With the use of machine learning, this research set out to design a new model for the safe diagnosis and monitoring of health issues affecting female students and minors that is facilitated by the internet of things (IoT)

Abstract

With the use of IoT, high-tech health monitoring systems have been developed. The emotional and physical health of an individual may be monitored using such a device. Common mental and physical ailments may be traced back to stress, worry, and high blood pressure. Stress, anxiety, and hypertension are all common among the elderly and need specialised care in this environment. Early detection of health issues by monitoring of stress, anxiety, and blood pressure is key to avoiding irreversible harm. The quality of life of patients, carers, and healthcare providers will all improve as a result. Using covert wearable sensors and machine learning methods, develop innovative technological solutions for real-time monitoring of stress, anxiety, and blood pressure. With the use of artificial intelligence, researchers were able to identify artefacts in BP and PPG data. The idea was put out to filter the blood pressure signal to get rid of any anomalies caused by motion. Then, the systolic blood pressure (SBP) and diastolic blood pressure (DBP) connection was analysed using eleven characteristics extracted from the sociometric waveform envelope (DBP). In this study, we demonstrate the efficacy of a computational approach to calculating blood pressure. Predicting systolic and diastolic blood pressure readings from PPG signal features is accomplished by using sophisticated regression in the suggested architecture.