An Accurate QRS complex and P wave Detection in ECG Signals using Complete Ensemble Empirical Mode Decomposition Approach.
An Accurate QRS complex and P wave Detection in ECG Signals using Complete Ensemble Empirical Mode Decomposition Approach.
复制标题
DOI：
10.1109/access.2019.2939943
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
Chon KH
中科院分区：
文献类型：
--
作者：
Hossain B;Bashar SK;Walkey AJ;McManus DD;Chon KH
提出了一种新的心电图（ECG）信号QRS波群和P波检测方法。该方法从具有自适应噪声的完整系综经验模式分解获得的模式中重建两种不同的信号，以用于QRS和P波检测，仅采用最能代表信号动态的那些模式。这种方法消除了对传统滤波的需要。我们首先检测QRS波群的位置，然后从重建的信号中去除QRS波群，以实现P波检测。我们介绍了一种新的方法，P波检测的积极和消极的幅度的ECG信号和自适应P波搜索方法，以找到真正的P波。我们的检测方法自动识别P波没有先验信息。该方法在两个著名的注释数据库-MIT BIH心律失常数据库（MITDB）和QT数据库（QTDB）上进行了验证。在所有验证数据库中，QRS检测算法的灵敏度为99.96%，阳性预测值为99.9%，误差为0.13%。P波检测方法与其他已知方法相比具有更好的性能。QTDB P波检测的敏感性为99.96%，阳性预测值为99.47%，平均误差小于或等于一个样本（4 ms）。
We developed a novel method for QRS complex and P wave detection in the electrocardiogram (ECG) signal. The approach reconstructs two different signals for the purpose of QRS and P wave detection from the modes obtained by the complete ensemble empirical mode decomposition with adaptive noise, taking only those modes that best represent the signal dynamics. This approach eliminates the need for conventional filtering. We first detect QRS complex locations, followed by removal of QRS complexes from the reconstructed signal to enable P wave detection. We introduce a novel method of P wave detection from both the positive and negative amplitudes of the ECG signal and an adaptive P wave search approach to find the true P wave. Our detection method automatically identifies P waves without prior information. The proposed method was validated on two well-known annotated databases—the MIT BIH Arrythmia database (MITDB) and The QT database (QTDB). The QRS detection algorithm resulted in 99.96% sensitivity, 99.9% positive predictive value, and an error of 0.13% on all validation databases. The P wave detection method had better performance when compared to other well-known methods. The performance of our P wave detection on the QTDB showed a sensitivity of 99.96%, a positive predictive value of 99.47%, and the mean error in P peak detection was less than or equal to one sample (4 ms) on average.