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
Accepted 2025-09-09
Published 2025-11-21
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. DOI: 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. DOI: 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. DOI: 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. DOI: 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. DOI: 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. DOI: 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. DOI: 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. DOI: 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. DOI: 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. DOI: 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. DOI: 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. DOI: 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. DOI: 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. DOI: 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. DOI: 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. DOI: 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. DOI: 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. DOI: 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. DOI: 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. DOI: 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. DOI: 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. DOI: 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. DOI: 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. DOI: 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. DOI: 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. DOI: 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. DOI: 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. DOI: 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. DOI: 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. DOI: 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. DOI: 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. DOI: 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. DOI: 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. DOI: 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. DOI: https://doi.org/10.3390/s23136015