Comparison of Feed-Forward Neural Network training algorithms for oscillometric blood pressure estimation

Feed-Forward Neural Network (FFNN) has recently been utilized to estimate blood pressure (BP) from the oscillometric measurements. However, there has been no study till now that consolidated the role played by the different neural network (NN) training algorithms in affecting the BP estimates. This paper compares the estimation errors in the BP due to ten different training algorithms belonging to three classes: steepest descent (with variable learning rate, with variable learning rate and momentum, resilient backpropagation), quasi-Newton (Broyden-Fletcher-Goldfarb-Shanno, one step secant, Levenberg-Marquardt) and conjugate gradient (Fletcher-Reeves update, Polak-Ribiére update, Powell-Beale restart, scaled conjugate gradient) that are used to train two separate NNs: one to estimate the systolic pressure and the other one to estimate the diastolic pressure. The different training algorithms are compared in terms of estimation error (mean absolute error and standard deviation of error) and training performance (training time and number of training iterations to reach the optimal weights). The NN-based approach is also compared with the conventional maximum amplitude algorithm.

[1]  Roberto Battiti,et al.  First- and Second-Order Methods for Learning: Between Steepest Descent and Newton's Method , 1992, Neural Computation.

[2]  M. J. D. Powell,et al.  Restart procedures for the conjugate gradient method , 1977, Math. Program..

[3]  Dwayne Westenskow,et al.  Noninvasive blood pressure monitoring from the supraorbital artery using an artificial neural network oscillometric algorithm , 1995, Journal of Clinical Monitoring.

[4]  Martin A. Riedmiller,et al.  A direct adaptive method for faster backpropagation learning: the RPROP algorithm , 1993, IEEE International Conference on Neural Networks.

[5]  Martin Fodslette Møller,et al.  A scaled conjugate gradient algorithm for fast supervised learning , 1993, Neural Networks.

[6]  Martin T. Hagan,et al.  Neural network design , 1995 .

[7]  M. Bolic,et al.  Assessment of algorithms for oscillometric blood pressure measurement , 2009, 2009 IEEE Instrumentation and Measurement Technology Conference.

[8]  E. Mizutani,et al.  Neuro-Fuzzy and Soft Computing-A Computational Approach to Learning and Machine Intelligence [Book Review] , 1997, IEEE Transactions on Automatic Control.

[9]  C. Charalambous,et al.  Conjugate gradient algorithm for efficient training of artifi-cial neural networks , 1990 .

[10]  F. Forster,et al.  Oscillometric determination of diastolic, mean and systolic blood pressure--a numerical model. , 1986, Journal of biomechanical engineering.

[11]  C. M. Reeves,et al.  Function minimization by conjugate gradients , 1964, Comput. J..

[12]  M. Møller.  A Scaled Conjugate Gradient Algorithm for Fast Supervised Learning , 1990 .

[13]  Hilmi R. Dajani,et al.  Adaptive neuro-fuzzy inference system for oscillometric blood pressure estimation , 2010, 2010 IEEE International Workshop on Medical Measurements and Applications.

[14]  John E. Dennis,et al.  Numerical methods for unconstrained optimization and nonlinear equations , 1983, Prentice Hall series in computational mathematics.

[15]  G. Lewicki,et al.  Approximation by Superpositions of a Sigmoidal Function , 2003 .

[16]  C. Small,et al.  Survey of automated noninvasive blood pressure monitors. , 1994, Journal of clinical engineering.

[17]  Mohammad Bagher Menhaj,et al.  Training feedforward networks with the Marquardt algorithm , 1994, IEEE Trans. Neural Networks.