Kalman-Normalized GSR Analysis for Real-Time Stress Quantification in Wearable Systems

Area of Science:

• Physiological computing
• Psychosocial health monitoring
• Biomedical signal processing

Background:

• Rising global stress levels impact mental and physical health.
• Galvanic skin response (GSR) measures physiological stress indicators.
• Accurate stress detection is crucial for effective management.

Purpose of the Study:

• To develop an accurate and personalized system for identifying and analyzing stress levels using GSR.
• To enhance the reliability and precision of stress detection through advanced signal processing techniques.

Main Methods:

• Utilized galvanic skin response (GSR) to measure skin conductivity changes.
• Employed the Kalman filter algorithm for noise reduction in raw GSR signals.
• Implemented dynamic range normalization for personalized, consistent stress level scaling (0-500).

Main Results:

• The developed system accurately identifies stress levels across defined ranges based on over 5000 samples.
• Kalman filtering ensured stable, noise-unaffected measurements.
• Dynamic normalization provided user-specific, consistent stress detection.

Conclusions:

• The research successfully created an accurate, personalized stress detection and analysis system.
• The system offers actionable insights for stress management strategies.
• This technology has significant potential for real-world applications in mental wellness.