Home About Login Current Archives Announcements Editorial Board
Submit Now For Authors Call for Submissions Statistics Contact
Home > Archives > Volume 20, No 7 (2022) > Article

DOI: 10.14704/nq.2022.20.7.NQ33469

IOT Based Healthcare Monitoring System for Diabetes Prediction using Extreme Gradient Boosting Techniques

T. Ramyaveni, Dr.V.Maniraj


Human health issues must be closely examined and addressed with proper medications. Chronic illnesses such as diabetes, heart disease (HD), cancer, and chronic respiratory disease are the main causes of death worldwide. The previous 10 years have seen a lot of research into healthcare services and their technology advancements. To be more specific, the Internet of Things (IoT) has showed promise in connecting a variety of medical devices, sensors, and healthcare specialists in order to provide high-quality medical treatment in a remote place. Patient safety has improved, healthcare expenses have decreased, healthcare services have become more accessible, and the healthcare industry's operational efficiency has increased. In this paper, a diabetic patient monitoring strategy is proposed that uses an IoT-based machine learning technique called eXtreme Gradient Boosting (XGB) to support in diabetes diagnosis and classification. A successful implementation of any classifier requires proper hyperparameter optimization. This work employed Bayesian optimization, which is a very effective method for hyper-parameter optimization, to optimize the hyper-parameters of XGBoost. The efficacy of the suggested method is assessed in terms of accuracy, specificity, sensitivity, and F1score. It outperforms better than the other existing algorithms.


Heart disease, Intrnet of Things, eXtreme Gradient Boosting (XGB)

Full Text