Volterra neural analysis of fetal cardiotocographic signals

A novel technique for electronic fetal monitoring is presented. It is based on training a Volterra based neural network to classify the fetal states based on a recorded cardiotocography (CTG) data base. The dataset consists of measurements of fetal heart rate and uterine contraction. The CTG signals have 21 attributes and three fetal states, normal, suspect and Pathologic. The Volterra based neural networks (VNN) employ Volterra series expansion for the input vectors and can produce explicit equations describing any multi-input multi-output (MIMO) system. Moreover, VNN has fast and uniform convergence. Simulations have demonstrated the efficiency of the proposed technique in electronic fetal monitoring. The VNN was able to classify the fetal states in a very low number of iterations with negligible error (practically zero). The conventional neural networks, on the other hand, have failed to achieve a reliable convergence.

[1]  Lenka Lhotska,et al.  Linear and non-linear features for intrapartum cardiotocography evaluation , 2010, 2010 Computing in Cardiology.

[2]  Janusz Jezewski,et al.  Predicting the Risk of Low-Fetal Birth Weight From Cardiotocographic Signals Using ANBLIR System With Deterministic Annealing and ${\bm \varepsilon}$ -Insensitive Learning , 2010, IEEE Transactions on Information Technology in Biomedicine.

[3]  Adam Gacek,et al.  The Prediction of Fetal Outcome by Applying Neural Network for Evaluation of CTG Records , 2008, Computer Recognition Systems 2.

[4]  Janusz Jezewski,et al.  Centralised Fetal Monitoring System with Hardware-Based Data Flow Control , 2006 .

[5]  E. Seagraves,et al.  Efficient implementation of Volterra systems using a multilinear SVD , 2007, 2007 International Symposium on Intelligent Signal Processing and Communication Systems.

[6]  Horngren Datar Rajan,et al.  3RD EDITION , 2008 .

[7]  K. Barner,et al.  Time-Varying Volterra System Identification Using Kalman Filtering , 2006, 2006 40th Annual Conference on Information Sciences and Systems.

[8]  H. V. Geijn,et al.  Critical Appraisal of Fetal Surveillance , 1994 .

[9]  S Abboud,et al.  Power spectrum analysis of fetal heart rate variability using the abdominal maternal electrocardiogram. , 1990, Journal of biomedical engineering.

[10]  W. Marsden.  I and J , 2012 .

[11]  Christine Henderson,et al.  Ctg Made Easy , 1992 .

[12]  Ping Chen,et al.  Fetal Weight Estimation Using the Evolutionary Fuzzy Support Vector Regression for Low-Birth-Weight Fetuses , 2009, IEEE Transactions on Information Technology in Biomedicine.

[13]  Tarek I. Haweel.  Modeling Induction Motors , 2012 .

[14]  Junghsi Lee,et al.  A fast recursive least squares adaptive second order Volterra filter and its performance analysis , 1993, IEEE Trans. Signal Process..

[15]  Tarek I. Haweel.  Adaptive least mean squares block Volterra filters , 2001, Int. J. Circuit Theory Appl..

[16]  Chrysostomos D. Stylios,et al.  Predicting the risk of metabolic acidosis for newborns based on fetal heart rate signal classification using support vector machines , 2006, IEEE Transactions on Biomedical Engineering.

[17]  Sanjay L. Nalbalwar,et al.  Modular neural network model based foetal state classification , 2011, 2011 IEEE International Conference on Bioinformatics and Biomedicine Workshops (BIBMW).

[18]  E. Cosmi,et al.  Fractal analysis: a new method for evaluating fetal heart rate variability , 1996, Journal of perinatal medicine.

[19]  Peter Händel,et al.  Measuring Volterra kernels of analog to digital converters using a stepped three-tone scan , 2006, IMTC 2006.

[20]  Christina Catley,et al.  Predicting High-Risk Preterm Birth Using Artificial Neural Networks , 2006, IEEE Transactions on Information Technology in Biomedicine.

[21]  Andreas Antoniou,et al.  Analysis of LMS-Newton adaptive filtering algorithms with variable convergence factor , 1995, IEEE Trans. Signal Process..

[22]  Ronald K. Pearson,et al.  Identification of structurally constrained second-order Volterra models , 1996, IEEE Trans. Signal Process..

[23]  Thomas F. Kelly,et al.  A critical appraisal of fetal surveillance , 1996 .

[24]  Metin Akay,et al.  Examining fetal heart-rate variability using matching pursuits , 1996 .