A Secure Deep Learning Based Disease Prediction on Paddy

The agriculture industry has seen notable change recently by using cutting-edge technology like Deep Learning (ML). Being a basic crop, rice is vulnerable to many illnesses that may seriously affect food security and agricultural output. Aiming to enable early diagnosis and reduce losses, this work proposes a safe, Deep Learning-based disease prediction method for paddy. To guarantee exact diagnosis, the proposed model uses a mix of supervised learning techniques to correctly diagnose illnesses depending on paddy leaf pictures and environmental data. By means of cryptographic methods including encryption and safe data transfer protocols, the security of the system is improved, therefore shielding the input data of the model as well as forecasts from hostile events. The system is designed to run well even in remote areas with limited resources, therefore guaranteeing farmer accessibility. High prediction accuracy, strong performance under many circumstances, and safe transfer of sensitive data are shown by experimental findings. This strategy provides a dependable and scalable method of disease control in paddy farming, therefore enhancing agricultural practices and food security.