A Study of Cloud of Things Enabled Machine Learning-Based Smart Health Monitoring System
Ayontika Das, Riya Paul, Anindya Nag, Biva Das · 2023
The healthcare industry is focusing strongly on providing in-home healthcare services, enabling patients to receive medical care in the comfort and privacy of their homes. A vital aspect of this effort involves implementing remote health monitoring systems, which allows patients in rural areas to communicate with doctors in larger cities. To develop these systems, machine learning techniques are being utilized. These systems utilize wearable sensors to collect and analyze five vital parameters: ECG readings, pulse rate, blood pressure, body temperature, and positional data. By leveraging machine learning algorithms, these systems can accurately identify suitable doctors for consultations and predict potential ailments. Furthermore, integrating Internet of Things (IoT) technology with health monitoring has dramatically enhanced the delivery of personalized and prompt healthcare. The main objective of this system is to continuously monitor patients’ vital signs in real-time, with authorized individuals able to conveniently access this information from their smartphones or PCs through a cloud server. In the study, Authors analysis various smart health monitoring systems that utilize IoT devices and machine learning techniques to enhance monitoring capabilities. Additionally, this study aims to analyze various machine learning algorithms utilized in health monitoring systems. The objective is to determine which machine learning algorithm yields superior outcomes. Authors suggest a health monitoring system achieved an impressive accuracy of 99.1% using Decision Tree as the best-performing classifier, showcasing significant promise for its intended purposes.