摘要
针对胎儿心电信号检测难的问题,提出基于FastICA及自适应相干处理的胎儿心电信号提取方法。首先利用自适应相干抵消进行基线漂移和母体心电的预处理,随后使用FastICA对数据进行分离和处理,从分离结果可以看出迭代次数为18时胎儿的心电信号最佳,然后对FastICA分离通道数进行讨论和实验,明确分离通道数目,最后使用频谱图观察处理后的胎儿心电信号质量,可以看出该方法收到了良好的效果。
In order to solve the problem of difficult detection of fetal electrocardiosignals,an extraction method of fetal electrocardiosignals based on FastICA and adaptive coherent processing is put forward.In this method,baseline drift and maternal ECG are preprocessed by adaptive coherent cancellation,and then the data is separated and processed by means of FastICA.It can be seen from the separating result that the fetal electrocardiosignal is best at 18 iterations.The number of FastICA separation channels was discussed and tested.And then,the number of separation channels was determined.The quality of fetal ECG signal was observed with the spectrogram.The observed result shows that the method has an excellent effect.
作者
刘春艳
司夏岩
崔艳群
王强
尹晶
何琪耀
LIU Chunyan;SI Xiayan;CUI Yanqun;WANG Qiang;YIN Jing;HE Qiyao(College of Optical and Electronical Information Changchun University of Science and Technology,Changchun 130114,China)
出处
《现代电子技术》
北大核心
2020年第21期35-38,共4页
Modern Electronics Technique
基金
吉林省教育厅科研项目(2016311):谱特征周期估计的胎儿心电图提取。
关键词
胎儿心电
信号提取
FASTICA
自适应滤波
噪声分析
盲信号分离
fetal electrocardiosignal
signal extraction
FastICA
adaptive filtering
noise analysis
blind signal separation
