An integrated approach for fetal electrocardiogram (ECG) extraction based on the joint application of wavelet transform (WT) and independent component analysis (ICA) is proposed. This research is aimed at development of computer based electrocardiography systems of high resolution, which require the advanced methods for early noninvasive diagnostics of fetal status. The results of this study demonstrate that ICA can effectively distinguish the fetal independent components, but requires the use of additional methods for noise removing from these components. Elimination of noise is achieved by WT applying. Joint application of ICA and WT allowed us to extract with slight distortions of useful signal the simulated fetal ECG from the artificial signal containing maternal ECG and noise.

The key areas of application of systems with microelectrode arrays (MEA) are studying the mechanisms of diseases and testing the effect of drugs on the hum

The work is devoted to improvement of methods for noninvasive identification of low-amplitude components of electrocardiogram (ECG) - atrial late potentials (ALP) which are markers of potentially dangerous heart rhythm disorders. A combined method for ALP detection based on wavelet analysis, decomposition in the basis of eigenvectors and classification by neural network is proposed. As the result of the numerical experiment the dimension of ALP feature vector was minimized that made it possible to distinguish between 2 classes "norm - no ALP" and "pathology - ALP are present" with minimum error classification.

The possibilities of high-resolution electrocardiography (HR ECG) application for diagnostics of post-traumatic myocardial dystrophy having multifactorial

A non-invasive approach to estimation of the condition of cardiovascular system has been considered. This approach is based on detection of subtle manifestations of cardiac electrical activity using...

This research is aimed at detection and evaluation of beat-to-beat T-wave alternans in electrocardiogram. To reveal diagnostic features related to T-wave alternans, variations in amplitude and shape of T-waves from synthetic and clinical recordings were explored by means of time-domain analysis, Poincare plots, and principal component analysis together with clustering analysis.