(School of Pure and Applied Science, Karatina University, Kenya)(2) Kelvin Sindu Mugoye
(School of Technology, KCA University, Kenya)(3) Rachael Kibuku
(School of Technology, KCA University, Kenya)*corresponding author
AbstractAccurate and timely crop disease detection is crucial for mitigating agricultural losses and ensuring food security, particularly in resource-limited settings. Traditional diagnostic methods are inefficient and prone to errors, while existing deep learning models, such as ResNet50 and Inception V3, struggle with generalizability and computational efficiency. This study proposes a Dynamic Edge-Optimized Multimodal Fusion (DEMF) model, integrating EfficientNetV2 and MobileNetV2 to enhance feature learning and scalability. The model was trained on a 76-class dataset comprising PlantVillage and locally collected images of crop diseases, ensuring robustness across diverse conditions. Feature fusion via concatenation, combined with compound scaling and transfer learning, enabled the model to capture fine-grained patterns of disease. Extensive experiments, including ablation studies and comparative evaluations against DenseNet-121, DenseNet-50, AlexNet, and ResNet-152, validated the model’s superiority. The proposed model achieved 99.2% accuracy, a Kappa of 0.9919, and an AUC of 0.9999, outperforming benchmarks. Statistical validation confirmed significant improvements (p<0.05) and stability. To enhance accessibility, an AI-powered mobile application was deployed on the Google Play Store, enabling real-time disease detection and actionable recommendations. To enhance accessibility, an AI-powered mobile application was deployed on the Google Play Store, enabling real-time disease detection and actionable recommendations. This research advances transfer learning, feature fusion, and statistical validation for robust, scalable crop disease detection in low-resource environments.
KeywordsCrop disease detection, Multimodal fusion model, Transfer learning, Edge computing, EfficientNetV2, MobileNetV2
|
DOIhttps://doi.org/10.26555/ijain.v11i3.2051 |
Article metricsAbstract views : 94 | PDF views : 10 |
Cite |
Full Text Download
|
References
[1] M. K. Kaleem, N. Purohit, K. Azezew, and S. Asemie D A Assistant, “A Modern Approach for Detection of Leaf Diseases Using Image Processing and ML Based SVM Classifier,” Turkish J. Comput. Math. Educ., vol. 12, no. 13, pp. 3340–3347, 2021, [Online]. Available at: https://www.proquest.com/openview/6330532b32b6f07544035f7dd2be60df/1?pq-origsite=gscholar&cbl=2045096.
[2] H. Kim and D. Kim, “Deep-Learning-Based Strawberry Leaf Pest Classification for Sustainable Smart Farms,” Sustainability, vol. 15, no. 10, p. 7931, May 2023, doi: 10.3390/su15107931.
[3] R. C. Bernardes et al., “Deep-Learning Approach for Fusarium Head Blight Detection in Wheat Seeds Using Low-Cost Imaging Technology,” Agriculture, vol. 12, no. 11, p. 1801, Oct. 2022, doi: 10.3390/agriculture12111801.
[4] A. M. Abdu, M. M. M. Mokji, and U. U. U. Sheikh, “Machine learning for plant disease detection: an investigative comparison between support vector machine and deep learning,” IAES Int. J. Artif. Intell., vol. 9, no. 4, p. 670, Dec. 2020, doi: 10.11591/ijai.v9.i4.pp670-683.
[5] G. G. and A. P. J., “Identification of plant leaf diseases using a nine-layer deep convolutional neural network,” Comput. Electr. Eng., vol. 76, pp. 323–338, Jun. 2019, doi: 10.1016/j.compeleceng.2019.04.011.
[6] M. J. Mia, S. K. Maria, S. S. Taki, and A. A. Biswas, “Cucumber disease recognition using machine learning and transfer learning,” Bull. Electr. Eng. Informatics, vol. 10, no. 6, pp. 3432–3443, Dec. 2021, doi: 10.11591/eei.v10i6.3096.
[7] R. A. F. Ishaq et al., “A Synergistic Framework for Coupling Crop Growth, Radiative Transfer, and Machine Learning to Estimate Wheat Crop Traits in Pakistan,” Remote Sens., vol. 16, no. 23, p. 4386, Nov. 2024, doi: 10.3390/rs16234386.
