• Abdullah Z
• Prarthana H D
• Sourab Rajeshh Vhanne
• sanjay M
• SharathP C

This paper presents an IoT-based wearable health monitoring system integrated with TinyML for real-time physiological data analysis. The device continuously measures heart rate, body temperature, and SpO₂ levels using low-cost biomedical sensors. A lightweight machine learning model is deployed on an ESP32 microcontroller to detect abnormal health patterns locally without cloud computation. Sensor data is simultaneously transferred to a mobile dashboard via Wi-Fi for visualization and alerts. The proposed system offers fast response, improved privacy, and low power consumption by performing inference on the edge. Experimental results demonstrate that the TinyML model accurately identifies abnormal readings with higher efficiency compared to conventional threshold-based systems.

TinyML, IoT, Wearable Health Monitoring, ESP32, MAX30102, Anomaly Detection, Edge Computing, Real-Time Systems.

"A TinyML-Based IoT Wearable Device for Real-Time Health Monitoring and Anomaly Detection", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 11, page no.e528-e539, November-2025, Available :http://www.jetir.org/papers/JETIR2511466.pdf

"A TinyML-Based IoT Wearable Device for Real-Time Health Monitoring and Anomaly Detection", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 11, page no. ppe528-e539, November-2025, Available at : http://www.jetir.org/papers/JETIR2511466.pdf