Klasifikasi Citra Berbasis Hybrid ResNet50–Broad Learning System pada Penyakit Daun Sawi Hijau
DOI:
https://doi.org/10.54065/artificial.2009Keywords:
Broad Learning System, Deep Learning, Klasifikasi Citra, Penyakit Daun Sawi Hijau, ResNet50Abstract
Penyakit pada daun sawi hijau dapat menurunkan kualitas tanaman, sementara identifikasi berdasarkan gejala visual secara manual berpotensi mengalami kesalahan, terutama pada penyakit yang memiliki karakteristik gejala serupa. Penelitian ini bertujuan mengembangkan dan mengevaluasi model hybrid ResNet50–Broad Learning System (BLS) untuk mengklasifikasikan citra daun sawi hijau ke dalam tiga kelas, yaitu bercak daun, busuk daun, dan daun sehat. Data yang digunakan berjumlah 1.937 citra yang diperoleh dari Kaggle, terdiri atas 1.173 citra data latih, 414 citra validasi, dan 350 citra uji. Tahapan penelitian meliputi preprocessing, augmentasi citra, ekstraksi fitur menggunakan ResNet50 dengan bobot ImageNet, standardisasi fitur menggunakan StandardScaler, dan klasifikasi menggunakan BLS. Kinerja model dievaluasi menggunakan akurasi, precision, recall, F1-score, dan confusion matrix. Hasil pengujian terhadap 350 citra menunjukkan bahwa model mencapai akurasi sebesar 94% dengan macro average F1-score sebesar 0,94. Kelas daun sehat memperoleh F1-score tertinggi sebesar 0,98, sedangkan kelas bercak daun dan busuk daun masing-masing memperoleh F1-score sebesar 0,91 dan 0,92. Kesalahan klasifikasi terutama terjadi antara kelas bercak daun dan busuk daun. Hasil tersebut menunjukkan bahwa kombinasi ResNet50–BLS mampu memberikan kinerja klasifikasi yang baik dan berpotensi mendukung identifikasi penyakit daun sawi hijau berbasis citra.
References
Bagga, M., & Goyal, S. (2024). Image-based detection and classification of plant diseases using deep learning: State-of-the-art review. Urban Agriculture & Regional Food Systems, 9, e20053. https://doi.org/10.1002/uar2.20053
Hafidurrohman, M., & Kusrini, K. (2025). Classification of mustard leaf diseases using convolutional neural network architecture. Journal of Electrical Engineering and Computer (JEECOM), 7(1), 1–6. https://doi.org/10.33650/jeecom.v7i1.10779
Huang, T., Li, H., Zhou, G., & Li, S. (2024). Stacking multi-view broad learning system with residual structures for classification. Information Sciences, 671, Artikel 120559. https://doi.org/10.1016/j.ins.2024.120559
Ji, Z., Bao, S., Chen, M., & Wei, L. (2024). ICS-ResNet: A Lightweight Network for Maize Leaf Disease Classification. Agronomy, 14(7), 1587. https://doi.org/10.3390/agronomy14071587
Jin, J., Chang, S., Duan, J., Li, Y., Ding, W., Wang, Z., Chen, C. L. P., & Li, P. (2025). Groupwise label enhancement Broad Learning System for image classification. IEEE Transactions on Cybernetics, 55(7), 3431–3444. https://doi.org/10.1109/TCYB.2025.3550175
Krishnakumar, D. P., & Balasubrahmanyan, K. (2024). An improved EigenGAN-based method for data augmentation for plant disease classification. Revue d’Intelligence Artificielle, 38(1), 237–242. https://doi.org/10.18280/ria.380124
Kurniawan, R., Sunardi, L., Intan, B., Elsi, Z. R. S., & Mohamad, F. S. (2026). A comprehensive evaluation of broad learning system for deep feature- based chili leaf disease classification. Communications in Science and Technology, 11(1), 138–149. https://doi.org/10.21924/cst.11.1.2026.1997
Liang, J., & Jiang, W. (2023). A ResNet50-DPA model for tomato leaf disease identification. Frontiers in Plant Science, 14, Artikel 1258658. https://doi.org/10.3389/fpls.2023.1258658
Lin, Y., Yu, Z., Yang, K., Fan, Z., & Chen, C. L. P. (2024). Boosting adaptive weighted broad learning system for multi-label learning. IEEE/CAA Journal of Automatica Sinica, 11(11), 2204–2219. https://doi.org/10.1109/JAS.2024.124557
