C.K.S. Vijila, P. Kanagasabapathy, S. Johnson, and P. Rajalakshmy (India)
: Adaptive Signal Processing, InterferenceCancellation, Fetal ECG, Neural Networks, ANFIS(Adaptive Neuro Fuzzy Inference System).
Non-invasive fetal electrocardiography reveals itself as a very interesting method to obtain reliable information about the fetus' state and thus assure its well being during pregnancy. This technique has the additional advantage that no energy is supplied to the fetus and thus long-term studies could be accomplished. The obtained signals are nevertheless characterized by a great amount of overlapped noise (base-line wander, power line interference, maternal electrocardiogram (MECG), electromyogram (EMG)) and its variability is increased by factors related to gestational age, position of the electrodes, skin impedance, etc. However, the main noise contribution is the maternal electrical activity since its amplitude is much higher than that of the fetus. The low fetal signal-to-noise ratio (SNR) makes it impossible to analyze the fetal ECG. [1] Attenuating the noise by classical filtering techniques is not satisfying due to an overlap in spectral content with the fetal ECG. Numerous methods have been used for the maternal signal cancellation: subtraction of an averaged pattern, orthogonal basis functions, spatial filtering, adaptive filters, etc. This paper discusses the effectiveness and the worth of designing and applying hybrid intelligent methodologies to this medical domain of application. The motivation for this work is the synergy derived by the computational intelligent components, such as fuzzy logic and neural networks.
Important Links:
Go Back
