Diabetes Mellitus is considered one of the deadliest and most chronic diseases which cause an increase in blood sugar. Diabetes is one of the most notable diseases in the world and ruling the world. But the hike in machine learning approaches solves the critical problem. In the paper, a machine learning-based approach has been proposed for the classification and prediction of diabetes. The main goal of this study is to build a model to predict diabetes with high accuracy and decrease risk. Therefore, some supervised machine learning algorithms like Support vector machines, Decision trees, KNN, and Logistic regression are used to predict the early stage of diabetes. We have also used the ensemble techniques like bagging, voting, and boosting and we have also used the artificial neural network to improve the accuracy of the machine learning models for the PIMA diabetes dataset, therefore, predicting in the best way. In the proposed system we used boosting technique for the Sylhet diabetes dataset to improve the accuracy of the machine learning model The performance of all the machine learning models and ANN are evaluated on various measures like Precision, Accuracy, F-Measure, and Recall.
₹10000 (INR)
NON IEEE -2022