Feature Selection of Diabetic Retinopathy Disease Using Particle Swarm Optimization and Neural Network

Currently, there are many medical experts who face difficulty in conducting early detection for diabetic retinopathy. This occurs because it is difficult to recognize the early symptoms of this disease. In order for this disease to be detected early, an accurate classification method is required. Data mining concept is one alternative in conducting classification. This study was conducting by applying particle swarm optimization (PSO) method to select the best Diabetic Retinopathy feature based on diabetic retinopathy dataset. Then, the selected feature is further classified using classification method of neural network. The study result show that there is an increase in result by applying neural network based particle swarm optimization (PSO) of 76.11%. This study also show that there is an increase in classification result by using feature selection method of 4.35% from previous result of 71.76% by only applying neural network method.