Edge-optimized multimodal cross-fusion architecture for efficient crop disease detection

Thomas Kinyanjui Njoroge, Kelvin Mugoye Shindu & Rachael Kibuku

Volume 5 Issue 2, June 2025

Abstract

Accurate and timely crop disease detection is critical for reducing agricultural losses and ensuring food security in low-resource settings. Traditional diagnostic methods, such as manual inspections, are often inefficient and error-prone. Existing deep learning models (e.g., ResNet50, Inception V3) struggle with computational inefficiency and poor generalizability in real-world farming contexts. This study proposes a lightweight multimodal fusion model integrating EfficientNetV2 and MobileNetV2, optimized for edge deployment. The architecture leverages compound scaling and feature fusion to recognize subtle disease patterns, and it was fine-tuned on a globally diverse dataset (PlantVillage and field-collected leaf images). The proposed model achieved state-leading metrics (99.0% accuracy, 0.993 precision, 0.990 F1-score, AUC = 0.999997), outperforming benchmarks like ShuffleNet and DenseNet50 (ranked 2nd–6th). Statistical validation via the Kruskal-Wallis test confirmed significant performance differences across models (H=614.90, p=1.4237e−129), with Bayesian analysis showing a 100% superiority probability over DenseNet50. Notably, the model exhibited the lowest confidence variance (0.000012) compared to alternatives (0.000014–0.000032), demonstrating unmatched prediction stability. Deployment on low-end mobile devices posed challenges such as computational constraints and offline usability. However, the TensorFlow Lite-powered mobile app addressed these limitations, offering real-time, offline disease classification with 0.094-second inference latency on devices with ≤2GB RAM. Validated on 249 unseen field images (95.98% accuracy), this solution bridges the gap between high-performance deep learning and real-world agricultural needs, empowering smallholder farmers with an accessible and scalable tool.

Keywords

Author information & Contribution

Thomas Kinyanjui Njoroge. Corresponding author. Department of Computer Science and Informatics, Karatina University, Kenya. Email: tnjoroge@karu.ac.ke

Kelvin Mugoye Shindu. Software Development & Information Systems (SD&IS) Department, School of Technology, KCA University, Kenya.

Rachael Kibuku. Software Development & Information Systems (SD&IS) Department, School of Technology, KCA University, Kenya.

"All authors contributed equally to the conception, design, preparation, data gathering and analysis, and manuscript writing. All authors read and approved the final manuscript."

Disclosure statement

Funding

Institutional Review Board Statement

AI Declaration

Notes

Acknowledgement

References

Abbasi, R., Martinez, P., & Ahmad, R. (2023). Automated visual identification of foliage chlorosis in lettuce grown in aquaponic systems. Agriculture (Switzerland), 13(3). https://doi.org/10.3390/agriculture13030615

Abdu, A. M., Mokji, M. M., & Sheikh, U. U. (2020a). Machine learning for plant disease detection: An investigative comparison between support vector machine and deep learning. IAES International Journal of Artificial Intelligence, 9(4), 670–683. https://doi.org/10.11591/ijai.v9.i4.pp670-683

Abdu, A. M., Mokji, M. M., & Sheikh, U. U. (2020b). Machine learning for plant disease detection: An investigative comparison between support vector machine and deep learning. IAES International Journal of Artificial Intelligence, 9(4), 670–683. https://doi.org/10.11591/ijai.v9.i4.pp670-683

Amin, H., Darwish, A., Hassanien, A. E., & Soliman, M. (2022). End-to-end deep learning model for corn leaf disease classification. IEEE Access, 10, 31103–31115. https://doi.org/10.1109/ACCESS.2022.3159678

Bi, C., Xu, S., Hu, N., Zhang, S., Zhu, Z., & Yu, H. (2023). Identification method of corn leaf disease based on improved Mobilenetv3 model. Agronomy, 13(2). https://doi.org/10.3390/agronomy13020300

Chao, X., Sun, G., Zhao, H., Li, M., & He, D. (2020). Identification of apple tree leaf diseases based on deep learning models. Symmetry, 12(7). https://doi.org/10.3390/sym12071065

Dong, K., Zhou, C., Ruan, Y., & Li, Y. (2020). MobileNetV2 model for image classification. Proceedings – 2020 2nd International Conference on Information Technology and Computer Application, ITCA 2020, 476–480. https://doi.org/10.1109/ITCA52113.2020.00106

Kaleem, M. K., Purohit, N., Azezew, K., & Asemie, S. (2021). A modern approach for detection of leaf diseases using image processing and ML Based SVM classifier. Turkish Journal of Computer and Mathematics Education, 12(13).

