[Detection of P wave through wavelet transform and neural network]

Area of Science:

• Biomedical Engineering
• Signal Processing
• Computational Neuroscience

Background:

• Electrocardiogram (ECG) signal analysis is crucial for diagnosing cardiac conditions.
• Accurate detection of ECG waveform components, particularly the P wave, is essential for advanced analyses like heart rate variability (HRV).
• Traditional P wave detection methods can be limited in accuracy and robustness.

Purpose of the Study:

• To develop and evaluate a novel method for P wave detection in ECG signals.
• To assess the efficacy of combining wavelet transform and neural networks for this task.
• To determine the utility of this enhanced P wave detection for HRV analysis.

Main Methods:

• ECG signals were processed using wavelet transform for decomposition.
• A neural network was employed for the detection of P waves within the decomposed ECG signal.
• The proposed method was validated as a supplementary technique.

Main Results:

• The wavelet transform-ECG signal decomposition effectively prepared the data for analysis.
• The neural network achieved satisfactory P wave detection accuracy.
• The method demonstrated positive results when applied as a supplement to existing analyses.

Conclusions:

• The integration of wavelet transform and neural networks provides a robust approach for ECG P wave detection.
• This method offers a significant improvement and a valuable supplementary tool for HRV analysis.
• Further research can explore its application in real-time clinical settings.