Non-Invasive Fetal Heartbeat Detection using Third-Order Cumulant Slices Matching and ANN Classifiers

W.A. Zgallai (UK)


Thirdorder cumlants, ECG signal, neural networkclassifiers, noninvasive detection, fetal heartbeats


Many techniques have been introduced to detect fetal heartbeats during labour. In this paper, the advances in higher-order statistics, non-linear filtering, and artificial neural networks are exploited to propose a hybrid technique to improve the non-invasive detection of fetal heartbeats during labour. The proposed hybrid system uses the mother and fetal third-order cumulants (TOCs), which carry the signature imprints of their respective QRS-complexes, in the signal processing phase. Quadratic and cubic Volterra filters with LMF updates have been employed to synthesise the signal into linear, quadratic, and cubic parts, and retain only the linear part. The classification phase employs an LMS-based single hidden-layer perceptron. The sensitivity, specificity and classification rate have been calculated. The technique has been evaluated for diagonal, wall, or arbitrary TOC slices, employing both the LMF-based quadratic and cubic Volterra filters. Results have shown a detection rate of 86% of fetal heartbeats during labour.

Important Links:

Go Back