Comparative and edge-hybrid modeling of EfficientNetV2 and MobileNetV2 for multi-classcrop disease classification with statistical validation
Article Sidebar
Main Article Content
Abstract
Crop disease classification is critical for global food security, yet deploying accurate deep learning models on resource-constrained edge devices remains challenging. This study systematically compares EfficientNetV2 and MobileNetV2 while proposing an edge-optimised hybrid architecture integrating both with Vision Transformers (ViT). Evaluated on PlantVillage and field-collected images, MobileNetV2 demonstrated superior edge compatibility with 99.0% accuracy, 0.0938 s/image inference speed, minimal resources (30.38MB size), and statistical superiority (z-test p=0.0071). The hybrid model combines MobileNetV2’s texture analysis and Efficient-NetV2’s multiscale detection through a dual-branch architecture enhanced with SE blocks, ViT (16×16 patches), and attention-guided fusion. It achieved 99.5% test accuracy with real-time performance (0.15 s/image) and 97.97% field accuracy via Android deployment. Statistical validation confirmed robustness: Kruskal-Wallis H=597.40 (p<0.05), near-perfect AUC (0.999998), and minimal confidence variance (0.000010). Ablation studies verified architectural efficacy (98.68% accuracy with SE/gating modules). This work advances precision agriculture through a scalable framework unifying hybrid deep learning with edge-compatible deployment.
Downloads
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
How to Cite
References
Abasi, A.K., Makhadmeh, S.N., Alomari, O.A., Tubishat, M. and Mohammed, H.J., 2023. Enhancing Rice Leaf Disease Classification: A Customized Convolutional Neural Network Approach. Sustainability, 15(20), p.15039. Available from: https://doi.org/10.3390/su152015039.
Abdu, A., Mokji, M.M. and Sheikh, U.U., 2020. Machine learning for plant disease detection: an investigative comparison between support vector machine and deep learning. IAES International Journal of Artificial Intelligence (IJ-AI), 9(4), pp.670–683. Available from: https://doi.org/10.11591/ijai.v9.i4.pp670-683.
Barman, U., Sarma, P., Rahman, M., Deka, V., Lahkar, S., Sharma, V. and Saikia, M.J., 2024. ViT-SmartAgri: Vision Transformer and Smartphone-Based Plant Disease Detection for Smart Agriculture. Agronomy, 14(2), p.327. Available from: https://doi.org/10.3390/agronomy14020327.
Bernardes, R.C., De Medeiros, A., Silva, L. da, Cantoni, L., Martins, G.F., Mastrangelo, T., Novikov, A. and Mastrangelo, C.B., 2022. Deep-Learning Approach for Fusarium Head Blight Detection in Wheat Seeds Using Low-Cost Imaging Technology. Agriculture, 12(11), p.1801. Available from: https://doi.org/10.3390/agriculture12111801.
Cecaj, A., Lippi, M., Mamei, M. and Zambonelli, F., 2020. Comparing Deep Learning and Statistical Methods in Forecasting Crowd Distribution from Aggregated Mobile Phone Data. Applied Sciences, 10(18), p.6580. Available from: https://doi.org/10.3390/app10186580.
Chen, H.C., Widodo, A.M., Wisnujati, A., Rahaman, M., Lin, J.C.W., Chen, L. and Weng, C.E., 2022. AlexNet Convolutional Neural Network for Disease Detection and Classification of Tomato Leaf. Electronics, 11(6), p.951. Available from: https://doi.org/10.3390/electronics11060951.
Dai, Q., Guo, Y., Li, Z., Song, S., Lyu, S., Sun, D., Wang, Y. and Chen, Z., 2023. Citrus Disease Image Generation and Classification Based on Improved FastGAN and EfficientNet-B5. Agronomy, 13(4), p.988. Available from: https://doi.org/10.3390/agronomy13040988.
Dhaka, V.S., Meena, S.V., Rani, G., Sinwar, D., Kavita, Ijaz, M.F. and Wo´zniak, M., 2021. A Survey of Deep Convolutional Neural Networks Applied for Prediction of Plant Leaf Diseases. Sensors, 21(14), p.4749. Available from: https://doi.org/10.3390/s21144749.
