An Interpretable, Imbalance-Aware Ensemble for Citrus Leaf Disease Classification using DenseNet169 and MobileNetV2

Carmelo Alejo D. Bisquera^1, , Romeo P. Evangelista¹, Michael John R. Robles¹ and Von P. Gabayan Jr.¹

¹Department of Information Technology, College of Information Technology Education, Nueva Vizcaya State University, Bayombong Nueva Vizcaya

Cite this paper:
Carmelo Alejo D. Bisquera, Romeo P. Evangelista, Michael John R. Robles and Von P. Gabayan Jr.. An Interpretable, Imbalance-Aware Ensemble for Citrus Leaf Disease Classification using DenseNet169 and MobileNetV2. Journal of Computer Sciences and Applications. 2026; 14(1):8-14. doi: 10.12691/jcsa-14-1-2

Abstract

Citrus leaf diseases pose a significant threat to agricultural productivity, particularly in regions dependent on smallholder farming. Early and accurate detection is essential, yet traditional diagnostic methods are labor-intensive and prone to subjectivity. This study proposes a logit-level weighted ensemble framework integrating DenseNet169 and MobileNetV2 for automated citrus disease classification under class imbalance conditions. A publicly available dataset of 594 images across four classes was utilized, employing a stratified 70/30 train-validation split and class-weighted cross-entropy loss to address imbalance. Results show that MobileNetV2 achieved the highest macro F1-score (0.9417), outperforming DenseNet169 (0.9327) and the proposed ensemble (0.9283). This indicates that a well-optimized single model can outperform ensemble methods in terms of peak accuracy, particularly when predictions are highly correlated. However, the ensemble demonstrated smoother convergence and more stable validation performance, emphasizing its strength in improving training stability and prediction consistency. Grad-CAM visualization confirmed that models focused on biologically relevant lesion regions. The framework was implemented using CPU-based computation, demonstrating feasibility in resource-constrained environments. Overall, ensemble learning enhances stability even when peak accuracy gains are limited.

Keywords:
citrus leaf disease deep learning ensemble CNN Grad-CAM weighted fusion automated classification

This work is licensed under a Creative Commons Attribution 4.0 International License. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/

Figures

References:

[1]	Gomez, M., Reyes, A., & Santos, R. (2020). Economic contribution of citrus farming in the Philippines. Philippine Journal of Crop Science, 45(2), 23–34.
[2]	Bové, J. M. (2006). Huanglongbing: A destructive, newly-emerging, century-old disease of citrus. Journal of Plant Pathology, 88(1), 7–37.
[3]	da Graça, J. V., Douhan, G. W., Halbert, S. E., Keremane, M. L., Lee, R. F., Vidalakis, G., & Zhao, H. (2016). Huanglongbing: An overview of a complex pathosystem ravaging the world’s citrus. Journal of Integrative Plant Biology, 58(4), 373–387.
[4]	Gottwald, T. R. (2010). Current epidemiological understanding of citrus huanglongbing. Annual Review of Phytopathology, 48, 119–139.
[5]	Iftikhar, Y., Rauf, S., Shahzad, U., & Zahid, M. A. (2016). Huanglongbing: Pathogen detection system for integrated disease management—A review. Journal of the Saudi Society of Agricultural Sciences, 15(1), 1–11.
[6]	Butt, N., Iqbal, M. M., Ramzan, S., Raza, A., Abualigah, L., Fitriyani, N. L., Gu, Y., & Syafrudin, M. (2025). Citrus diseases detection using innovative deep learning approach and hybrid meta-heuristic. PLOS ONE, 20(1), e0316081.
[7]	Al-Hiary, H., Bani-Ahmad, S., Reyalat, M., Braik, M., & AlRahamneh, Z. (2011). Fast and accurate detection and classification of plant diseases. International Journal of Computer Applications, 17(1), 31–38.
[8]	Mahlein, A. K. (2016). Plant disease detection by imaging sensors—Parallels and specific demands for precision agriculture and plant phenotyping. Plant Disease, 100(2), 241–251.
[9]	Ferentinos, K. P. (2018). Deep learning models for plant disease detection and diagnosis. Computers and Electronics in Agriculture, 145, 311–318.
[10]	Mohanty, S. P., Hughes, D. P., & Salathé, M. (2016). Using deep learning for image-based plant disease detection. Frontiers in Plant Science, 7, 1419.
[11]	Too, E. C., Yujian, L., Njuki, S., & Yingchun, L. (2019). A comparative study of fine-tuning deep learning models for plant disease identification. Computers and Electronics in Agriculture, 161, 272–279.
[12]	Sladojevic, S., Arsenovic, M., Anderla, A., Culibrk, D., & Stefanovic, D. (2016). Deep neural networks-based recognition of plant diseases by leaf image classification. Computational Intelligence and Neuroscience, 2016, 3289801.
[13]	Brahimi, M., Boukhalfa, K., & Moussaoui, A. (2017). Deep learning for tomato diseases: Classification and symptoms visualization. Applied Artificial Intelligence, 31(4), 299–315.
[14]	Buda, M., Maki, A., & Mazurowski, M. A. (2018). A systematic study of the class imbalance problem in convolutional neural networks. Neural Networks, 106, 249–259.
[15]	Sun, X., Wang, Z., & Li, Y. (2019). Addressing class imbalance in plant disease datasets with weighted loss. Pattern Recognition Letters, 125, 105–111.
[16]	Zhou, C., Zhang, S., Xing, J., & Song, J. (2019). Citrus leaf disease recognition with a deep convolutional neural network. Smart Health, 14, 100064.
[17]	Pacal, I., Kunduracioglu, I., Alma, M. H., Deveci, M., Kadry, S., Nedoma, J., et al. (2024). A systematic review of deep learning techniques for plant diseases. Artificial Intelligence Review, 57(11), 304.
[18]	Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L. C. (2018). MobileNetV2: Inverted residuals and linear bottlenecks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 4510–4520).
[19]	Huang, G., Liu, Z., van der Maaten, L., & Weinberger, K. Q. (2017). Densely connected convolutional networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 4700–4708).
[20]	Ali, A. H., Youssef, A., Abdelal, M., & Raja, M. A. (2024). An ensemble of deep learning architectures for accurate plant disease classification. Ecological Informatics, 81, 102618.
[21]	Dietterich, T. G. (2000). Ensemble methods in machine learning. In J. Kittler & F. Roli (Eds.), Multiple classifier systems (Lecture Notes in Computer Science, Vol. 1857, pp. 1–15). Springer.
[22]	Shen, D., Wu, G., & Suk, H.-I. (2017). Deep learning in medical image analysis. Annual Review of Biomedical Engineering, 19(1), 221–248.
[23]	Apleni, T., Isinkaye, F. O., & Olusanya, M. O. (2025). A novel ensemble approach for crop disease detection by leveraging customized EfficientNets and interpretability. Pattern Recognition Letters, 197, 370–377.
[24]	Guo, C., Pleiss, G., Sun, Y., & Weinberger, K. Q. (2017). On calibration of modern neural networks. In Proceedings of the 34th International Conference on Machine Learning (pp. 1321–1330).
[25]	Mohammed, L., & Yusoff, Y. (2023). Detection and classification of plant leaf diseases using digital image processing methods: A review. ASEAN Engineering Journal.
[26]	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. In Proceedings of the IEEE International Conference on Computer Vision (pp. 618–626).