Development of a Stress Monitoring System

This paper presents the development of a stress monitoring system based on wearable biometric sensors and Internet of Things (IoT) technologies. The MAX30102 measures HR (50-200 beats/min) and SpO<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">₂</inf> (70-100%). GSR records skin conductivity (0-10 kOhm) to assess stress level. DS18B20 records body temperature (-55°C to +125°C, accuracy ±0.5°C). Collaborative data analysis enables accurate detection of stress conditions. Data processing is performed on ESP32 with a clock frequency of 240 MHz, transmission is carried out via Wi-Fi and Bluetooth. Machine learning algorithms (CNN, LSTM) are used to analyse biosignals and predict stress states with an accuracy of up to 92%. Data filtering is performed using Butterworth filter (3 Hz threshold) and wavelet transform. The system runs on a 1200 mAh lithium-ion battery, providing up to 24 hours of autonomy. Data visualisation is available on the 1.3-inch OLED display (128×64 pixels) or in the mobile app. The system is intended for use in medicine, psychology, sports and corporate sector for physiological condition monitoring and stress management.