An internet of things-based healthcare system performing on a prediction approach based on random forest regression

Abstract

To predict physiological indicators, such as heart rate, blood pressure, and body heat sensors, this study develops an internet of things (IoT)-based healthcare approach performing on random forest regression models and mean square error (MSE). Machine learning approaches such as random forest design is trained to predict factors like age, heart rate, and recorded physiological measures using a dataset generated by sensors with Raspberry Pi. The precision and dependability of the models are assessed by contrasting the predictions with the physiological degrees produced by sensors. IoT-enabled models and sensors are useful for a variety of healthcare monitoring tasks, such as early anomaly detection and quick assistance for medical interventions. It is seen that the proposed model could provide appropriate predictions that are in line with common datasets demonstrated by the results. Moreover, there is strong agreement between the sensor readings and the predicted values for the considered parameters showcasing the outperformance of the proposed healthcare system.