<![CDATA[Vital sign monitoring plays an important role in supporting early detection of health conditions. However, most Internet of Things (IoT)-based health monitoring systems are limited to displaying physiological data without providing automatic health status classification and integrated real-time cloud-based monitoring. This study aims to design and develop an IoT-based vital sign monitoring system using Mamdani Fuzzy Logic and Firebase Realtime Database to classify health conditions into Normal, Alert, and Emergency categories. The proposed system employs a NodeMCU ESP8266 microcontroller, a MAX30102 sensor to measure heart rate and blood oxygen saturation (SpO₂), an MLX90614 sensor to measure body temperature, Firebase Realtime Database for cloud data synchronization, and a web-based monitoring dashboard. The Mamdani Fuzzy method utilizes three input variables with 15 fuzzy rules, Max–Min inference, and centroid defuzzification. Sensor validation was conducted on five healthy adult respondents aged 25–30 years by comparing the sensor measurements with reference medical devices. The MLX90614 sensor achieved a Mean Absolute Error (MAE) of 0.136°C, a Root Mean Square Error (RMSE) of 0.140°C, and a correlation coefficient of 0.998. For heart rate measurement, the MAX30102 sensor produced an MAE of 1.6 BPM, an RMSE of 1.673 BPM, and a correlation coefficient of 0.956, while SpO₂ measurement resulted in an MAE of 1.2%, an RMSE of 1.265%, and a correlation coefficient of 0.968. Verification of the Mamdani Fuzzy implementation against MATLAB simulation showed an average difference of 0.37 on a fuzzy output scale of 0–100 without affecting the resulting health status classification. The developed system successfully performs real-time vital sign monitoring and automatic health status classification through a web interface and Firebase Realtime Database. Nevertheless, the system is intended as an initial health monitoring support tool rather than a medical diagnostic device, as clinical validation with healthcare professionals has not yet been conducted.]]>
Copyrights © 2026
