پژوهش‌های مکانیک ماشینهای کشاورزی

پژوهش‌های مکانیک ماشینهای کشاورزی

A Lightweight Family of CNN-MLP Framework for Apple Leaf Disease Classification on Augmentation-Enhanced Heterogeneous Dataset

نوع مقاله : شماره ویژه انگلیسی

نویسندگان
فروغ احسانفر
فاطمه مویدی
مرکز آموزش عالی لارستان
10.22034/jrmam.2026.14992.763
چکیده
Accurate, computationally efficient classification of apple leaf diseases is essential to improving orchard productivity. Despite advances in deep learning, many existing models rely on intensive architectures that limit deployment in resource-constrained environments. This study proposes a lightweight CNN-MLP framework optimized for disease classification under heterogeneous visual conditions. Pre-trained ResNet-18 and EfficientNet-B0 backbones were utilized for feature extraction, with their original classification heads replaced by a task-specific, two-layer multilayer perceptron (MLP) head. This architectural adaptation, incorporating a 256-neuron hidden layer and dropout regularization, aims to enhance learning of non-linear boundaries in diverse datasets. An experimental evaluation on the 9-class AL9EE dataset, conducted across five independent runs, demonstrated that the EfficientNet-B0-MLP model achieved 98.42 ± 0.26% accuracy and a macro F1-score of 98.33 ± 0.34%, outperforming the ResNet-18-MLP variant. The lower standard deviations indicate improved training stability and reproducibility. By balancing predictive performance with reduced computational complexity, this framework provides a practical solution for edge-oriented agricultural applications, offering an effective pathway for intelligent disease monitoring in smart farming.
کلیدواژه‌ها
Apple leaf disease classification
Hybrid deep learning
EfficientNet-B0
ResNet-18
Lightweight deep learning Heterogeneous visual conditions
Agricultural Research Center of Iran. (2022). Survey on plant diseases in apple orchards. (In Persian).
 
Ali, H., Shifa, N., Benlamri, R., Farooque, A. A., & Yaqub, R. (2025). A fine tuned EfficientNet-B0 convolutional neural network for accurate and efficient classification of apple leaf diseases. Scientific Reports, 15(1), 25732.
   https://doi.org/10.1038/s41598-025-04479-2
 
Ali, M. U., Khalid, M., Farrash, M., Lahza, H. F. M., Zafar, A., & Kim, S. H. (2024). AppleLeafNet: A lightweight and efficient deep learning framework for diagnosing apple leaf diseases. Frontiers in Plant Science, 15, 1502314. https://doi.org/10.3389/fpls.2024.1502314
 
Anam, S. (2020). Segmentation of leaf spot disease in apple plants using particle swarm optimization and K-means algorithm. Journal of Physics: Conference Series, 1562, 012011. https://doi.org/10.1088/1742-6596/1562/1/012011
 
Ashmafee, M. H., Ahmed, T., Ahmed, S., Hasan, M. B., Jahan, M. N., & Rahman, A. A. (2023, February). An efficient transfer learning-based approach for apple leaf disease classification. In 2023 International Conference on Electrical, Computer and Communication Engineering (ECCE) (pp. 1-6). IEEE. https://doi.org/10.1109/ECCE57851.2023.10101542
 
Birant, D. (2024). PlantVillage dataset. Figshare. https://doi.org/10.6084/m9.figshare.26096800.v1
 
Bracino, A. A., Concepcion, R. S., Bedruz, R. A. R., Dadios, E. P., & Vicerra, R. R. P. (2020, December). Development of a hybrid machine learning model for apple (Malus domestica) health detection and disease classification. In 2020 IEEE 12th international conference on humanoid, nanotechnology, information technology, communication and control, environment, and management (HNICEM) (pp. 1-6). IEEE. https://doi.org/10.1109/HNICEM51456.2020.9400139
 
Chakraborty, S., Paul, S., & Rahat-uz-Zaman, M. (2021). Prediction of apple leaf diseases using multiclass support vector machine. In 2021 2nd International Conference on Robotics, Electrical and Signal Processing Techniques (ICREST) (pp. 1–6). https://doi.org/10.1109/ICREST51555.2021.9331132
 
Food and Agriculture Organization of the United Nations. (2025). FAOSTAT: Crops and livestock products. Retrieved August 30, 2025, from https://www.fao.org/faostat/en/#data
 
Fu, J., Li, S., Sun, Y., Mu, Y., Hu, T., & Gong, H. (2022). Lightweight CNN for apple leaf disease recognition. Frontiers in Plant Science, 13, 831219. https://doi.org/10.3389/fpls.2022.831219
 
He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 770–778). IEEE. https://doi.org/10.1109/CVPR.2016.90
 
Howard, J., & Gugger, S. (2020). Deep learning for coders with fastai & PyTorch. O’Reilly Media.
 
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.
 
Khan, M. A., Lali, M. I. U., Sharif, M., Javed, K., Aurangzeb, K., Haider, S. I., ... & Akram, T. (2019). An optimized method for segmentation and classification of apple diseases based on strong correlation and genetic algorithm based feature selection. IEEE Access, 7, 46261-46277.https://doi.org/10.1109/ACCESS.2019.2908040
 
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017). ImageNet classification with deep convolutional neural networks. Communications of the ACM, 60, 84–90. https://doi.org/10.1145/3065386
 
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., ... & Duchesnay, É. (2011). Scikit-learn: Machine learning in Python. the Journal of machine Learning research, 12, 2825-2830.Sai, A. M., &
 
Patil, N. (2022). Comparative analysis of machine learning algorithms for disease detection in apple leaves. In 2022 International Conference on Distributed Computing, VLSI, Electrical Circuits and Robotics (DISCOVER) (pp. 239–244). https://doi.org/10.1109/DISCOVER55800.2022.9974840
 
Szegedy, C., Ioffe, S., Vanhoucke, V., & Alemi, A. (2017, February). Inception-v4, inception-resnet and the impact of residual connections on learning. In Proceedings of the AAAI conference on artificial intelligence (Vol. 31, No. 1).
 
Tan, M., & Le, Q. V. (2019). EfficientNet: Rethinking model scaling for convolutional neural networks. In Proceedings of the 36th International Conference on Machine Learning (ICML) (pp. 6105–6114).
 
Zhu, F. (2023). AppleLeaf9-Enhanced Edition (AL9EE) dataset. Figshare. https://doi.org/10.6084/m9.figshare.23606010.v1