Survey of Different Feature Selection Algorithms for Diabetes Mellitus Prediction

Diabetes Mellitus is a non-communicable diseases and it is a major health hazard in the world today. There is a huge data of diabetes in health care industry which is chaotic (not structured). Hence to structure and emphasize the size of this huge diabetic data is very necessary for better and accurate prediction results. The major task in this prediction is to select the relevant features for prediction. With the help of feature selection algorithm we can achieve better prediction of diabetes. In this paper we are discussing some feature selection algorithms like-K Nearest Neighbor, K means, branch and bound algorithm, etc. We are considering a common diabetic dataset and analyzing each algorithm for its performance and accuracy and selecting best algorithm among them.