Fetal ECG extraction using an FIR neural network

Camps, G.; Martínez, M.; Soria, Emilio

doi:10.1109/cic.2001.977639

Cited by 56 publications

(37 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Figure 1 shows a typical electrode placement scheme for the acquisition of mECG and fECG signals. In particular, eight locations (7)(8)(9)(10)(11)(12)(13)(14) are in the abdominal region, and the remaining six (1)(2)(3)(4)(5)(6) in the thoracic region. Signals (for a duration of 15 s) recorded from five of these electrode locations (1, 2, 3, 4 and 11) are shown in Fig.…”

Section: Methodsmentioning

confidence: 99%

Extraction of fetal electrocardiogram using H ∞ adaptive algorithms

Puthusserypady

2007

Med Bio Eng Comput

View full text Add to dashboard Cite

The fetal electrocardiogram (fECG) contains important information regarding the health of the fetus. However, the fECG obtained noninvasively from the abdominal surface electrical recordings of a pregnant woman are dominated by strong interference from the maternal electrocardiogram (mECG). In this paper, based on the H(infinity) principle, two adaptive algorithms are proposed for the extraction of fECG from the trans-abdominal recordings of pregnant women. The motivation behind the application of H(infinity) techniques is the fact that they are robust with respect to model uncertainties and lack of statistical information regarding noise. The proposed algorithms are applied to simulated as well as real multichannel ECG recordings and their performances are compared to that of the well-known least-mean-square (LMS) adaptive algorithm. It is found that the proposed H(infinity) based algorithms perform superior to the LMS algorithm in extracting the fECG signal.

show abstract

Section: Methodsmentioning

confidence: 99%

Extraction of fetal electrocardiogram using H ∞ adaptive algorithms

Puthusserypady

2007

Med Bio Eng Comput

View full text Add to dashboard Cite

show abstract

“…This is owing to the fact that the signal is measured far away from its source (the mother's heart), and consequently it encounters some non-linear transformation as it travels to the abdominal area. Some non-linear modelling methods have been employed to address this problem, such as Neuron Networks [9][10][11][12][13], but it is often confronted with the problem of bad generalisation capability, the trouble of learning non-convergence and selecting the neuron function or network structure on experiences.…”

Section: Introductionmentioning

confidence: 99%

Adaptive filtering in phase space for foetal electrocardiogram estimation from an abdominal electrocardiogram signal and a thoracic electrocardiogram signal

Wei

Liu

Cheng

2012

IET Signal Process.

View full text Add to dashboard Cite

In this study, an adaptive filtering in phase space for foetal electrocardiogram (ECG) extraction from a maternal abdominal ECG signal and a thoracic ECG signal is proposed. The phase space trajectory is reconstructed with one abdominal ECG signal and one thoracic ECG signal from a pregnant women. The non-linear and time-variant relationship between the thoracic ECG signal and maternal ECG component in abdominal signal is built by the adaptive local modelling in phase space, and the maternal ECG component in abdominal ECG signal can be estimated, which is then subtracted from the abdominal ECG signal to obtain a foetal ECG estimate. The local modelling process is carried on the spatial neighbouring points of each point in phase space, not on the temporal neighbouring points of each point in time sequence as usual. This can utilise the geometric information of the periodic ECG signal, and the simpler local relationship represented in phase space makes the estimation of the relationship easier and more accurate. Compared with the classical adaptive filter, the proposed method has shown the improved robustness and fidelity in restoration of the foetal ECG, testing with synthetic and real ECG signals.

show abstract

“…Various research efforts have been carried out in the area of FECG and FHR extraction, including subtraction of an averaged pattern [2], matched filtering [3], adaptive filtering [4][5][6], orthogonal basis functions [7], fractals [8], FIR [9], dynamic neural networks [10], temporal structure [11], fuzzy logic [12], frequency tracking [13], polynomial networks [14], and real-time signal processing [15]. The wavelet transform (WT) is another approach that has been proposed for FECGs processing.…”

Section: Introductionmentioning

confidence: 99%

A Method for Fetal Heart Rate Extraction Based on Time-Frequency Analysis

Karvounis

Tsipouras

Fotiadis

et al. 2006

19th IEEE Symposium on Computer-Based Medical Systems (CBMS'06)

View full text Add to dashboard Cite

A three-stage method for fetal heart rate extraction, from abdominal ECG recordings, is proposed. In the first stage the maternal R-peaks and fiducial points (QRS onset and offset) are detected, using time-frequency analysis, and the maternal QRS complexes are eliminated. The second stage locates the positions of the candidate fetal R-peaks, using complex wavelets and pattern matching theory techniques. In the third stage, the fetal R-peaks that overlap with the maternal QRS complexes are found. The method is validated using a dataset of 4 long duration recordings and the obtained results indicate high detection ability of the method (96% accuracy).

show abstract

Fetal ECG extraction using an FIR neural network

Cited by 56 publications

References 4 publications

Extraction of fetal electrocardiogram using H ∞ adaptive algorithms

Extraction of fetal electrocardiogram using H ∞ adaptive algorithms

Adaptive filtering in phase space for foetal electrocardiogram estimation from an abdominal electrocardiogram signal and a thoracic electrocardiogram signal

A Method for Fetal Heart Rate Extraction Based on Time-Frequency Analysis

Contact Info

Product

Resources

About