Abstract
The paper presents an adaptive Gaussian radial basis function neural network (RBFNN) for rapid estimation of evoked potential (EP). Usually, a recorded EP is severely contaminated by background ongoing activities of the brain. Many approaches have been reported to enhance the signal-to-noise ratio (SNR) of the recorded signal. However, non-linear methods are seldom explored due to their complexity and the fact that the non-linear characteristics of the signal are generally hard to determine. An RBFNN possesses built-in non-linear activation functions that enable the neural network to learn any function mapping. An RBFNN was carefully designed to model the EP signal. It has the advantage of being linear-in-parameter, thus a conventional adaptive method can efficiently estimate its parameters. The proposed algorithm is simple so that its convergence behaviour and performance in signal-to-noise ratio (SNR) improvement can be mathematically derived. A series of experiments carried out on simulated and human test responses confirmed the superior performance of the method. In a simulation experiment, an RBFNN having 15 hidden nodes was trained to approximate human visual EP (VEP). For detecting gene rate=0.005) speeded up the estimation remarkably by using only 80 ensembles to achieve a result comparable to that obtained by averaging 1000 ensembles.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Aminoff, M.J. (1980): ‘Electrodiagnosis in clinical neurology,’ Churchill Livingstone, New York
Boston, J.R. (1985): ‘Noise cancellation for brainstem auditory evoked potentials,’IEEE Trans. Biomed. Eng.,32, pp. 1066–1070
Cerutti, S., Chiarenza, G., Liberati, D., Mascellani, P. andPavesi, G. (1988): ‘A parametric method of identification of single-trial event-related potentials in the brain,’IEEE Trans. Biomed. Eng.,35, pp. 701–711
Chan, F.H.Y., Lam, F.K., Poon, P.W.F. andDu, M.H. (1992): ‘Measurement of human BAEP by the maximum length sequence technique,’Med. Biol. Eng. Comput.,30, pp. 32–40
Chinrungrueng, C. andSequin, C.H. (1995): ‘Optimal adaptive K-means algorithm with dynamic adjustment of learning rate,’IEEE Trans. Neural Networks,6, pp. 157–169
Desmedt, J.E. (1979): ‘Cognitive components in cerebral event-related potentials and selective attention’, Karger, Basel, Switzerland
DeWeerd, J.P.C. (1981): ‘A posteriori time-varying filtering of averaged evoked potential’,Biol. Cybern.,41, pp. 211–222
Fung, K.S.M., Chan, F.H.Y., Lam, F.K., Liu, J.G. andPoon, P.W.F. (1996): ‘Visual evoked potential enhancement by an artificial neural network filter’,Bio-Med. Mat. Eng.,6, pp. 1–13
Harmony, T. (1984): ‘Neurometric assessment of brain dysfunction in neurological patients’, (Lawrence Erlbaum, Hillsdale, NJ)
Hartman, E.J., Keeler, J.D. andKowalski, J.M. (1990): ‘Layered neural networks with Gaussian hidden units as universal approximation’,Neural Comput.,2, pp. 1210–215
Kalouptsidis, N. andTheodoridis, S. (1993): ‘Adaptive system identification and signal processing algorithms’, (Prentice Hall, New York)
Laguna, P., Meste, O., Jane, R., Poon, P.W., Caminal, P., Rix, H., andThakor, N.V. (1992): ‘Adaptive filter for event-related bioelectric signals using an impulse correlated reference input: comparison with signal averaging techniques’,IEEE Trans. Biomed. Eng.,39, pp. 1032–1044
Lam, F.K., Chan, F.H.Y., Poon, P.W.F., Qiu W. andXu, B.Z. (1994): ‘Visual evoked potential measurement by adaptive filtering’,Bio-Med. Mater. Eng.,4, pp. 409–417
McGillen, C.D., Aunon, J.I. andYu, K.B. (1985): ‘Signals and noise in evoked brain potentials’,IEEE Trans. Biomed. Eng.,BME-32, pp. 1012–1016
Micchelli, C.A. (1986): ‘Interpolation of scatter data: distance matrices and conditionally positive definite functions’,Constructive Approximation,2, pp. 11–22
Mirchandani, G., Zinser, R.L. andEvans, J.B. (1992): ‘A new adaptive noise cancellation scheme in the presence of crosstalk’,IEEE Trans. Circuits Syst. ± II: Analog Digital Sig. Proc.,39, pp. 681–694
Park, J. andSandberg, I.W. (1991): ‘Universal approximation using radial basis function networks’,Neural Comput.,3, pp. 247–257
Parsa, V. andParker, P. (1994): ‘Constrained crosstalk resistant adaptive noise canceller’,Electron. Lett.,30, pp. 1276–1277
Parsa, V., Parker, P. andScott, R. (1994): ‘Crosstalk resistant adaptive noise cancellation applied to somatosensory evoked potential enhancement’,Proc. 1995 Int. Conf. on Acoustics, Speech and Signal Processing, Detroit, USA, vol. 5, pp. 2931–2934
Powell, M.J.D. (1987): ‘Radial basis functions for multivariable interpolation: a review’, Algorthms for Approximation, pp. 143–167
Qiu, W., Chan, F.H.Y., Lam, F.K. andPoon, P.W.F. (1994): ‘An enhanced approach to adaptive processing of the brain stem auditory evoked potential’,Australasian Physical Eng. Sci. Med.,17, pp. 131–135
Regan, D. (1972): ‘Evoked potentials in psychology, sensory physiology, and clinical medicine’ (Wiley, New York)
Regan, D. (1989): ‘Human brain electrophysioloogy: evoked potentials and evoked magnetic fields in science and medicine’ (Elsevier, New York)
Sherstinsky, A. andPicard, R.W. (1996): ‘On the efficiency of the orthogonal least squares training method for radial basis function networks’,IEEE Trans. Neural Networks,7, pp. 195–200
Shirvaikar, M.V. andTrivedi, M.M. (1995): ‘A neural network filter to detect small targets in high clutter backgrounds’,IEEE Trans. Neural Network,6, pp. 252–257
Uncini, A., Marchesi, M., Orlandi, G. andPiazza, F. (1990): ‘Non-linear adaptive filter using neural network’,Proc. Int. Conf. Neural Network, Paris, vol. 1, p. 158
Vaz, C.A. andThakor, N.V. (1989): ‘Adaptive Fourier estimation of time-varying evoked potentials’,IEEE Trans. Biomed. Eng.,36, pp. 448–455
Widrow, B. andStearns, S.D. (1985): ‘Adaptive signal processing’ (Prentice-Hall, Englewood Cliffs, NJ)
Widrow, B., Glover, J.R., McCoool, J.M., Kaunitz, J., Williams, C.S., Hearn, R.H., Zeidler, J.R., Dong, E. Jr. andGoodlin, R.C. (1975): ‘Adaptive noise canceling: Principles and applications’,Proc. IEEE,63, pp. 1692–1716
Xiao, H.Y., Yi, S.Z. andZhen, Y.H. (1994): ‘Peak component latency-corrected average method for evoked potential waveform estimation’,IEEE Trans. Biomed. Eng.,41, pp. 1072–1082
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Fung, K.S.M., Chan, F.H.Y., Lam, F.K. et al. A tracing evoked potential estimator. Med. Biol. Eng. Comput. 37, 218–227 (1999). https://doi.org/10.1007/BF02513290
Received:
Accepted:
Issue Date:
DOI: https://doi.org/10.1007/BF02513290