Fetal ECG extraction has the vital significance for fetal monitoring.This paper introduces a method of extracting fetal ECG based on adaptive linear neural network.The method can be realized by training a small quanti...Fetal ECG extraction has the vital significance for fetal monitoring.This paper introduces a method of extracting fetal ECG based on adaptive linear neural network.The method can be realized by training a small quantity of data.In addition,a better result can be achieved by improving neural network structure.Thus,more easily identified fetal ECG can be extracted.Experimental results show that the adaptive linear neural network can be used to extract fetal ECG from maternal abdominal signal effectively.What's more,a clearer fetal ECG can be extracted by improving neural network structure.展开更多
ECG is an important tool for the primary diagnosis of heart diseases,which shows the electrophysiology of the heart.In our method,a single maternal abdominal ECG signal is taken as an input signal and the maternal P-Q...ECG is an important tool for the primary diagnosis of heart diseases,which shows the electrophysiology of the heart.In our method,a single maternal abdominal ECG signal is taken as an input signal and the maternal P-QRS-T complexes of original signal is averaged and repeated and taken as a reference signal.LMS and RLS adaptive filters algorithms are applied.The results showed that the fetal ECGs have been successfully detected.The accuracy of Daisy database was up to 84% of LMS and 88%of RLS while PhysioN et was up to 98% and 96% for LMS and RLS respectively.展开更多
The electrocardiogram(ECG) recorded from the abdominal surface of a pregnant woman is a composite of maternal ECG, fetal ECG(f ECG) and other noises, while only the f ECG component is always needed by us. With dif...The electrocardiogram(ECG) recorded from the abdominal surface of a pregnant woman is a composite of maternal ECG, fetal ECG(f ECG) and other noises, while only the f ECG component is always needed by us. With different locations of electrode pairs on the maternal abdominal surface to measure f ECGs, the signal-to-noise ratios(SNRs) of the recorded abdominal ECGs are also correspondingly different. Some regularity on how to locate electrodes to obtain higher f ECG SNRs is needed practically. In this paper, 343 groups of abdominal ECG records were acquired from 78 pregnant women with different electrode pairs locating, and an appropriate extended research database is formed. Then the regularity on f ECG SNRs corresponding to different electrode pairs locating was studied. Based on statistical analysis, it is shown that the f ECG SNRs are significantly higher in certain locations than others. Reasonable explanation is also provided to the statistical result using the theories of the fetal cardiac electrical axis and the signal phase delay.展开更多
We collected 343 groups of abdominal electrocardiogram (ECG) data from 78 pregnant women and deleted the chan- nels unable for experts to determine R-wave peaks from them; then, based on these filtered data, the sta...We collected 343 groups of abdominal electrocardiogram (ECG) data from 78 pregnant women and deleted the chan- nels unable for experts to determine R-wave peaks from them; then, based on these filtered data, the statistics of position difference of corresponding R-wave peaks for different maternal ECG components from different points were studied. The resultant statistics showed the regularity that the position difference of corresponding maternal R-wave peaks between dif- ferent abdominal points does not exceed the range of 30 ms. The regularity was also proved using the fECG data from MIT-BIH PhysioBank. Additionally, the paper applied the obtained regularity, the range of position differences of the corresponding maternal R-wave peaks, to accomplish the automatic detection of maternal R-wave peaks in the recorded all initial 343 groups of abdominal signals, including the ones with the largest fetal ECG components, and all 55 groups of ECG data from MIT-BIH PhysioBank, achieving the successful separation of the maternal ECGs.展开更多