Kemi Afolabi-Yusuf, G., Arjun, G., A, O. B., O, O. Y., K, A. G., Muhammed, B. F., & M, A. A. (2022). Computer vision-based plant disease identification system: A review. AAN Journal of Sciences, Engineering & Technology, 1(1), 59-78.

Liu, L., Qiao, S., Chang, J., Ding, W., Xu, C., Gu, J., Sun, T., & Qiao, H. (2024). A multi-scale feature fusion neural network for multi-class disease classification on the maize leaf images. Heliyon, 10(7). https://doi.org/10.1016/j.heliyon.2024.e28264

Liu, Y., Wei, C., Yoon, S. C., Ni, X., Wang, W., Liu, Y., Wang, D., Wang, X., & Guo, X. (2024). Development of multimodal fusion technology for tomato maturity assessment. Sensors, 24(8). https://doi.org/10.3390/s24082467

Mi, Z., Zhang, X., Su, J., Han, D., & Su, B. (2020). Wheat stripe rust grading by deep learning with attention mechanism and images from mobile devices. Frontiers in Plant Science, 11. https://doi.org/10.3389/fpls.2020.558126

Mohammed, L., & Yusoff, Y. (2023). Detection and classification of plant leaf diseases using digital image processing methods: A review. ASEAN Engineering Journal, 13(1), 1–9. https://doi.org/10.11113/aej.V13.17460

Mousavi, S., & Farahani, G. (2022). A novel enhanced VGG16 model to tackle grapevine leaves diseases with automatic method. IEEE Access, 10, 111564–111578. https://doi.org/10.1109/ACCESS.2022.3215639

Nguyen, H. T., Luong, H. H., Huynh, L. B., Le, B. Q. H., Doan, N. H., & Le, D. T. D. (2023). An improved MobileNet for disease detection on tomato leaves. Advances in Technology Innovation, 8(3), 192–209. https://doi.org/10.46604/aiti.2023.11568

Önler, E. (2023). Feature fusion-based artificial neural network model for disease detection of bean leaves. Electronic Research Archive, 31(5), 2409–2427. https://doi.org/10.3934/era.2023122

Rajeena P. P, F., S. U, A., Moustafa, M. A., & Ali, M. A. S. (2023). Detecting plant disease in corn leaf using EfficientNet architecture—An analytical approach. Electronics (Switzerland), 12(8). https://doi.org/10.3390/electronics12081938

Sala, F., Popescu, C. A., Herbei, M. V., & Rujescu, C. (2020). Model of color parameters variation and correction to “Time-View” image acquisition effects in wheat crop. Sustainability (Switzerland), 12(6). https://doi.org/10.3390/su12062470

Saleem, M. H., Potgieter, J., & Arif, K. M. (2020). Plant disease classification: A comparative evaluation of convolutional neural networks and deep learning optimizers. Plants, 9(10), 1–17. https://doi.org/10.3390/plants9101319

Sarker, I. H. (2021). Deep learning: A comprehensive overview on techniques, taxonomy, applications and research directions. SN Computer Science, 2(6). https://doi.org/10.1007/s42979-021-00815-1

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. https://doi.org/10.1155/2016/3289801

Ulutaş, H., & Aslantaş, V. (2023). Design of efficient methods for the detection of tomato leaf disease utilizing proposed ensemble CNN model. Electronics (Switzerland), 12(4). https://doi.org/10.3390/electronics12040827

Vellaichamy, A. S., Swaminathan, A., Varun, C., & S, K. (2021). Multiple plant leaf disease classification using Densenet-121 architecture. International Journal of Electrical Engineering and Technology, 12(5). https://doi.org/10.34218/ijeet.12.5.2021.005

Zhao, Z., Alzubaidi, L., Zhang, J., Duan, Y., & Gu, Y. (2024). A comparison review of transfer and self-supervised learning: Definitions, applications, advantages and limitations. In Expert Systems with Applications, 242. https://doi.org/10.1016/j.eswa.2023.122807

Zheng, Y. Y., Kong, J. L., Jin, X. B., Wang, X. Y., Su, T. L., & Zuo, M. (2019). Cropdeep: The crop vision dataset for deep-learning-based classification and detection in precision agriculture. Sensors (Switzerland), 19(5). https://doi.org/10.3390/s19051058

Cite this article:

Njoroge, T.K., Shindu, K.M. & Kibuku, R. (2025). Edge-optimized multimodal cross-fusion architecture for efficient crop disease detection. International Journal of Science, Technology, Engineering and Mathematics, 5(2), 1-37. https://doi.org/10.53378/ijstem.353186