Diagnosis of diabetes using Bagging algorithm

Diabetes is a disease that is caused by high blood sugar levels. The various traditional methods available for diagnosing diabetes are based on physical and chemical tests. These methods can have errors due to various uncertainties. For statistical classification of diabetes, we used a data set that includes ۷۶۸ samples (patients) and ۸ features were examined. And we used the bagging algorithm to implement. The combining classification algorithm combines several classifications. In fact, these classifiers each build their own model on the data and store this model. Finally, for classification, a vote is taken among these categories, and the class that gets the most votes is the final class. Using this algorithm, we were able to increase the accuracy of diabetes classification by ۷۵.۳۹%.

کلیدواژه ها:

data mining ، diabetes ، bagging algorithm.