AI-enhanced remote health monitoring device using ESP32-CAM: real-time monitoring of vital signs and acne detection

In recent years, the demand for remote health monitoring solutions has surged, driven by the necessity for accessible and continuous healthcare. This study presents the design and implementation of an AI-enhanced remote health monitoring system using the ESP32-CAM microcontroller. The primary objective is to develop a cost-effective, real-time health surveillance solution that leverages facial recognition and deep learning models to detect symptoms such as fever and drowsiness. The methodology integrates the ESP32-CAM for image capture, the Open CV and Mediapipe libraries for facial landmark detection, and a custom-trained deep learning model to analyse patient states. Additionally, the system incorporates Google Firebase for cloud storage and real-time updates, ensuring seamless data transmission and monitoring. The results demonstrate the system's ability to accurately detect and classify key health indicators with minimal latency. This work contributes to the field by offering an efficient and scalable solution for remote healthcare, particularly beneficial in rural or resource-constrained environments.