Earlier Diagnosis and Survey of Diabetes Mellitus Using Machine Learning Techniques

Machine learning is the major aspect in artificial intelligence that empowers the development of the intelligent systems to have the capability of acquiring the knowledge through training. It eliminates the effort of the human and also avoids human errors in the upcoming era. The objective of the paper is to understand the different types and stages of diabetes mellitus. Also it provides the in depth knowledge of the machine learning techniques that supports to identify the neuropathy at its earlier stage. The various techniques involve Artificial Neural Network (ANN), Principle component, Genetic algorithms, Decision trees, Fuzzy logic have been discussed and compared. In the diabetic patients the nervous system is mainly affected and this leads to the amputation of the external body parts. This can be easily detected using the heart rate variability but not only is the HRV significant, galvanic skin response is also needed to predict the nervous system response. This paper presents the significance of HRV and GSR to track the blood glucose level and nervous response to experimentally identify the diabetes at the earlier stage.