Evolutionary self-adaptive multimodel prediction algorithms of the fetal magnetocardiogram
2002 14th International Conference on Digital Signal Processing Proceedings. DSP 2002 (Cat. No.02TH8628) - Tập 2 - Trang 1149-1152 vol.2
Tóm tắt
A novel technique for the analysis, nonlinear model identification and prediction of the fetal magnetocardiogram (f-MCG) is presented. f-MCGs can be recorded with the use of specific totally non-invasive superconductive quantum interference devices (SQUID). For the analysis and classification of the f-MCG signals we introduce an intelligent method that combines the following well known advanced signal processing techniques: the genetic algorithms (GA), the multimodel partitioning (MMP) theory and the extended Kalman filters (EKF). Simulations illustrate that the proposed method is selecting the correct model structure and identifies the model parameters in a sufficiently small number of iterations and tracks successfully changes in the signal, in real time. The information provided by the proposed analysis is easily interpreted and assessed by gynecologists and consist of the clinical status of the fetus. The proposed algorithm can be parallel implemented and also a VLSI implementation is feasible.
Từ khóa
#Prediction algorithms #Signal processing algorithms #Superconducting magnets #Magnetic analysis #Signal processing #Predictive models #Magnetic devices #Superconductivity #Interference #SQUIDsTài liệu tham khảo
10.1007/s002469900150
10.1111/j.1471-0528.1999.tb08149.x
10.1002/(SICI)1097-0223(199907)19:7<677::AID-PD597>3.0.CO;2-Z
10.1016/S0002-9378(98)70282-0
tong, 1983, Threshold Models in Nonlinear Time Series Analysis, 10.1007/978-1-4684-7888-4
10.1109/TAES.1986.310718
10.1109/TAES.1981.309141
andrade, 1978, On the optimal and suboptimal nonlinear filtering problem for discrete-time systems, IEEE Trans Automat Contr, 23, 1062, 10.1109/TAC.1978.1101894
10.1109/TAC.1968.1098800
karimiemi, 1974, The fetal nagnetocardiogram, Journal of Perinatal Medicine, 2, 214
10.1055/s-2007-1023539
10.1161/01.RES.67.6.1503
10.1515/jpme.1984.12.5.273
10.1088/0967-3334/16/3/006
10.1111/j.1471-0528.1994.tb13547.x
10.1088/0143-0815/10/4B/002
10.1515/jpme.1995.23.6.459
kotini, 2001, Linear analysis of fetal magnetocardiogram recordings in normal pregnancies at various gestational ages, Journal of Obstetrics and Gynaecology, 21, 154, 10.1080/01443610020026074
10.1109/TAC.1971.1099684
beligiannis, 1999, Evolutionary Multimodel Partitioning Filters for Nonlinear Systems, Genetic and Evolutionary Computation Conference 1999 Poster Session, 11, 1227
chui, 1987, Kalman Filtering with Real Time Applications, 10.1007/978-3-662-02508-6
beligiannis, 2000, Self-Adaptive Evolution Strategies for ARMA Model Identification, X European Signal Processing Conference
beligiannis, 1999, Evolutionary Non-Linear Multimodel Partitioning Filters, IEEE International WorkShop on Intelligent Signal Processing 1999, 77
10.1109/29.56035
demiris, 2000, Nonlinear AR Model Identification with Unknown Process Order, 2000 IEEE International Symposium on Intelligent Signal Processing, 777