Multi-Head Self-Attention Fusion Network for Enhanced Multi-Class Crop Disease Classification | ||
| Journal of AI and Data Mining | ||
| دوره 13، شماره 2، تیر 2025، صفحه 227-240 اصل مقاله (1.07 M) | ||
| نوع مقاله: Original/Review Paper | ||
| شناسه دیجیتال (DOI): 10.22044/jadm.2025.15689.2687 | ||
| نویسندگان | ||
| Thomas Njoroge Kinyanjui* 1؛ Kelvin Mugoye1؛ Rachael Kibuku2 | ||
| 1Computer Science & Informatics Department, School of Pure and Applied Science, Karatina University, Kenya. | ||
| 2Software Development & Information Systems, School of Technology, KCA University, Nairobi, Kenya | ||
| چکیده | ||
| This paper presents a Multi-Head Self-Attention Fusion Network (MHSA-FN) for real-time crop disease classification, addressing key limitations in existing models, including suboptimal feature extraction, inefficient feature recalibration, and weak multi-scale fusion. Unlike prior works that rely solely on CNNs or transformers, MHSA-FN integrates MobileNetV2, EfficientNetV2, and Vision Transformers (ViTs) with a structured multi-level attention framework for enhanced feature learning. A gated fusion mechanism and a Multiscale Fusion Module (MSFM) optimize local texture details and global spatial relationships. The model was trained on a combined dataset of PlantVillage and locally collected images, improving adaptability to real-world conditions. It achieved 98.66% training accuracy and 99.0% test accuracy across 76 disease classes, with 99.34% precision, 99.01% recall, and 99.04% F1 score. McNemar’s test (p = 0.125) and Bayesian superiority probability (0.851) validated its robustness. Confidence variance analysis (0.000010) outperformed existing models, demonstrating MHSA-FN as a scalable, high-performance AI solution for precision agriculture in resource-constrained environments. | ||
| کلیدواژهها | ||
| Crop Disease Detection؛ Vision Transformers؛ Convolutional Neural Networks؛ Multimodal Fusion؛ Deep Learning | ||
| مراجع | ||
|
[1] M. I. Hossain, S. Jahan, M. R. Al Asif, M. Samsuddoha, and K. Ahmed, “Detecting tomato leaf diseases by image processing through deep convolutional neural networks,” Smart Agricultural Technology, vol. 5, Oct. 2023, doi: 10.1016/j.atech.2023.100301.
[2] A. M. Abdu, M. M. Mokji, and U. U. Sheikh, “Machine learning for plant disease detection: An investigative comparison between support vector machine and deep learning,” IAES International Journal of Artificial Intelligence, vol. 9, no. 4, pp. 670–683, Dec. 2020, doi: 10.11591/ijai.v9.i4.pp670-683.
[3] H. T. Nguyen, H. H. Luong, L. B. Huynh, B. Q. H. Le, N. H. Doan, and D. T. D. Le, “An Improved MobileNet for Disease Detection on Tomato Leaves,” Advances in Technology Innovation, vol. 8, no. 3, pp. 192–209, 2023, doi: 10.46604/aiti.2023.11568.
[4] S. R. Shah, S. Qadri, H. Bibi, S. M. W. Shah, M. I. Sharif, and F. Marinello, “Comparing Inception V3, VGG 16, VGG 19, CNN, and ResNet 50: A Case Study on Early Detection of a Rice Disease,” Agronomy, vol. 13, no. 6, Jun. 2023, doi: 10.3390/agronomy13061633.
[5] U. Barman et al., “ViT-SmartAgri: Vision Transformer and Smartphone-Based Plant Disease Detection for Smart Agriculture,” Agronomy, vol. 14, no. 2, Feb. 2024, doi: 10.3390/agronomy14020327.
[6] S. Ramesh and D. Vydeki, “Recognition and classification of paddy leaf diseases using Optimized Deep Neural network with Jaya algorithm,” Information Processing in Agriculture, vol. 7, no. 2, pp. 249–260, Jun. 2020, doi: 10.1016/j.inpa.2019.09.002.
[7] A. T. Le, M. Shakiba, I. Ardekani, and W. H. Abdulla, “Optimizing Plant Disease Classification with Hybrid Convolutional Neural Network–Recurrent Neural Network and Liquid Time-Constant Network,” Applied Sciences (Switzerland), vol. 14, no. 19, Oct. 2024, doi: 10.3390/app14199118.
[8] D. Guo, P. Duan, Z. Yang, X. Zhang, and Y. Su, “Convolutional Neural Network and Bidirectional Long Short-Term Memory (CNN-BiLSTM)-Attention-Based Prediction of the Amount of Silica Powder Moving in and out of a Warehouse,” Energies (Basel), vol. 17, no. 15, Aug. 2024, doi: 10.3390/en17153757.
[9] 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, Feb. 2023, doi: 10.3390/agronomy13020300.
[10] 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.
[11] S. Z. M. Zaki, M. A. Zulkifley, M. Mohd Stofa, N. A. M. Kamari, and N. A. Mohamed, “Classification of tomato leaf diseases using mobilenet v2,” IAES International Journal of Artificial Intelligence, vol. 9, no. 2, pp. 290–296, Jun. 2020, doi: 10.11591/ijai.v9.i2.pp290-296.
[12] 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.