Dong, H., Liu, R. and Tham, A.W., 2024. Accuracy Comparison between Five Machine Learning Algorithms for Financial Risk Evaluation. Journal of Risk and Financial Management, 17(2), p.50. Available from: https://doi.org/10.3390/jrfm17020050.
Dong, K., Zhou, C., Ruan, Y. and Li, Y., 2020. MobileNetV2 Model for Image Classification. 2020 2nd International Conference on Information Technology and Computer Application (ITCA). pp.476–480. Available from: https://doi.org/10.1109/ITCA52113.2020.00106.
Fang, X., Zhen, T. and Li, Z., 2023. Lightweight Multiscale CNN Model for Wheat Disease Detection. Applied Sciences, 13(9), p.5801. Available from: https://doi.org/10.3390/app13095801.
Ge, H., Ma, F., Li, Z., Tan, Z. and Du, C., 2021. Improved Accuracy of Phenological Detection in Rice Breeding by Using Ensemble Models of Machine Learning Based on UAV-RGB Imagery. Remote Sensing, 13(14), p.2678. Available from: https://doi.org/10.3390/rs13142678.
Ge, H., Wang, L., Pan, H., Liu, Y., Li, C., Lv, D. and Ma, H., 2024. Cross Attention-Based Multi-Scale Convolutional Fusion Network for Hyperspectral and LiDAR Joint Classification. Remote Sensing, 16(21), p.4073. Available from: https://doi.org/10.3390/rs16214073.
Glegoła, W., Karpus, A. and Przybyłek, A., 2021. MobileNet family tailored for Raspberry Pi. Procedia Computer Science, 192, pp.2249–2258. Available from: https://doi.org/10.1016/j.procs.2021.08.238.
Jia, L., Wang, T., Chen, Y., Zang, Y., Li, X., Shi, H. and Gao, L., 2023. MobileNet-CA-YOLO: An Improved YOLOv7 Based on the MobileNetV3 and Attention Mechanism for Rice Pests and Diseases Detection. Agriculture, 13(7), p.1285. Available from: https://doi.org/10.3390/agriculture13071285.
Karypidis, E., Mouslech, S., Skoulariki, K. and Gazis, A., 2022. Comparison Analysis of Traditional Machine Learning and Deep Learning Techniques for Data and Image Classification. WSEAS Transactions on Mathematics, 21, pp.122–130. Available from: https://doi.org/10.37394/23206.2022.21.19.
Kim, H.S., Choi, D., Yoo, D.G. and Kim, K.P., 2022. Hyperparameter Sensitivity Analysis of Deep Learning-Based Pipe Burst Detection Model for Multiregional Water Supply Networks. Sustainability, 14(21), p.13788. Available from: https://doi.org/10.3390/su142113788.
Liu, B.Y., Fan, K.J., Su, W.H. and Peng, Y., 2022. Two-Stage Convolutional Neural Networks for Diagnosing the Severity of Alternaria Leaf Blotch Disease of the Apple Tree. Remote Sensing, 14(11), p.2519. Available from: https://doi.org/10.3390/rs14112519.
Liu, Y., Liu, J., Cheng, W., Chen, Z., Zhou, J., Cheng, H. and Lv, C., 2023. A High-Precision Plant Disease Detection Method Based on a Dynamic Pruning Gate Friendly to Low-Computing Platforms. Plants, 12(11), p.2073. Available from: https://doi.org/10.3390/plants12112073.
Mamun, S.S., Ren, S., Rakib, M.Y.K. and Asafa, G.F., 2025. WGA-SWIN: Efficient Multi-View 3D Object Reconstruction Using Window Grouping Attention in Swin Transformer. Electronics, 14(8), p.1619. Available from: https://doi.org/10.3390/electronics14081619.
Nazir, T., Iqbal, M.M., Jabbar, S., Hussain, A. and Albathan, M., 2023. EfficientPNet — An Optimized and Efficient Deep Learning Approach for Classifying Disease of Potato Plant Leaves. Agriculture, 13(4), p.841. Available from: https://doi.org/10.3390/agriculture13040841.
Ojo, M.O. and Zahid, A., 2023. Improving Deep Learning Classifiers Performance via Preprocessing and Class Imbalance Approaches in a Plant Disease Detection Pipeline. Agronomy, 13(3), p.887. Available from: https://doi.org/10.3390/agronomy13030887.