目的设计基于移动智能终端的单通道胎儿心电监护系统,以实现扩展卡尔曼滤波(extended Kalman filtering,EKF)和奇异值分解(singular value decomposition,SVD)相结合的单通道胎儿心电提取算法,实时获取高信噪比的胎儿心电信号,完成胎心...目的设计基于移动智能终端的单通道胎儿心电监护系统,以实现扩展卡尔曼滤波(extended Kalman filtering,EKF)和奇异值分解(singular value decomposition,SVD)相结合的单通道胎儿心电提取算法,实时获取高信噪比的胎儿心电信号,完成胎心监护的远程移动医疗。方法利用STM32单片机控制24位采样芯片ADS1298,对单通道的孕妇腹部信号进行采集,并将采集后的数据经蓝牙传送给移动智能终端,在基于Android的移动智能终端上实现EKF和SVD相结合的单通道胎儿心电提取算法,完成对胎儿心电的实时提取、显示、存储与分析,计算心律变异率,实现对整个监护系统进行控制等功能。结果测试结果表明,该系统可从单通道孕妇腹部信号中准确提取出胎儿心电信号,准确度为95.60%,阳性预测率为98.71%,系统工作稳定,连续处理5个胎心周期的数据用时约为70μs,小于一个母体心动周期(约0.8 s)的时间,适于临床对胎儿心电的实时监护。结论该系统实时性强、准确率高、工作稳定、操作简单、便于携带,实现了对胎心监护的可穿戴式远程移动医疗,适合社区医院和家庭使用。展开更多
胎儿心电信号是人体的基本生理信号.胎儿心电信号通常伴有母亲心电信号的噪声干扰,为了消除噪声,采用最小均方算法设计了自适应滤波器,利用MATLAB和Xilinx System Generator开发工具搭建了滤波器模型,通过FPGA完成电路的RTL级验证.仿真...胎儿心电信号是人体的基本生理信号.胎儿心电信号通常伴有母亲心电信号的噪声干扰,为了消除噪声,采用最小均方算法设计了自适应滤波器,利用MATLAB和Xilinx System Generator开发工具搭建了滤波器模型,通过FPGA完成电路的RTL级验证.仿真结果表明,滤波器对母亲心电信号的噪声干扰能起到很好的滤波作用.展开更多
基金Foundation of Young Backbone Teacher of Beijing Citygrant number:102KB000845
文摘Fetal ECG extraction has the vital significance for fetal monitoring.This paper introduces a method of extracting fetal ECG based on adaptive linear neural network.The method can be realized by training a small quantity of data.In addition,a better result can be achieved by improving neural network structure.Thus,more easily identified fetal ECG can be extracted.Experimental results show that the adaptive linear neural network can be used to extract fetal ECG from maternal abdominal signal effectively.What's more,a clearer fetal ECG can be extracted by improving neural network structure.
文摘ECG is an important tool for the primary diagnosis of heart diseases,which shows the electrophysiology of the heart.In our method,a single maternal abdominal ECG signal is taken as an input signal and the maternal P-QRS-T complexes of original signal is averaged and repeated and taken as a reference signal.LMS and RLS adaptive filters algorithms are applied.The results showed that the fetal ECGs have been successfully detected.The accuracy of Daisy database was up to 84% of LMS and 88%of RLS while PhysioN et was up to 98% and 96% for LMS and RLS respectively.
基金supported by the National Natural Science Foundation of China(Grant No.61271079)the Supporting Plan Project of Jiangsu Province,China(Grant No.BE2010720)
文摘The electrocardiogram(ECG) recorded from the abdominal surface of a pregnant woman is a composite of maternal ECG, fetal ECG(f ECG) and other noises, while only the f ECG component is always needed by us. With different locations of electrode pairs on the maternal abdominal surface to measure f ECGs, the signal-to-noise ratios(SNRs) of the recorded abdominal ECGs are also correspondingly different. Some regularity on how to locate electrodes to obtain higher f ECG SNRs is needed practically. In this paper, 343 groups of abdominal ECG records were acquired from 78 pregnant women with different electrode pairs locating, and an appropriate extended research database is formed. Then the regularity on f ECG SNRs corresponding to different electrode pairs locating was studied. Based on statistical analysis, it is shown that the f ECG SNRs are significantly higher in certain locations than others. Reasonable explanation is also provided to the statistical result using the theories of the fetal cardiac electrical axis and the signal phase delay.
基金Project supported by the National Natural Science Foundation of China (Grant No. 61271079) and the Jiangsu Supporting Plan Project, China (Grant No. BE2010720).
文摘We collected 343 groups of abdominal electrocardiogram (ECG) data from 78 pregnant women and deleted the chan- nels unable for experts to determine R-wave peaks from them; then, based on these filtered data, the statistics of position difference of corresponding R-wave peaks for different maternal ECG components from different points were studied. The resultant statistics showed the regularity that the position difference of corresponding maternal R-wave peaks between dif- ferent abdominal points does not exceed the range of 30 ms. The regularity was also proved using the fECG data from MIT-BIH PhysioBank. Additionally, the paper applied the obtained regularity, the range of position differences of the corresponding maternal R-wave peaks, to accomplish the automatic detection of maternal R-wave peaks in the recorded all initial 343 groups of abdominal signals, including the ones with the largest fetal ECG components, and all 55 groups of ECG data from MIT-BIH PhysioBank, achieving the successful separation of the maternal ECGs.
文摘胎儿心电信号是人体的基本生理信号.胎儿心电信号通常伴有母亲心电信号的噪声干扰,为了消除噪声,采用最小均方算法设计了自适应滤波器,利用MATLAB和Xilinx System Generator开发工具搭建了滤波器模型,通过FPGA完成电路的RTL级验证.仿真结果表明,滤波器对母亲心电信号的噪声干扰能起到很好的滤波作用.