TERMA Framework for Biomedical Signal Analysis: An Economic-Inspired Approach

Area of Science:

• Biomedical Engineering
• Signal Processing
• Physiological Monitoring

Background:

• Biomedical signals contain crucial physiological event information marked by peaks.
• Accurate peak detection is essential for disease monitoring and diagnosis.
• Current methods lack a universal, robust framework for consistent event detection.

Purpose of the Study:

• Introduce a novel, universal framework for detecting events in biomedical signals.
• Develop a robust and efficient method for biomedical event detection.
• Provide a flexible solution suitable for various biomedical applications.

Main Methods:

• Developed the two event-related moving averages (TERMA) framework.
• Utilized six independent components for high-accuracy event detection.
• Defined optimal window size relationships (8 × W1 ≥ W2 ≥ 2 × W1) for moving averages.

Main Results:

• TERMA framework demonstrates high accuracy in detecting biomedical events.
• The method is flexible, universal, and robust.
• TERMA is computationally efficient, outperforming complex machine learning solutions.

Conclusions:

• TERMA offers a significant advancement in biomedical signal processing for event detection.
• The framework's simplicity and efficiency make it suitable for resource-constrained devices like wearables.
• TERMA provides a consistent and reliable approach to analyzing physiological events.