基于生成对抗网络的动态心电信号QRS波检测

心电信号分析是预防心血管疾病的重要举措,QRS波的精确检测不仅是心电信号处理的关键步骤且对心率计算和异常情况分析具有重要作用.针对动态心电信号存在信号质量差或异常节奏波形导致常用QRS波检测方法精度较低的问题,本文提出了 一种基于生成对抗网络新型QRS波检测算法.该算法以Pix2Pix网络为基础,生成网络采用U-Net...

QRS wave detection algorithm of dynamic ECG signal based on generative adversarial networks

ECG signal detection is an important measure to prevent cardiovascular diseases.The accurate detection of QRS wave is not only a key step in ECG signal processing,but also plays an important role in heart rate calculation and abnormal situation analysis.In order to solve the problem of poor signal quality or abnormal rhythm waveforms in dynamic ECG signals,which results in low accuracy of commonly used QRS wave detection methods,therefore this paper proposes a new QRS wave detection based on our proposed algorithm.The a lgorithm is based on the Pix2Pix network.The Generative network adopts the U-Net structure,the Discriminant network uses the Patch-GAN idea,and makes full use of the jump connection structure of the U-Net structure to realize the mapping of ECG data to R wave peak position data,and improve the signal-to-noise ratio of the input signal by denoising and reorganizing the original signal.Using 2000groups of single-lead ECG signals about ICBEB dynamic ECG database for algorithm verification,comparing with the other two algorithms,the results show that the accuracy rate of QRS wave detection algorithm based on our proposed algorithm reaches 99.13%,which is significantly better than the other two algorithms.Our algorithm also gets the best results on Se and +P criteria,which shows the effectiveness of the algorithm in this paper.