Abstract:In this paper, we address the imminent problem which arises when researchers unjudiciously use a linear and instantaneous (memoryless) model for the source mixing structures of independent component analysis (ICA), also known as blind source separation (BSS), in persuit of separating noisy and frequently nonstationary combined mother and fetal electrocardiogram (ECG) signals from cutaneous measurements under the following false assumptions. (1) Sensors (electrodes) are instantaneous linear mixtures of mother and fetal source signals. (2) Noise is an additive Gaussian perturbation. (3) Mother and fetal ECG signals are assumed to be stationary and linear, mutually statistically independent and statistically independent from noise. (4) Most of the second-order (SO) and fourth-order (FO) blind source separation (BSS) methods developed this last decade assume that third-order cumulants vanish hence the need to use FO. All these assumptions are not valid and will be challenged. We will expose these vices without providing any significant contributions for overcoming them. Rather, we provide a framework for investigations which are based on conformal mapping of nonlinear mixtures and novel dynamic nonlinear structures with time-variant memory to cater for quadratic coupling between mother and fetal which is quasi-periodical and the concomitant (quasi) cyclostationarity. Results given here show linear ICA shortfalls in nonstationary environment which is precipitated by quadratic coupling between mother and fetal ECGs during events of synchronised QRS complexes and P-waves and account for more than 20% of the 100,000 maternal cardiac cycles obtained from several clinical trials.Keywords: Noninvasive fetal electrocardiogram, Blind source separation, linear/nonlinear independent component analysis, quadratically coupled sources, nonlinear and nonstationary mixtures.
I. DISCUSSIONS
I.1 Issues for discussions• The unsuitability of using linear independent component analysis (ICA) or blind source separation (BSS) to the problem of separating fetal heartbeat from transabdominally measured signals.• Wrong assumptions and conditions for solutions to the above problem.• Evidence of nonlinear coupling and (quasi) cyclostationarity in the transabdominally measured signals.• Present techniques for nonlinear ICA only cater for nonlinear mixtures and may not be adequate for nonlinear mixtures of individually nonlinear mother/fetal ECGs.
I.2 Linear Independent Component Analysis (ICA)Blind source separation is to recover unobservable independent sources (or signals) from multiple observed data masked by linear mixing. Most existing algorithms for linear mixing models stem from the theory of the independent component analysis (ICA) [1]- [3]. Most of the second-order (SO) and fourth-order (FO) blind source separation methods developed this decade are aimed at blindly separating statistically independent sources that are assumed zero-mean, stationary and ergodic. Nevertheless, in many situations of practical interest, such as in ...