Effective fall detection and post-fall breath rate tracking using a low-cost CW Doppler radar sensor.

Area of Science:

• Biomedical Engineering
• Signal Processing
• Machine Learning

Background:

• Existing Doppler radar fall detection systems suffer from false alarms and lack post-fall health tracking.
• These limitations reduce accuracy and overall suitability for real-world applications.

Purpose of the Study:

• To develop a cost-effective and robust fall detection system with integrated post-fall health tracking.
• To address the limitations of current systems by improving accuracy and reducing false alarms.

Main Methods:

• Utilized a 3.18 GHz continuous-wave Doppler radar sensor for data acquisition.
• Developed a four-stage hierarchical algorithm trained at each stage for optimized classification.
• Employed a modular system architecture with low-power equipment and traditional machine learning algorithms to minimize computational cost and power consumption.

Main Results:

• Achieved a fall detection accuracy of 93.24%.
• Demonstrated a breath rate measurement error of 2.26%.
• Results are competitive with current state-of-the-art methods.

Conclusions:

• The proposed system effectively overcomes false alarms and enables post-fall health tracking.
• The system offers a cost-effective, accurate, and robust solution for fall detection.