Lepore N.Brieva J.Garcia J.D.Romero E.2020-03-262020-03-262017Proceedings of SPIE - The International Society for Optical Engineering; Vol. 1057297815106163320277786Xhttps://hdl.handle.net/20.500.12585/8958Fetal ECG monitoring is a useful method to assess the fetus health and detect abnormal conditions. In this paper we propose an approach to extract fetal ECG from abdomen and chest signals using independent component analysis based on the joint approximate diagonalization of eigenmatrices approach. The JADE approach avoids redundancy, what reduces matrix dimension and computational costs. Signals were filtered with a high pass filter to eliminate low frequency noise. Several levels of decomposition were tested until the fetal ECG was recognized in one of the separated sources output. The proposed method shows fast and good performance. © 2017 SPIE.Recurso electrónicoapplication/pdfenghttp://creativecommons.org/licenses/by-nc-nd/4.0/info:eu-repo/semantics/conferenceObject10.1117/12.2285962BioengineeringFetal ECGIndependent component analysisSignal processingBioinformaticsElectrocardiographyHigh pass filtersIndependent component analysisSignal processingSilicate mineralsSystems scienceAbnormal conditionsComputational costsFetal ECGFetal ecg extractionsJoint approximate diagonalization of eigen-matricesLow-Frequency NoiseBiomedical signal processinginfo:eu-repo/semantics/restrictedAccessAtribución-NoComercial 4.0 InternacionalUniversidad Tecnológica de BolívarRepositorio UTB56520286300572108228565719986186055985160800