基于小波变换的心电信号特征提取

Feature Extraction of ECG Signal Based on Wavelet Transform

心电信号中的QRS波群及T波包含心脏活动的重要信息,对心脏疾病的预防和治疗具有重要意义。为正确高效地提取出心电信号中的这些特征点,提出一种基于小波变换的QRST波检测方法。采用Coiflet4小波基对心电信号进行8层分解,用软阈值法去除心电信号中的噪声,采用改进的自适应差分阈值法对心电信号中的特征点进行检测。研究表明,该方法对于Mitdb中的心电信号,能够准确检测出Q波、R波、S波及T波位置,尤其是检测R波的平均敏感度为99.57%,平均阳性预测正确率为99.74%,具有较高的准确率和实用价值。

The QRS complex and T wave in the ECG signal contain important information about heart activity,which is of great significance for the prevention and treatment of heart diseases.In order to extract these characteristic points in the ECG signal correctly and efficiently,a detection method to detect QRST waves based on wavelet transform is proposed.The Coiflet4 wavelet base is used to decompose the ECG signal in 8 layers,the soft threshold method is used to remove the noise in the ECG signal,and the improved adaptive differential threshold method is used to detect the characteristic points in the ECG signal.The research results show that,for the ECG signal in mitdb,the Q wave,R wave,S wave and T wave positions can be detected accurately,especially the average sensitivity of detecting R wave is 99.57%,and the average positive prediction accuracy is 99.74%,which has relatively high practical value.