Muslih, & Krismawan, A. D. (2024). Tomato leaf diseases classification using convolutional neural networks with transfer learning ResNet-50. Kinetik, 9(2), 149–158. https://doi.org.10.22219/kinetik.v9i2.1939
Pacal, I., Kunduracioglu, I., Alma, M. H., Deveci, M., Kadry, S., Nedoma, J., Slany, V., & Martínek, R. (2024). A systematic review of deep learning techniques for plant diseases. Artificial Intelligence Review, 57, Artikel 453. https://doi.org/10.1007/s10462-024-10944-7
Rachmad, A., Mufarroha, F. A., Rochman, E. M. S., Syakur, M. A., Solihin, F., & Asmara, Y. P. (2025). The impact of convolutional layer selection in ResNet-50v2 architecture on corn leaf disease classification. Ingénierie des Systèmes d’Information, 30(6), 1509–1515. https://doi.org/10.18280/isi.300609
Rehman, S., Khan, M. A., Alhaisoni, M., Armghan, A., Alenezi, F., Alqahtani, A., & lainnya. (2023). Fruit leaf diseases classification: A hierarchical deep learning framework. Computers, Materials & Continua, 75(1), 1179–1194. https://doi.org/10.32604/cmc.2023.035324
Rismawati, R., & Nuhardin , I. . (2023). Pengembangan dan Uji Kinerja Alat Pencacah Nilam dengan Rekayasa Nilai . Journal Artificial: Informatika Dan Sistem Informasi, 1(2), 60–69. https://doi.org/10.54065/artificial.406
Sajitha, P., Andrushia, A. D., Anand, N., & Naser, M. Z. (2024). A review on machine learning and deep learning image-based plant disease classification for industrial farming systems. Journal of Industrial Information Integration, 38, Artikel 100572. https://doi.org/10.1016/j.jii.2024.100572
Sandora, R., Hidayat, A. T., Intan, B., & Daulay, N. K. (2026). Deteksi Penyakit Tanaman Apel Berdasarkan Citra Digital Menggunakan Broad Learning System (BLS). JUTIM (Jurnal Teknik Informatika Musirawas), 11(1), 40–53. https://doi.org/10.32767/jutim.v11i1.2950
Sya'roni, W., Abdillah, Y. A., Arifin, S., & Hibatullah, R. (2025). Klasifikasi penyakit daun sawi menggunakan VGG19 berbasis citra digital. TRILOGI: Jurnal Ilmu Teknologi, Kesehatan, dan Humaniora, 6(3), 270–280. https://doi.org/10.33650/trilogi.v6i3.12106
Wafda, A. (2024). Artificial Intelligence dalam Prediksi dan Manajemen Bencana: Tinjauan Literatur Komprehensif. Journal Artificial: Informatika Dan Sistem Informasi, 2(1), 10–24. https://doi.org/10.54065/artificial.542
Xie, F., Wang, R., Jin, C., & Wang, G. (2024). Hyperspectral image classification based on superpixel merging and broad learning system. The Photogrammetric Record, 39, 435–456. https://doi.org/10.1111/phor.12493
Yi, L., Lv, D., Liu, D., Li, S., & Liu, R. (2024). Self-Training-Transductive-Learning Broad Learning System (STTL-BLS): A model for effective and efficient image classification. Pattern Recognition, 156, Artikel 110747. https://doi.org/10.1016/j.patcog.2024.110747
Younes, Z. Y., & Alsaadi, E. M. T. A. (2024). A review on plant leaf disease classification using deep learning. Iraqi Journal of Science, 65(11), 6738–6752. https://doi.org/10.24996/ijs.2024.65.11.43
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Mutia Salsabilla, Andri Anto Tri Susilo, Lukman Hakim, Bunga Intan
This work is licensed under a Creative Commons Attribution 4.0 International License.
License and Copyright Agreement
- Authors retain copyright and other proprietary rights related to the article.
- Authors retain the right and are permitted to use the substance of the article in their own future works, including lectures and books.
- Authors grant the journal the right of first publication with the work simultaneously licensed under Creative Commons Attribution License (CC BY 4.0) 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 or self-archive 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.