[8] M. Tika Adilah and D. A. Kristiyanti, “Implementation of Transfer Learning Mobilenetv2 Architecture for Identification of Potato Leaf Disease,” J. Theor. Appl. Inf. Technol., vol. 101, no. 16, pp. 6273–6285, 2023, [Online]. Available at: https://www.jatit.org/volumes/Vol101No16/3Vol101No16.pdf.
[9] Z. Wu, F. Jiang, and R. Cao, “Research on recognition method of leaf diseases of woody fruit plants based on transfer learning,” Sci. Rep., vol. 12, no. 1, p. 15385, Sep. 2022, doi: 10.1038/s41598-022-18337-y.
[10] L. Mohammed and Y. Yusoff, “Detection And Classification Of Plant Leaf Diseases Using Digtal Image Processing Methods: A Review,” ASEAN Eng. J., vol. 13, no. 1, pp. 1–9, Feb. 2023, doi: 10.11113/aej.v13.17460.
[11] Z. Zhao, L. Alzubaidi, J. Zhang, Y. Duan, and Y. Gu, “A comparison review of transfer learning and self-supervised learning: Definitions, applications, advantages and limitations,” Expert Syst. Appl., vol. 242, p. 122807, May 2024, doi: 10.1016/j.eswa.2023.122807.
[12] Hai Thanh Nguyen, Huong Hoang Luong, Long Bao Huynh, Bao Quoc Hoang Le, Nhan Hieu Doan, and Duc Thien Dao Le, “An Improved MobileNet for Disease Detection on Tomato Leaves,” Adv. Technol. Innov., vol. 8, no. 3, pp. 192–209, Jul. 2023, doi: 10.46604/aiti.2023.11568.
[13] M. Kabir, F. Unal, T. C. Akinci, A. A. Martinez-Morales, and S. Ekici, “Revealing GLCM Metric Variations across a Plant Disease Dataset: A Comprehensive Examination and Future Prospects for Enhanced Deep Learning Applications,” Electronics, vol. 13, no. 12, p. 2299, Jun. 2024, doi: 10.3390/electronics13122299.
[14] S. Barman et al., “Optimized Crop Disease Identification in Bangladesh: A Deep Learning and SVM Hybrid Model for Rice, Potato, and Corn,” J. Imaging, vol. 10, no. 8, p. 183, Jul. 2024, doi: 10.3390/jimaging10080183.
[15] P. K. Mensah et al., “CCMT: Dataset for crop pest and disease detection,” Data Br., vol. 49, p. 109306, Aug. 2023, doi: 10.1016/j.dib.2023.109306.
[16] A. Blekos et al., “A Grape Dataset for Instance Segmentation and Maturity Estimation,” Agronomy, vol. 13, no. 8, p. 1995, Jul. 2023, doi: 10.3390/agronomy13081995.
[17] H. Amin, A. Darwish, A. E. Hassanien, and M. Soliman, “End-to-End Deep Learning Model for Corn Leaf Disease Classification,” IEEE Access, vol. 10, pp. 31103–31115, 2022, doi: 10.1109/ACCESS.2022.3159678.
[18] C. Sun, X. Zhou, M. Zhang, and A. Qin, “SE-VisionTransformer: Hybrid Network for Diagnosing Sugarcane Leaf Diseases Based on Attention Mechanism,” Sensors, vol. 23, no. 20, p. 8529, Oct. 2023, doi: 10.3390/s23208529.
[19] U. Barman et al., “ViT-SmartAgri: Vision Transformer and Smartphone-Based Plant Disease Detection for Smart Agriculture,” Agronomy, vol. 14, no. 2, p. 327, Feb. 2024, doi: 10.3390/agronomy14020327.
[20] S. Padshetty and Ambika, “Leaky ReLU-ResNet for Plant Leaf Disease Detection: A Deep Learning Approach,” in RAiSE-2023, Dec. 2023, vol. 59, no. 1, p. 39, doi: 10.3390/engproc2023059039.
[21] T. Wang, H. Xia, J. Xie, J. Li, and J. Liu, “A Multi-Scale Feature Focus and Dynamic Sampling-Based Model for Hemerocallis fulva Leaf Disease Detection,” Agriculture, vol. 15, no. 3, p. 262, Jan. 2025, doi: 10.3390/agriculture15030262.
