Noninvasive extraction of fetal electrocardiogram based on Support Vector Machine

Yumei Fu; Shihan Xiang; Tianyi Chen; Ping Zhou; Weiyan Huang

doi:10.1117/12.2199662

15 October 2015 Noninvasive extraction of fetal electrocardiogram based on Support Vector Machine

Yumei Fu, Shihan Xiang, Tianyi Chen, Ping Zhou, Weiyan Huang

Proceedings Volume 9672, AOPC 2015: Advanced Display Technology; and Micro/Nano Optical Imaging Technologies and Applications; 96720O (2015) https://doi.org/10.1117/12.2199662
Event: Applied Optics and Photonics China (AOPC2015), 2015, Beijing, China

Abstract

The fetal electrocardiogram (FECG) signal has important clinical value for diagnosing the fetal heart diseases and choosing suitable therapeutics schemes to doctors. So, the noninvasive extraction of FECG from electrocardiogram (ECG) signals becomes a hot research point. A new method, the Support Vector Machine (SVM) is utilized for the extraction of FECG with limited size of data. Firstly, the theory of the SVM and the principle of the extraction based on the SVM are studied. Secondly, the transformation of maternal electrocardiogram (MECG) component in abdominal composite signal is verified to be nonlinear and fitted with the SVM. Then, the SVM is trained, and the training results are compared with the real data to ensure the effect of the training. Meanwhile, the parameters of the SVM are optimized to achieve the best performance so that the learning machine can be utilized to fit the unknown samples. Finally, the FECG is extracted by removing the optimal estimation of MECG component from the abdominal composite signal. In order to evaluate the performance of FECG extraction based on the SVM, the Signal-to-Noise Ratio (SNR) and the visual test are used. The experimental results show that the FECG with good quality can be extracted, its SNR ratio is significantly increased as high as 9.2349 dB and the time cost is significantly decreased as short as 0.802 seconds. Compared with the traditional method, the noninvasive extraction method based on the SVM has a simple realization, the shorter treatment time and the better extraction quality under the same conditions.

Citation Download Citation

Yumei Fu, Shihan Xiang, Tianyi Chen, Ping Zhou, and Weiyan Huang "Noninvasive extraction of fetal electrocardiogram based on Support Vector Machine", Proc. SPIE 9672, AOPC 2015: Advanced Display Technology; and Micro/Nano Optical Imaging Technologies and Applications, 96720O (15 October 2015); https://doi.org/10.1117/12.2199662

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available