IOT BASED HEALTH CARE PREDICTION USING AI

Abstract: Wearable health monitoring devices play a crucial role in the timely detection of medical emergencies, such as abnormal heart conditions and falls. But current systems primarily depend on cloud computing, which leads to delays, the need for reliable network connectivity, and privacy issues. To address these issues, this paper proposes an edge- intelligent wearable health monitoring system that can perform real-time health and safety monitoring by fusing multiple sensor readings and applying TinyML. Proposed system incorporates physiological and motion sensors such as heart rate, SpO₂ (oxygen saturation), body temperature and a triaxial accelerometer, interfaces to an ESP32 microcontroller. Rather than sending data to the cloud, the system leverages on-device analytics with TinyML models. This allows real-time detection of cardiac abnormalities and falls to occur on the device. The multi-sensor fusion and embedded machine learning enhance detection performance while minimizing energy and bandwidth costs. The edge computing approach allows for rapid response, improved security and privacy, and does not rely on a strong network connection. In case of a fall or other abnormal event, the device sends immediate notifications to family or health-care providers via wireless communication. The developed system offers a small, low-cost and scalable solution to continuous health monitoring, enabling safe and independent living for the elderly and patients who need continuous monitoring.

Keywords: Wearable-type sensors, IoT healthcare, real-time monitoring, fall detection, edge computing, Tiny ML, low-power systems, embedded system.