[22] Y. Gulzar, “Fruit Image Classification Model Based on MobileNetV2 with Deep Transfer Learning Technique,” Sustainability, vol. 15, no. 3, p. 1906, Jan. 2023, doi: 10.3390/su15031906.
[23] W. Li, L. Zhu, and J. Liu, “PL-DINO: An Improved Transformer-Based Method for Plant Leaf Disease Detection,” Agriculture, vol. 14, no. 5, p. 691, Apr. 2024, doi: 10.3390/agriculture14050691.
[24] J. Fu, Y. Zhao, and G. Wu, “Potato Leaf Disease Segmentation Method Based on Improved UNet,” Appl. Sci., vol. 13, no. 20, p. 11179, Oct. 2023, doi: 10.3390/app132011179.
[25] M. Xie and N. Ye, “Multi-Scale and Multi-Factor ViT Attention Model for Classification and Detection of Pest and Disease in Agriculture,” Appl. Sci., vol. 14, no. 13, p. 5797, Jul. 2024, doi: 10.3390/app14135797.
[26] N. R. Almarines, S. Hashimoto, J. M. Pulhin, C. L. Tiburan, A. T. Magpantay, and O. Saito, “Influence of Image Compositing and Multisource Data Fusion on Multitemporal Land Cover Mapping of Two Philippine Watersheds,” Remote Sens., vol. 16, no. 12, p. 2167, Jun. 2024, doi: 10.3390/rs16122167.
[27] S. Yi, S. Hong, Y. Qin, H. Wang, and N. Liu, “Virtual Machine Placement in Edge Computing Based on Multi-Objective Reinforcement Learning,” Electronics, vol. 14, no. 3, p. 633, Feb. 2025, doi: 10.3390/electronics14030633.
[28] C. Bi, S. Xu, N. Hu, S. Zhang, Z. Zhu, and H. Yu, “Identification Method of Corn Leaf Disease Based on Improved Mobilenetv3 Model,” Agronomy, vol. 13, no. 2, p. 300, Jan. 2023, doi: 10.3390/agronomy13020300.
[29] X. Chao, G. Sun, H. Zhao, M. Li, and D. He, “Identification of Apple Tree Leaf Diseases Based on Deep Learning Models,” Symmetry (Basel)., vol. 12, no. 7, p. 1065, Jun. 2020, doi: 10.3390/sym12071065.
[30] I. V. D. Srihith, “A Short Review on Deep Learning in Agriculture,” J. Adv. Res. Artif. Intell. It’s Appl., vol. 1, no. 3, pp. 23–39, 2024. [Online]. Available at: https://zenodo.org/records/11612440.
[31] M. Gu, K.-C. Li, Z. Li, Q. Han, and W. Fan, “Recognition of Crop Diseases Based on Depthwise Separable Convolution in Edge Computing,” Sensors, vol. 20, no. 15, p. 4091, Jul. 2020, doi: 10.3390/s20154091.
[32] P. Rajendran, S. Maloo, R. Mitra, A. Chanchal, and R. Aburukba, “Comparison of Cloud-Computing Providers for Deployment of Object-Detection Deep Learning Models,” Appl. Sci., vol. 13, no. 23, p. 12577, Nov. 2023, doi: 10.3390/app132312577.
[33] R. Yulvina et al., “Hybrid Vision Transformer and Convolutional Neural Network for Multi-Class and Multi-Label Classification of Tuberculosis Anomalies on Chest X-Ray,” Computers, vol. 13, no. 12, p. 343, Dec. 2024, doi: 10.3390/computers13120343.
[34] S. Parez, N. Dilshad, N. S. Alghamdi, T. M. Alanazi, and J. W. Lee, “Visual Intelligence in Precision Agriculture: Exploring Plant Disease Detection via Efficient Vision Transformers,” Sensors, vol. 23, no. 15, p. 6949, Aug. 2023, doi: 10.3390/s23156949.
