Exploiting Fuzzy Classification of Time and Amplitude for Efficient QRS Complex Detection

Electrocardiography is crucial for diagnosing and managing cardiovascular diseases, with precise QRS complex detection critical for accurate diagnosis and heart rate monitoring. Wearable ECG devices have simplified monitoring but introduced challenges in detection due to signal quality, necessitating more efficient algorithms. Traditional QRS detection methods, which focus on amplitude characteristics (Y-axis), often neglect temporal (X-axis), thus limiting their noise robustness and accuracy in signals that exhibit amplitude variations or abnormalities. To overcome these issues, this study proposes a novel QRS complex detection method that integrates fuzzy classification of both temporal and amplitude features. By evaluating both aspects simultaneously, the algorithm mimics expert judgment to improve detection accuracy. Evaluations on the MIT-BIH Arrhythmia Database show superior performance compared to widely used algorithms, achieving an average sensitivity of 99.70%, a positive predictive value of 99.80%, and an F1 score of 99.75%. The results indicate that the algorithm proposed in this study has significant application potential in ECG detection for wearable devices and the diagnosis of cardio-vascular diseases.