Diabetic Retinopathy Grading System Using Machine Learning

IJCSEC Front Page

The remote monitoring system is growing very rapidly due to the growth of supporting technologies as well. And also problem that may occur in remote monitoring such as the number of objects to be monitored and how fast, how much data to be transmitted to the data center to be processed properly. This study focuses on the situation for sensing on the environment condition and disaster early detection. Sensors are used to predict the disaster situations. Data are automatically get change over based on sensor information. Where those two things, it has become an important issue, especially in big cities big cities that have many residents. This study proposes to build the conceptual then prototype model in a comprehensive manner from the remote terminal till development method for data retrieval. We also propose using FTR-HTTP method to guarantee the delivery from remote client to server.

Keywords: Diabetic Retinopathy, Feature extraction, Classification, Segmentation, Bright lesion, Red lesions.


  1. American Diabetes Association. (2011, Jan. 26). Data from the 2011 national diabetes fact sheet. [Online]. Available: http://www.diabetes.org/diabetes-basics/diabetes-statistics/
  2. S. Roychowdhury, D. D. Koozekanani, and K. K. Parhi, ”DREAM: Diabetic Retinopathy Analysis Using Machine Learning,” IEEE journal of biomedical and health informatics, vol. 18, no. 5, September 2014.
  3. S. Roychowdhury, D. D. Koozekanani, and K. K. Parhi, ”Screening fundus images for diabetic retinopathy,” in Proc. Conf. Record 46th Asilomar Conf. Signals, Syst. Comput., 2012, pp. 1641-1645.
  4. L. Shen and L. Bai, “Abstract adaboost gabor feature selection for classification,” in Proc. Image Vis. Comput., 2004, New Zealand, pp. 77–83.