Diabetes Prediction using Machine Learning Algorithms with Feature Selection and Dimensionality Reduction

• Published in: International Conference on Advanced Computing and Communication Systems (Online) Vol. 1; pp. 141 - 146
• Main Authors: Sivaranjani, S, Ananya, S, Aravinth, J, Karthika, R
• Format: Conference Proceeding
• Language: English
• Published: IEEE 19.03.2021
• Subjects: classifier; Diabetes; Dimensionality reduction; Feature extraction; feature selection; Machine learning algorithms; PIMA dataset; pre-processing; Radio frequency; Random Forest (RF); Random forests; Support Vector Machine (SVM); Support vector machines
• ISBN: 9781665405201; 1665405201
• ISSN: 2575-7288
• DOI: 10.1109/ICACCS51430.2021.9441935

In today's world diabetes has become one of the most life threatening and at the same time most common diseases not only in India but around the world. Diabetes is seen in all age groups these days and they are attributed to lifestyle, genetic, stress and age factor. Whatever be the reasons for diabetics, the outcome could be severe if left unnoticed. Currently various methods are being used to predict diabetes and diabetic inflicted diseases. In the proposed work, we have used the Machine Learning algorithms Support Vector Machine (SVM) & Random Forest (RF) that would help to identify the potential chances of getting affected by Diabetes Related Diseases. After pre-processing the data, features which influences the prediction are selected by implementing step forward and backward feature selection. The Principle Component Analysis (PCA) dimensionality reduction method is analyzed after the selection of specific features and the accuracy of the prediction is 83% implementing Random Forest (RF) which is significant in comparison with Support Vector Machine (SVM) with accuracy of 81.4%.