基于短时傅里叶变换和盲分离的胎儿心率检测方法

Detection of Heart Rate of Fetal ECG Based on STFT and BSS

胎儿心率的变化是循环系统和中枢神经系统机能调节的表现,在围产期对胎儿进行胎心率检测具有重要的意义,基于此该文提出了一种基于短时傅里叶变换和盲分离的胎儿心率检测方法。首先对混叠心电信号进行预处理,然后运用小波变换技术分离出含有噪声的胎儿心电信号,再对它进行短时傅里叶变换和盲分离,之后计算它们的相关系数,最后选取与原信号相关性最强的一个独立分量进行峰值检测并计算出胎儿瞬时心率。实验结果表明:该方法能够提高胎儿峰值(R波)检测率,而且在信噪比较低的情况下,它对胎儿峰值(R波)定位具有较高的准确性。

Changes in heart rate of fetal is function regulating performance of the circulatory system and the central nervous system, it is significant to detect heart rate of fetus in perinatal fetal. This paper puts forward the fetal heart rate detection method based on short time Fourier transform and blind source separation. First of all, the mixed ECG signal was preprocessed, and then the wavelet transform technique was used to separate the fetal ECG signal with noise from mixed ECG signal, after that, the short-time Fourier transform and the blind separation were carried on it, and then calculated the correlation coefficient of it, Finally, An independent component that it has strongest correlation with the original signal was selected to make FECG peak detection and calculated the fetal instantaneous heart rate. The experimental results show that the method can improve the detection rate of the FECG peak（R）, and it has high accuracy in fixing peak（R） location in the case of low signal-noise ratio.