A Novel approach to predict diabetes mellitus using modified Extreme learning machine

Data Classification and predictions are one of the prime tasks in Data mining. They continue to play a vital role in the area of computer science and data processing field. Clustering and classifications in Data Mining are used in various domains to give meaning to the available data and give some useful prediction results which can be applied to some of the crucial problem areas of the real world. Diabetes mellitus otherwise known as a slow poison by the medical experts is a major, alarming and gradually becoming a global problem. This paper experimented and used the concept of modified extreme learning machine to identify the patients of being diabetic or non-diabetic basing on some previously given data which in turn helps the medical people to identify whether someone is affected by diabetes or not. It also describes and compares the application of two popular machine learning methods: Back propagation neural network and modified Extreme learning machine which are used as binary classifiers to address the diabetes prediction problem. These two approaches are applied on same type of multi class classification datasets and the work tries to generate some comparative inferences from training and testing results. The datasets which are used in our work is taken from UCI learning repository.