Improving R Peak Detection in ECG Signal Using Dynamic Mode Selected Energy and Adaptive Window Sizing Algorithm with...

Area of Science:

• Biomedical Engineering
• Signal Processing
• Cardiology

Background:

• R peak detection is vital for analyzing electrocardiogram (ECG) signals and diagnosing cardiovascular diseases (CVDs).
• Existing methods may lack efficiency and speed for real-time applications and wearable devices.

Purpose of the Study:

• To propose a novel algorithm for efficient and accurate R peak detection in ECG signals.
• To enhance the diagnostic capabilities for cardiovascular diseases using intelligent medical devices.

Main Methods:

• The proposed method utilizes Dynamic Mode Selected Energy (DMSE) for signal component separation and Adaptive Window Sizing (AWS) to define Regions of Interest (ROIs).
• Feature extraction, Sequential Forward Selection (SFS), an ensemble of decision trees, and an R location correction (RLC) algorithm are employed for R peak identification and refinement.

Main Results:

• The algorithm achieved high experimental accuracy (99.94%), sensitivity (99.98%), and positive predictability (99.96%).
• A low detection error rate of 0.06% was recorded, demonstrating the method's precision.

Conclusions:

• The proposed R peak detection algorithm offers high efficiency and processing speed.
• Its accuracy and performance make it suitable for intelligent medical and wearable devices for cardiovascular disease diagnosis.