Cotton plant disease detection system

Using state-of-the-art convolutional neural network (CNN) architectures and transfer learning, this research introduced a deep learning system for disease detection in cotton plants. With the suggested system, real-time agricultural monitoring is possible and the accuracy is excellent. Integration of drone-based picture acquisition, implementation of vision transformers for enhanced feature extraction, diversification of datasets, and deployment of optimised models on edge devices for smart farming applications at the field level are all parts of the future work.

Zhang et al., “AttentionBased Deep Learning Model for Crop Disease Recognition,” IEEE Access, 2023. M. Rahman et al., “Hybrid CNNTransformer Architecture for Plant Leaf Disease Detection,” IEEE Transactions on AI, 2024. “Transfer Learning Approach for Agricultural Disease Classification,” IEEE Access, 2023. Chen et al., “Lightweight Deep Learning Models for RealTime Plant Disease Diagnosis,” IEEE Internet of Things Journal, 2024. R. Patel et al., “Explainable AI for Plant Disease Identification Using GradCAM,” IEEE Transactions on Computational Imaging, 2025. Lee et al., “LargeScale MultiCrop Disease Dataset and Benchmarking,” IEEE Access, 2024. Singh et al., “Vision Transformer for Precision Agriculture Applications,” IEEE Transactions on Neural Networks and Learning Systems, 2025. “Deep Residual Networks for Agricultural Image Classification,” IEEE Access, 2023. K. Sharma et al., “EdgeBased Smart Farming Using Deep Learning,” IEEE Internet of Things Journal, 2025. D. Roy et al., “Robust CNN Architectures for Leaf Disease Detection Under Field Conditions,” IEEE Access, 2024. H. Kim et al., “MultiScale Feature Learning for Plant Disease Classification,” IEEE Transactions on AI, 2025. T. Nguyen et al., “Efficient Model Compression for Agricultural Deep Learning Systems,” IEEE Access, 2026.