Orchi, H., Sadik, M., Khaldoun, M. and Sabir, E., 2023. Automation of Crop Disease Detection through Conventional Machine Learning and Deep Transfer Learning Approaches. Agriculture, 13(2), p.352. Available from: https://doi.org/10.3390/agriculture13020352.
Padshetty, S. and Ambika, 2023. Leaky ReLU-ResNet for Plant Leaf Disease Detection: A Deep Learning Approach. Engineering Proceedings, 59(1), p.39. Available from: https://doi.org/10.3390/engproc2023059039.
Parez, S., Dilshad, N., Alghamdi, N.S., Alanazi, T.M. and Lee, J.W., 2023. Visual Intelligence in Precision Agriculture: Exploring Plant Disease Detection via Efficient Vision Transformers. Sensors, 23(15), p.6949. Available from: https://doi.org/10.3390/s23156949.
Phinzi, K., Abriha, D. and Szabó, S., 2021. Classification Efficacy Using K-Fold Cross-Validation and Bootstrapping Resampling Techniques on the Example of Mapping Complex Gully Systems. Remote Sensing, 13(15), p.2980. Available from: https://doi.org/10.3390/rs13152980.
Pineda Medina, D., Miranda Cabrera, I., Cruz, R.A. de la, Guerra Arzuaga, L., Cuello Portal, S. and Bianchini, M., 2024. A Mobile App for Detecting Potato Crop Diseases. Journal of Imaging, 10(2), p.47. Available from: https://doi.org/10.3390/jimaging10020047.
Saleem, M.H., Potgieter, J. and Arif, K.M., 2020. Plant Disease Classification: A Comparative Evaluation of Convolutional Neural Networks and Deep Learning Optimizers. Plants, 9(10), p.1319. Available from: https://doi.org/10.3390/plants9101319.
Saleem, S., Sharif, M.I., Sharif, M.I., Sajid, M.Z. and Marinello, F., 2024. Comparison of Deep Learning Models for Multi-Crop Leaf Disease Detection with Enhanced Vegetative Feature Isolation and Definition of a New Hybrid Architecture. Agronomy, 14(10), p.2230. Available from: https://doi.org/10.3390/agronomy14102230.
Shah, S., Taj, I., Usman, S., Shah, S., Imran, A. and Khalid, S., 2024. A hybrid approach of vision transformers and CNNs for detection of ulcerative colitis. Scientific Reports, 14, 10. Available from: https://doi.org/10.1038/s41598-024-75901-4.
Shah, S.R., Qadri, S., Bibi, H., Shah, S.M.W., Sharif, M.I. and Marinello, F., 2023. Comparing Inception V3, VGG 16, VGG 19, CNN, and ResNet 50: A Case Study on Early Detection of a Rice Disease. Agronomy, 13(6), p.1633. Available from: https://doi.org/10.3390/agronomy13061633.
Sun, Y., Ning, L., Zhao, B. and Yan, J., 2024. Tomato Leaf Disease Classification by Combining EfficientNetv2 and a Swin Transformer. Applied Sciences, 14(17), p.7472. Available from: https://doi.org/10.3390/app14177472.
Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A. and Jegou, H., 2021. Training data-efficient image transformers & distillation through attention. In: M. Meila and T. Zhang, eds. Proceedings of the 38th International Conference on Machine Learning, Proceedings of machine learning research, vol. 139. PMLR, pp.10347–10357. Available from: https://proceedings.mlr.press/v139/
touvron21a.html.
Yu, D., Wan, B. and Sheng, Q., 2024. Automated Generation of Urban Spatial Structures Based on Stable Diffusion and CoAtNet Models. Buildings, 14(12), p.3720. Available from: https://doi.org/10.3390/buildings14123720.
Zhang, Z.Y., Yan, C.X., Min, Q.M., Zhang, Y.X., Jing, W.F., Hou, W.X. and Pan, K.Y., 2024. Leverage Effective Deep Learning Searching Method for Forensic Age Estimation. Bioengineering, 11(7), p.674. Available from: https://doi.org/10.3390/bioengineering11070674.
Zhu, D., Tan, J., Wu, C., Yung, K. and Ip, A.W.H., 2023. Crop Disease Identification by Fusing Multiscale Convolution and Vision Transformer. Sensors, 23(13), p. 6015. Available from: https://doi.org/10.3390/s23136015.