Title :
A new non-linear recursive algorithm for obtaining the fetal electrocardiogram
Author :
Soria, E. ; Martínez, M. ; Calpe, J. ; Franccs, J.V. ; Serrano, A.J. ; Guerrero, J.F.
Author_Institution :
Grupo de Procesado Digital de Senales, Valencia Univ., Spain
Abstract :
The addition of a non-linear block at the output of an FIR adaptive filter improves its performance. A new recursive algorithm is proposed to increase the velocity of convergence of the learning schemes based on gradient descent. The behavior of the entire system is analyzed in a non-invasive extraction of fetal ECG. Experiments with real and simulated registers show that the new algorithm is better than the classic LMS for recovering fetal ECG
Keywords :
FIR filters; adaptive filters; electrocardiography; medical signal processing; recursive filters; FIR adaptive filter; classic LMS; convergence velocity; electrodiagnostics; fetal electrocardiogram; learning schemes; nonlinear block; nonlinear recursive algorithm; real registers; recursive algorithm; simulated registers; Adaptive filters; Adaptive systems; Convergence; Electrocardiography; Finite impulse response filter; Least squares approximation; Neural networks; Neurons; Stability; System identification;
Conference_Titel :
Computers in Cardiology 1997
Conference_Location :
Lund
Print_ISBN :
0-7803-4445-6
DOI :
10.1109/CIC.1997.647936
