<![CDATA[Diabetes mellitus is one of the diseases that can cause death and one of the diseases heredity. Most people do not care about a healthy lifestyle. Health is very important in everyday life. The public is less aware of the problem of health care so that the rate of deaths worldwide has increased. The public salso did not understand the similarity of the symptoms of disease appear not treated quickly lead to disease. To overcome these problems invented a system for the identification of diabetes mellitus using the Modified K-Nearest Neighbor (MKNN). Modified K-Nearest Neighbor (MKNN) is one method of classification is based on the number of class occurrence on data mining. There are 15 symptoms and 2 types of diseases are used as parameters in development of the system. An output as the result produced by the system is diagnosis of the type of disease and how to control. Based on method, this research obtain 93,33% of good accuracy and error rate of 6,67%. The system using of method Modified K-Nearest Neighbor (MKNN) can be applied in society based on result.]]>
Copyrights © 2017
