经验模式分解在QRS波群和T波检测中的应用

摘要

针对未经预处理的心电信号中QRS波群和T波,提出一种基于经验模式分解的检测算法.该方法首先采用结合端点延拓的经验模式分解方法对信号进行分解,然后通过适当选择分解后的固有模态函数和残余分量,不使用"经验阈值"能得到准确的检测结果.利用MIT BIH Arrhythmia Database中心电数据检测表明,QRS波群的检测率达到99%以上,T波的正确识别率也获得较大的提高.该算法中提出的端点延拓方法能有效地减少使用经验模式分解的次数,提高检测的实时性,具有较好的应用前景.%In order to detect the position of QRS and T wave in a non-preprocessed ECG signal, a combination method of the empirical mode decomposition (EMD) and morphological algorithm is introduced in this paper. Firstly, a novel boundary processing method is proposed to decrease the boundary distortion of EMD by means of signal extending. Secondly, the improved EMD is used to decompose the ECG signal into stationary intrinsic mode functions (IMFs) and residual components. Next, the two IMFs of low frequencies are reconstructed after de-noising with threshold method, and then the reconstructed signal is supplied to orient QRS to morphological method. T wave is detected by residual components. This method has been validated by the data from the MIT-BIH database, and the result shows that the detection rate of QRS is up to 99％. Moreover, this method has higher accuracy and better real-time performance compared with the traditional methods.