一种基于特征增强的自适应阈值R波检测算法

为提高心电信号R波检测准确度,提出了一种基于特征增强的R波检测算法。首先经过小波分析去除心电信号的高频噪声和基线漂移,然后对信号进行差分运算,选取各数据点前后连续10个差分的最大和最小值做乘积运算,达到增强R波特征的目的,最后设定两个自适应阈值,对全部数据完成检测。实验结果:经过MIT-BIH Arrhythmia Database数据验证,R波检测准确度Acc可达99.57%,敏感度Se高达99.76%,真阳性率+P高达99.82%。将得到的结果与已有文献中的方法进行比较,本文算法简单,实时性好,检测准确率高,更符合实际临床应用的需求。

An Adaptive Threshold R Wave Detection Algorithm Based on Feature Enhancement

In order to improve the accuracy of R-wave detection of ECG signals, an R-wave detection algorithm based on feature enhancement is proposed. Firstly, the wavelet analysis is used to remove the high-frequency noise and baseline drift of the ECG signal, and then the signal is subjected to differential operation. The maximum and minimum values of 10 consecutive differences before and after each data point are selected as the product to achieve the purpose of enhancing the R-wave feature. Finally, Set two adaptive thresholds to complete the detection of all data. Experimental results: After MIT-BIH Arrhythmia Database data verification, the accuracy of R wave detection Acc can reach 99.57%, the sensitivity Se is as high as 99.76%, and the true positive rate +P is as high as 99.82%, The obtained results are compared with the methods in the existing literature. The algorithm is simple, real-time, and has high detection accuracy, which is more in line with the needs of practical clinical applications.