Design of a Multi-Sensor Wearable Physiological Parameters Monitoring System Using Machine Learning Algorithm

An aging population and changing lifestyles have led to an increase in health problems, necessitating a robust and scalable medical system. A healthy society can be fostered by implementing a comprehensive health tracking system that enables early disease detection and continuous remote healthcare monitoring. This can be achieved by employing a wearable healthcare monitoring system, that can assist the medical sector in reducing hospitalizations and facilitating early diagnosis. To address this need, a Wearable Physiological Monitoring System (W-PMS) is proposed in this study. A prototype has been developed with the capability to record electrocardiography (ECG), photoplethysmography (PPG), and body temperature, and calculate crucial vital parameters such as heart rate, saturation of peripheral oxygen (SpO2) level, and blood pressure (BP). The W-PMS comprises three sensor modules integrated with a microcontroller to collect the physiological data. The acquired physiological data are processed by the microcontroller to calculate certain parameters such as heart rate and SpO2 level. The acquired data are pushed to the cloud to estimate the BP through an indigenous Android application. The data transmission between the microcontroller and the application occurs via Bluetooth communication. The final results are visualized on a mobile device, enabling users to track their health status. In conclusion, wearable devices incorporating biomedical sensors have the potential to remotely monitor an individual's health condition.