<![CDATA[Purpose: Accurate detection of paddy leaf diseases is essential to ensure optimal crop yield and effective disease management. Methods/Study design/approach: In this study, we propose a hybrid deep learning model combining Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), and an Attention mechanism for paddy leaf disease classification using the Paddy Doctor dataset. The CNN layers extract spatial features from leaf images, the LSTM captures contextual relationships between these features, and the Attention mechanism emphasizes the most relevant patterns for accurate classification. Result/Findings: Experimental results show that the proposed CNN+LSTM+Attention model achieves 95.5% accuracy, 98.12% precision, 98.3% recall, and 0.994 macro AUC, outperforming a simple CNN-3 layer while offering competitive performance compared to state-of-the-art architectures such as ResNet34 and Xception. Novelty/Originality/Value: These results demonstrate that the proposed model is highly effective in detecting paddy leaf diseases with minimal false negatives, providing a reliable and practical solution for automated paddy disease monitoring systems]]>
Copyrights © 2025
