DocumentCode :
1837867
Title :
The Novel Method for the Fetal Electrocardiogram Extraction from the Abdominal Signal
Author :
Mi Hye Song ; Sung Pil Cho ; Ho Dong Park ; Kyoung Joung Lee
Author_Institution :
Yonsei Univ., Wonju
fYear :
2007
fDate :
22-26 Aug. 2007
Firstpage :
3282
Lastpage :
3284
Abstract :
In this paper, we have proposed a new method to extract the fetal ECG from a pregnant woman´s abdominal signal using least square acceleration (LSA) filter and adaptive impulse correlation (AIC) filter. To evaluate the performance, the proposed method and other fetal ECG extraction techniques were processed using the synthetic and real ECG data and then the results were compared. According to comparative results, the proposed method is powerful and successful for extracting the fetal ECG. It was able to separate perfectly even though the fetal beats overlap with the QRS wave of the maternal beats and to extract fetal ECG using any single-channel abdominal signal measured from pregnant woman´s abdominal surface. Also, it could be implemented easily by fast computation time and simple structure. It is sure that our method could be useful for portable fetal monitoring system.
Keywords :
adaptive filters; electrocardiography; feature extraction; least squares approximations; medical signal processing; obstetrics; abdominal signal; adaptive impulse correlation filter; fetal electrocardiogram extraction; least square acceleration filter; Abdomen; Acceleration; Adaptive filters; Biomedical engineering; Data mining; Electrocardiography; Independent component analysis; Least squares methods; Pregnancy; Signal processing; Abdomen; Algorithms; Artificial Intelligence; Cardiotocography; Diagnosis, Computer-Assisted; Electrocardiography; Fetal Heart; Humans; Pattern Recognition, Automated; Reproducibility of Results; Sensitivity and Specificity;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Engineering in Medicine and Biology Society, 2007. EMBS 2007. 29th Annual International Conference of the IEEE
Conference_Location :
Lyon
ISSN :
1557-170X
Print_ISBN :
978-1-4244-0787-3
Type :
conf
DOI :
10.1109/IEMBS.2007.4353030
Filename :
4353030
Link To Document :
بازگشت