[13] Q. Dai et al., “Citrus Disease Image Generation and Classification Based on Improved FastGAN and EfficientNet-B5,” Agronomy, vol. 13, no. 4, Apr. 2023, doi: 10.3390/agronomy13040988.
[14] S. Saleem, M. I. Sharif, M. I. Sharif, M. Z. Sajid, and F. Marinello, “Comparison of Deep Learning Models for Multi-Crop Leaf Disease Detection with Enhanced Vegetative Feature Isolation and Definition of a New Hybrid Architecture,” Agronomy, vol. 14, no. 10, Oct. 2024, doi: 10.3390/agronomy14102230.
[15] S. He, P. Peng, Y. Chen, and X. Wang, “Multi-Crop Classification Using Feature Selection-Coupled Machine Learning Classifiers Based on Spectral, Textural and Environmental Features,” Remote Sens (Basel), vol. 14, no. 13, Jul. 2022, doi: 10.3390/rs14133153.
[16] Y. Wang, Y. Deng, Y. Zheng, P. Chattopadhyay, and L. Wang, “Vision Transformers for Image Classification: A Comparative Survey,” Technologies (Basel), vol. 13, no. 1, p. 32, Jan. 2025, doi: 10.3390/technologies13010032.
[17] D. Zhu, J. Tan, C. Wu, K. L. Yung, and A. W. H. Ip, “Crop Disease Identification by Fusing Multiscale Convolution and Vision Transformer,” Sensors, vol. 23, no. 13, Jul. 2023, doi: 10.3390/s23136015.
[18] P. Christakakis, N. Giakoumoglou, D. Kapetas, D. Tzovaras, and E.-M. Pechlivani, “Vision Transformers in Optimization of AI-Based Early Detection of Botrytis cinerea,” AI, vol. 5, no. 3, pp. 1301–1323, Aug. 2024, doi: 10.3390/ai5030063.
[19] H. Wang, L. Zhang, and J. Zhao, “Application of a Fusion Attention Mechanism-Based Model Combining Bidirectional Gated Recurrent Units and Recurrent Neural Networks in Soil Nutrient Content Estimation,” Agronomy, vol. 13, no. 11, Nov. 2023, doi: 10.3390/agronomy13112724.
[20] Y. Wang et al., “Classification of Plant Leaf Disease Recognition Based on Self-Supervised Learning,” Agronomy, vol. 14, no. 3, Mar. 2024, doi: 10.3390/agronomy14030500.
[21] L. Bi, G. Hu, M. M. Raza, Y. Kandel, L. Leandro, and D. Mueller, “A gated recurrent units (Gru)-based model for early detection of soybean sudden death syndrome through time-series satellite imagery,” Remote Sens (Basel), vol. 12, no. 21, pp. 1–20, Nov. 2020, doi: 10.3390/rs12213621.
[22] X. Ni, F. Wang, H. Huang, L. Wang, C. Wen, and D. Chen, “A CNN- and Self-Attention-Based Maize Growth Stage Recognition Method and Platform from UAV Orthophoto Images,” Remote Sens (Basel), vol. 16, no. 14, Jul. 2024, doi: 10.3390/rs16142672.
[23] X. Wang, S. Fang, Y. Yang, J. Du, and H. Wu, “A New Method for Crop Type Mapping at the Regional Scale Using Multi-Source and Multi-Temporal Sentinel Imagery,” Remote Sens (Basel), vol. 15, no. 9, May 2023, doi: 10.3390/rs15092466.
[24] O. Jouini, M. O.-E. Aoueileyine, K. Sethom, and A. Yazidi, “Wheat Leaf Disease Detection: A Lightweight Approach with Shallow CNN Based Feature Refinement,” AgriEngineering, vol. 6, no. 3, pp. 2001–2022, Jul. 2024, doi: 10.3390/agriengineering6030117.
[25] S. M. Hassan, A. K. Maji, M. Jasiński, Z. Leonowicz, and E. Jasińska, “Identification of plant-leaf diseases using cnn and transfer-learning approach,” Electronics (Switzerland), vol. 10, no. 12, Jun. 2021, doi: 10.3390/electronics10121388.
[26] R. A. Ansari and T. J. Mulrooney, “Self-Attention Multiresolution Analysis-Based Informal Settlement Identification Using Remote Sensing Data,” Remote Sens (Basel), vol. 16, no. 17, p. 3334, Sep. 2024, doi: 10.3390/rs16173334.
[27] 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.
[28] 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, Aug. 2023, doi: 10.3390/s23156949.
[29] 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, Dec. 2024, doi: 10.1038/s41598-024-75901-4.
[30] U Barman et al., “ViT-SmartAgri: Vision Transforer and Smartphone-Based Plant Disease Detection for Smart Agriculture,” Agronomy, vol. 14, no. 2, Feb. 2024, doi: 10.3390/agronomy14020327.
[31] Touvron, M. Cord, M. Douze, F. Massa, A. Sablayrolles, and H. Jégou, "Training data-efficient image transformers & distillation through attention," in Proceedings of the 38th International Conference on Machine Learning (ICML), Online, Jul. 18–24, 2021, vol. 139, pp. 10347–10357. [Online]. Available: https://proceedings.mlr.press/v139/touvron21a.html
| ||
|
آمار تعداد مشاهده مقاله: 308 تعداد دریافت فایل اصل مقاله: 231 |
||