[35] F. Rajeena P. P., A. S. U., M. A. Moustafa, and M. A. S. Ali, “Detecting Plant Disease in Corn Leaf Using EfficientNet Architecture—An Analytical Approach,” Electronics, vol. 12, no. 8, p. 1938, Apr. 2023, doi: 10.3390/electronics12081938.
[36] G. Arjun, O. B. A, O. Y. O, A. G. K, B. F. Muhammed, and A. A. M, “Computer Vision-Based Plant Disease Identification System: A Review,” AAN J. Sci. Eng. Technol., vol. 1, pp. 59–78, 2022[Online]. Available at : https://d1wqtxts1xzle7.cloudfront.net/95812316/6_Computer_Vision_for_Plant.
[37] Y.-Y. Zheng, J.-L. Kong, X.-B. Jin, X.-Y. Wang, T.-L. Su, and M. Zuo, “CropDeep: The Crop Vision Dataset for Deep-Learning-Based Classification and Detection in Precision Agriculture,” Sensors, vol. 19, no. 5, p. 1058, Mar. 2019, doi: 10.3390/s19051058.
[38] B. Alabsi, M. Anbar, and S. Rihan, “CNN-CNN: Dual Convolutional Neural Network Approach for Feature Selection and Attack Detection on Internet of Things Networks,” Sensors, vol. 23, no. 14, p. 6507, Jul. 2023, doi: 10.3390/s23146507.
[39] X. Fang, T. Zhen, and Z. Li, “Lightweight Multiscale CNN Model for Wheat Disease Detection,” Appl. Sci., vol. 13, no. 9, p. 5801, May 2023, doi: 10.3390/app13095801.
[40] L. Jia et al., “MobileNet-CA-YOLO: An Improved YOLOv7 Based on the MobileNetV3 and Attention Mechanism for Rice Pests and Diseases Detection,” Agriculture, vol. 13, no. 7, p. 1285, Jun. 2023, doi: 10.3390/agriculture13071285.
[41] A. Tragoudaras et al., “Design Space Exploration of a Sparse MobileNetV2 Using High-Level Synthesis and Sparse Matrix Techniques on FPGAs,” Sensors, vol. 22, no. 12, p. 4318, Jun. 2022, doi: 10.3390/s22124318.
[42] S. Zhuang, Y. Hou, and D. Wang, “Towards Efficient Object Detection in Large-Scale UAV Aerial Imagery via Multi-Task Classification,” Drones, vol. 9, no. 1, p. 29, Jan. 2025, doi: 10.3390/drones9010029.
[43] L. Zhang, G. Ding, C. Li, and D. Li, “DCF-Yolov8: An Improved Algorithm for Aggregating Low-Level Features to Detect Agricultural Pests and Diseases,” Agronomy, vol. 13, no. 8, p. 2012, Jul. 2023, doi: 10.3390/agronomy13082012.
[44] Z. Mi, X. Zhang, J. Su, D. Han, and B. Su, “Wheat Stripe Rust Grading by Deep Learning With Attention Mechanism and Images From Mobile Devices,” Front. Plant Sci., vol. 11, p. 558126, Sep. 2020, doi: 10.3389/fpls.2020.558126.
[45] H. Ge et al., “Cross Attention-Based Multi-Scale Convolutional Fusion Network for Hyperspectral and LiDAR Joint Classification,” Remote Sens., vol. 16, no. 21, p. 4073, Oct. 2024, doi: 10.3390/rs16214073.
[46] S. Sladojevic, M. Arsenovic, A. Anderla, D. Culibrk, and D. Stefanovic, “Deep Neural Networks Based Recognition of Plant Diseases by Leaf Image Classification,” Comput. Intell. Neurosci., vol. 2016, no. 1, pp. 1–11, Jan. 2016, doi: 10.1155/2016/3289801.
[47] W. Lu, X. Wang, L. Sun, and Y. Zheng, “Spectral–Spatial Feature Extraction for Hyperspectral Image Classification Using Enhanced Transformer with Large-Kernel Attention,” Remote Sens., vol. 16, no. 1, p. 67, Dec. 2023, doi: 10.3390/rs16010067.
[48] M. Bakr, S. Abdel-Gaber, M. Nasr, and M. Hazman, “DenseNet Based Model for Plant Diseases Diagnosis,” Eur. J. Electr. Eng. Comput. Sci., vol. 6, no. 5, pp. 1–9, Sep. 2022, doi: 10.24018/ejece.2022.6.5.458.
