jatilima : Jurnal Multimedia Dan Teknologi Informasi Volume, 07(02):90–95. https://doi.org/10.54209/jatilima.v7i02.1448.
Annisa, R., Mardiana, Martinus, Putri, R. A. M., Febriyani, C., and Afif, M. (2024). Pengembangan Model Klasifikasi Citra Tanaman Hutan Melicopelatifolia Berbasis CNN dengan Custom-Built Dataset. JUKI : Jurnal Komputer dan Informatika, 6:174–181.
Ardianto, R. and Wibisono, S. K. (2023). Analisis Deep Learning Metode Convolutional Neural Network Dalam Klasifikasi Varietas Gandum. Jurnal Kolaboratif Sains, 6(12):2081–2092. https: //doi.org/10.56338/jks.v6i12.4938.
Aryanti, A., Apriliani, D., Putri, W. Z., Ramadhani, D., Malinda, T., and Andreansyah, D. (2025). Identifikasi CNN dalam Deteksi Penyakit Daun Jagung Berbasis Pengenalan Gambar. MIND (Multimedia Artificial Intelligent Networking Database) Journal MIND, 10(2):195–205. https://doi.org/10.26760/mindjournal.v10i2.195-205.
Batubara, N. P., Widiyanto, D., and Chamidah, N. (2020). Klasifikasi Rempah Rimpang Berdasarkan Ciri Warna RGB Dan Tekstur GLCM Menggunakan Algoritma Naive Bayes. JURNAL INFORMATIK, 16(3):156–163. https://doi.org/10.52958/iftk.v16i3.2196.
Burhanuddin, M. I., Syaifullah, A., Jaya, S. P. A., and Somoal, M. G. (2025). Analisis Komparatif Model MobilenetV1 Dan EfficientnetB0 Dalam Klasifikasi Citra Empat Musim Menggunakan Transfer Learning. Jurnal Teknik Informatika, 5(2):508–521. https://doi.org/10.58794/jekin.v5i2. 1378.
Erlin, Desnelita, Y., Nasution, N., Suryati, L., and Zoromi, F. (2022). Dampak SMOTE terhadap Kinerja Random Forest Classifier berdasarkan Data Tidak seimbang Impact of SMOTE on Random Forest Classifier Performance based on Imbalanced Data. Matrik: Jurnal Managemen,Teknik Informatika, dan Rekayasa Komputer, 21(3):667–690. https://doi.org/10.30812/matrik.v21i3.1726.
Hartono, A., Fitriyah, H., and Widasari, E. R. (2023). Sistem Deteksi Tomat Matang Hidroponik berdasarkan Warna Hue , Saturation dan Value menggunakan Metode Threshold berbasis Graphical User Interface. Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer, 7(5):2313–2319. https://doi.org/10.46764/teknimedia.v5i2.220.
Ht. Barat, A. I. R., Astuti, W. S. A., Wanto, A., and Solikhun, S. (2025). Optimisasi VGG16 dengan Transfer Learning dalam Mendeteksi Penyakit Pada Daun Jagung. Bulletin of Computer Science Research, 5(5):1049–1058. https://doi.org/10.47065/bulletincsr.v5i5.631.
Husen, D. (2024). Evaluasi Teknik Augmentasi Data Untuk Klasifikasi Tumor Otak Menggunakan CNN Pada Citra MRI. TEKNIMEDIA, 5(2):219–227. https://doi.org/10.46764/teknimedia.v5i2.220.
Jiven, F. F. and Rumini (2025). MRI Classification of Brain Tumors Using EfficientNetB0 Feature Extraction and Machine Learning Methods. Journal of Applied Informatics and Computing (JAIC), 9(6):3394–3404. https://doi.org/10.30871/jaic.v9i6.10363.
Kurniawan, I. R., Fakhrizal, I. U., Cahyadewi, F. A., and Saputra, F. D. (2025). Pengaruh Penambahan Arsitektur Model dalam Klasifikasi Citra Bencana Alam Menggunakan Ensemble Learning. JURNAL FASILKOM, 15(2):280–289. https://doi.org/10.37859/jf.v15i2.9103.
Melia, F., Aldian, F. M., Pahlevi, M. S. F., Naufal, R., Risqullah, I., and Oktaffiani, S. (2023). Peran Pemerintah dalam Meningkatkan Volume Ekspor Jagung. Jurnal economina, 2:270–284. https://doi.org/10.55681/economina.v2i1.287.
Patmawati, Sunyoto, A., and Luthfi, E. T. (2023). Augmentasi Data Menggunakan DCGAN pada Gambar Tanah. TEKNIMEDIA, 4(1):45–52. https://doi.org/10.46764/teknimedia.v4i1.100.
Prasetyo, M. B. and Wulaningrum, R. (2023). Deteksi Penyakit Tanaman Jagung Berbasis Pengolahan Citra Digital Menggunakan Metode Color Moments dan GLCM. INOTEK, 7:148–156. https: //doi.org/10.29407/inotek.v7i1.3422.
