A robust method for QRS detection based on modified p-spectrum

In this paper, we propose a robust method based on the modified p-spectrum to detect heart beats in ECG signals, which is also referred as QRS detection in the literature. QRS detection is an old problem that has been studied for several decades. In the literature, there are many methods based on various forms of transformations and thresholding, which require predetermined or fine-tuned thresholds. Another class of existing methods are based on machine learning, which require carefully labeled training data. In our study, we propose the modified p-spectrum for QRS detection, which does not require either predetermined thresholds or training data, and can operate in real-time. The proposed method is evaluated using the MIT-BIH arrhythmia database.