• Komala K V
• Anurag Ranjan Jha
• Badri A
• Simran Kaur Grewal
• Lata B T

Abstract: This study introduces a Convolutional Neural Network (CNN) based approach for automated detection of diseases in mulberry leaves, crucial for effective disease management and prevention of economic losses in sericulture. The proposed models, incorporating batch normalization and attention mechanisms, differentiate between healthy and diseased leaves with high accuracy. Compared to the base paper’s lightweight parallel depth-wise separable CNN model, our models offer improved performance while maintaining explainability. The addition of attention mechanisms enhances the interpretability of the models, providing insights into the decision-making process. The promising results indicate potential for practical implementation in real-world agricultural settings.

Attention Mechanism, Batch Normalization, Convolution Neural Networks, Deep Learning, Leaf Disease Detection, Layers, TensorFlow.

"MulberrySenseAI: Deep Learning Disease Detection of Mulberry Leaf Using Attention Mechanism", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 2, page no.g43-g57, February-2023, Available :http://www.jetir.org/papers/JETIR2302614.pdf

"MulberrySenseAI: Deep Learning Disease Detection of Mulberry Leaf Using Attention Mechanism", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 2, page no. ppg43-g57, February-2023, Available at : http://www.jetir.org/papers/JETIR2302614.pdf