Prayesy, P. A. (2025). Studi Perbandingan Metode Support Vector Machine, Random Forest, dan Convolutional Neural Network untuk Klasifikasi Penyakit Kulit. Jurnal Kecerdasan Buatan dan Teknologi Informasi Vol., 4(1):70–76. https://doi.org/10.69916/jkbti.v4i1.214STUDI.
Purba, M. (2025). Klasifikasi Jenis Daun Tanaman Tropis Menggunakan Model ResNet50 Berbasis Transfer Learning dengan Dataset Tropical Plant Leaf. JCOSIS (Journal Computer Science and Information Syetem), (2):51–57. https://doi.org/10.61567.
Putra, I. P. and Alamsyah, D. (2022). Klasifikasi Penyakit Daun Jagung Menggunakan Metode Convolutional Neural Network. Jurnal Algoritme, 2(2):102–112. https://doi.org/10.35957/algoritme.v2i2.2360.
Rahmanita, E., Negara, Y. D. P., Kustiyahningsih, Y., Sasmeka, V., and Khotimah, B. K. (2023). Imple mentasi Metode Naive Bayes dan Information Gain Untuk Klasifikasi Penyakit dan Hama Tanaman Jagung Implementation of Naive Bayes Method and Information Gain for Classification of Diseases and Pests of Corn Plants. TEKNIKA, 12(November):198–204. https://doi.org/10.34148/teknika. v12i3.684.
Ryanto, S. S. and Sari, I. P. (2024). Optimasi Rekonstruksi Dan Pengenalan Wajah Berbasis Generative Adversarial Network ( GAN ) Dan CNN. JEKIN (Jurnal Teknik Informatika) Generative, 4(3):769–777.https://doi.org/10.58794/jekin.v4i3.1081.
Sarah, S. and Guntaro (2023). Identifikasi Penyakit Tanaman Jagung Berdasarkan Citra Daun Tinjauan Literatur Sistematis (SLR). Prosiding-Seminar Nasional Teknologi Informasi & Ilmu Komputer (SEMASTER), 2(1):278–289.
Sarasati, F., Nugraha, F. S., and Radiyah, U. (2022). Pemanfaatan Metode Deep Learning untuk Klasifikasi Penyakit pada Tanaman Jagung. Jurnal Infortech, 4(2):133–138.
Suhesi, Kurnia, D. A., Wijaya, Y. A., Anwar, S., and Hayati, U. (2025). Peningkatan Robustness Model Klasifikasi Penyakit Daun Semangka Menggunakan Fine-Tuning Vgg16 dan Augmentasi Data Sintetis Berbasis Generative Adversarial Network. Journal Of Computer Science and Artificial Intelligence (JCSAI), 06(02):1–8. https://doi.org/10.32485/jcsai.Kata.
Tirta, M. S., Kurniawan, R., and Zulius, A. (2025). Model Transfer Learning Dalam Klasifikasi Penyakit Daun Jagung Menggunakan Arsitektur Densenet-201. Jurnal of Informatics, Electrical and Electronics Engineering, 4(3):91–99. https://doi.org/10.47065/jieee.v4i3.2347.
Tono, Ariani, M., and Suryana, A. (2023). Kinerja Ketahanan Pangan Indonesia : Pembelajaran Dari Penilaian dengan Kriteria Global dan Nasional. Analisis Kebijakan Pertanian, 21(1):1–20. https://doi.org/10.21082/akp.v21n1.2023.1-20
Wildah, S. K., Latif, A., and Haryanto, T. (2024). Sintesa Citra Daun Kopi Menggunakan Generative Adversarial Network pada Dataset Penyakit Daun Kopi. INTI NUSA MANDIRI, 19(1):23–30. https://doi.org/10.33480/inti.v19i1.5045.
Wirabowo, I. and Susilawati, I. (2025). Implementasi Convolution Neural Network ( CNN ) untuk Deteksi Penyakit pada Daun Jagung Berbasis Citra Digital. Jurnal Pustaka Data, 5(1):233–241.
You, A., Kim, J. K., Ryu, I. H., and Yoo, T. K. (2022). Application of generative adversarial networks (GAN) for ophthalmology image domains : a survey. Eye and Vision, 9(6):2–19. https://doi.org/ 10.1186/s40662-022-00277-3.
Yulianti, S. E. H., Soesanto, O., and Sukmawaty, Y. (2022). Penerapan Metode Extreme Gradient Boosting ( XGBOOST ) pada Klasifikasi Nasabah Kartu Kredit. JOMTA: Journal of Mathematics: Theory and Applications, 4(1):21–26. https://doi.org/10.31605/jomta.v4i1.1792.
Yuninsar, E., Hasmin, E., and Samsie, I. (2024). Analisis Perbandingan Metode Convolutional Neural Network (CNN) dan Artificial Neural Network (ANN) dalam Klasifikasi Penyakit Daun Jagung. Jurnal Ilmiah Betrik, 15(03):321–333. https://doi.org/10.36050/kx56ex79.
