It is better to cure any disease as early as possible before it’s too late. if diabetic retinopathy is left untreated it can cause permanent blindness. Also, identification of the stage of DR is tricky and it requires a human expert of fundus images. So simplified thing of detection is easy and can help many people.it occurs mainly when diabetes is unmanageable. It classifies the fundus images based on their severity levels as No DR, Mild, Moderate, Severe, and Proliferative DR. The datasets Aptos 2019 Blindness Detection were both obtained from Kaggle. Our proposed model achieved 90% of accuracy. The Regression model was also employed, manifested up the accuracy of 78%. Keywords: Deep learning, diabetic retinopathy, deep convolution neural network, kaggle, APTOS 2019.

Nonlinear optimization design models were developed for field conditions to design and manage border irrigation system using Lewis-Kostiakov infiltration equation. The design criterion used in the models was the depth of irrigation and basic infiltration rate of the soil. The objective function of the nonlinear model was constructed on the basis of a relationship between net returns and water application efficiency. The design variables of the models were the inflow rate, length of run, cutoff time, number of borders per set and number of sets. The nonlinear model gives a better representation of the design parameters and is more flexible because it permits easy changes in the objective function. Highlights• The non linear model developed can be used to compare different types of border irrigation management strategies.• Optimization technique can be used as a tool for the design and management of border irrigation system.• The optimal design of border irrigation can be used to increase farm income by optimizing design variables.• The model gives the optimal values of design variables.