Performance enhancement of diabetes prediction by finding optimum K for KNN classifier with feature selection method

Machine learning algorithm plays an important role for the data generation and analysis to ease the difficulties of life. Whereas the disease classification or prediction can be performed using machine learning algorithms. These learning algorithms are applied to enhance the capability of classifiers. In this research experiments, KNN and machine learning methods are used in the prediction model to classify whether the patient is diabetic or non-diabetic. The PIMA diabetes dataset is used for research purpose in the python implemented model. Research study has been performed to improve the performance of KNN classifier by using feature selection method, normalization and considering different number of neighbors. The performance of classifier is measured based on different metrics such as accuracy, precision, sensitivity, specificity, F1 score and error rate.