Application of KNN Machine Learning and Fuzzy C-Means to Diagnose Diabetes

The disease is a common thing in humans. Diseases that attack humans do not know anyone and age. experienced by person starts from an ordinary level until it can be declared severe to the point of being at risk death. In this study, early diagnosis was carried out related diabetes, where diabetes condition which sufferer’s body has low sugar levels above normal. Symptoms sufferers include frequent thirst, urination, hunger, weight loss. Based on these problems, system needed quickly find patient. This research aimed diagnose based symptoms. methods used are KNN web-based fuzzy C-means. Creating represent medical personnel experts fast-diagnosing approach diabetes. computer program embedded with knowledge characteristics results testing Fuzzy C-means applications get accuracy 96% for KNearest Neighbor method, while C-Means method Confusion Matrix calculations, obtained, so concluded Means better than K-Nearest method.