[49] K. Dong, C. Zhou, Y. Ruan, and Y. Li, “MobileNetV2 Model for Image Classification,” in 2020 2nd International Conference on Information Technology and Computer Application (ITCA), Dec. 2020, pp. 476–480, doi: 10.1109/ITCA52113.2020.00106.
[50] S. Mousavi and G. Farahani, “A Novel Enhanced VGG16 Model to Tackle Grapevine Leaves Diseases With Automatic Method,” IEEE Access, vol. 10, pp. 111564–111578, 2022, doi: 10.1109/ACCESS.2022.3215639.
[51] Q. Dai et al., “Citrus Disease Image Generation and Classification Based on Improved FastGAN and EfficientNet-B5,” Agronomy, vol. 13, no. 4, p. 988, Mar. 2023, doi: 10.3390/agronomy13040988.
[52] H. Ulutaş and V. Aslantaş, “Design of Efficient Methods for the Detection of Tomato Leaf Disease Utilizing Proposed Ensemble CNN Model,” Electronics, vol. 12, no. 4, p. 827, Feb. 2023, doi: 10.3390/electronics12040827.
[53] M. E. H. Chowdhury et al., “Automatic and Reliable Leaf Disease Detection Using Deep Learning Techniques,” AgriEngineering, vol. 3, no. 2, pp. 294–312, May 2021, doi: 10.3390/agriengineering3020020.
[54] T. Paranayapa, P. Ranasinghe, D. Ranmal, D. Meedeniya, and C. Perera, “A Comparative Study of Preprocessing and Model Compression Techniques in Deep Learning for Forest Sound Classification,” Sensors, vol. 24, no. 4, p. 1149, Feb. 2024, doi: 10.3390/s24041149.
[55] G. R. Babu, M. Gokuldhev, and P. S. Brahmanandam, “Integrating IoT for Soil Monitoring and Hybrid Machine Learning in Predicting Tomato Crop Disease in a Typical South India Station,” Sensors, vol. 24, no. 19, p. 6177, Sep. 2024, doi: 10.3390/s24196177.
[56] A. Siddiqua, M. A. Kabir, T. Ferdous, I. B. Ali, and L. A. Weston, “Evaluating Plant Disease Detection Mobile Applications: Quality and Limitations,” Agronomy, vol. 12, no. 8, p. 1869, Aug. 2022, doi: 10.3390/agronomy12081869.
[57] M. H. Saleem, J. Potgieter, and K. M. Arif, “Plant Disease Classification: A Comparative Evaluation of Convolutional Neural Networks and Deep Learning Optimizers,” Plants, vol. 9, no. 10, p. 1319, Oct. 2020, doi: 10.3390/plants9101319.
[58] D. Zhu, J. Tan, C. Wu, K. Yung, and A. W. H. Ip, “Crop Disease Identification by Fusing Multiscale Convolution and Vision Transformer,” Sensors, vol. 23, no. 13, p. 6015, Jun. 2023, doi: 10.3390/s23136015.
[59] S. A. Shah, I. Taj, S. M. Usman, S. N. Hassan Shah, A. S. Imran, and S. Khalid, “A hybrid approach of vision transformers and CNNs for detection of ulcerative colitis,” Sci. Rep., vol. 14, no. 1, p. 24771, Oct. 2024, doi: 10.1038/s41598-024-75901-4.
[60] H. Touvron, M. Cord, M. Douze, F. Massa, A. Sablayrolles, and H. Jegou, “Training data-efficient image transformers & distillation through attention,” in Proceedings of the 38th International Conference on Machine Learning, Jul. 2021, pp. 10347–10357. [Online]. Available at: https://proceedings.mlr.press/v139/touvron21a.html.
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
___________________________________________________________
International Journal of Advances in Intelligent Informatics
ISSN 2442-6571 (print) | 2548-3161 (online)
Organized by UAD and ASCEE Computer Society
Published by Universitas Ahmad Dahlan
W: http://ijain.org
E: info@ijain.org (paper handling issues)
andri.pranolo.id@ieee.org (publication issues)
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0