Research on intelligent algorithm for detecting ECG R waves

Waveform detection is the basis for automatic analysis of ECG signals, and the detection accuracy has an important effect on the assay performance. In a cardiac cycle, R wave characteristics are very obvious and easy to identify, so most researchers take ECG R wave detection as the foundation of feature extraction. This paper studies the principle of ECG R wave detection and carries out an in-depth discussion on some key technologies. As a result, an intelligent algorithm of R wave detection is proposed. The algorithm uses filter, multi-order difference and Shannon energy transformation to process ECG signals, and then it adopts an improved adaptive threshold method for detecting R waves. The author used ECG data files from the MIT-BIH arrhythmia database (mitdb) to measure the performance of the algorithm. Overall, the experiment obtained 99.84% sensitivity and 99.92% precision of R wave detection, while the error rate is only 0.24%. Experiments show that, this algorithm could be also applied for R wave real-time detection under the requirements of high accuracy and low error rate.