Adaptive split spectrum processing using a neural network
Source abstract
Abstract
Abstract The polarity thresholding algorithm for split spectrum processing (SSP) is known to work well once properly tuned. However, there are several problems related to the finding of the right split parameters such as the number of filters and the information carrying spectral range. Here we show that the polarity thresholding method can be formulated as a multilayer perceptron (MLP) neural network with binary neurons and binary input signals operating in feedforward mode. Then the method is generalized to process nonbinary data using an adaptive MLP with graded neurons. Experiments with real ultrasonic NDE signals are presented using the conventional backpropagation optimization algorithm (BP) and a second order optimization method (BFGS) with exact line search. Finally, alternative adaptive algorithms based on a decomposition of the network into single neurons or linear discriminants are briefly discussed.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Blind Source Separation Techniques · Image and Signal Denoising Methods · Structural Health Monitoring Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (23)
Show source-provided references
1. V.L. Newhouse, N.M. Bilgutay, J. Saniie, and E.S. Furgason.Ultrasonics. 1059–68 (1982)10.1016/0041-624X(82)90003-8 ↗
2. N.M. Bilgutay, U. Benchairt, R. Murthy and J. Sanniie.Ultrasonics. 2890–97 (1990)10.1016/0041-624X(90)90004-8 ↗
3. D.E. Rumelhart et al.Parallel Distributed Processing, Vol. 1. MIT Press (1986)
4. Y.H. Pao.Adaptive Pattern Recognition and Neural Networks, Addison-Wesley (1989)
5. R. Beale and T. Jackson.Neural Computing: An Introduction, Adam Hilger (1990)10.1887/0852742622 ↗
6. J. Hertz et al.Introduction to the Theory of Neural Computation, Addison-Wesley (1991)
7. A. Papoulis.Probability, Random Variables and Stochastic Processes, McGraw-Hill (1984)
8. B. Widrow and S.D. Stearns.Adaptive Signal Processing, Prentice Hall (1985)
9. D. Hebb.The Organization of Behaviour, Wiley (1949)
10. F. Rosenblatt.Psychological Review 65386–408 (1958)10.1037/h0042519 ↗
11. R.P. Lippmann.IEEE ASSP Magazine April (1987)
12. R.P. Lippmann.IEEE Communications Magazine November (1989)
13. P. Werbos. Beyond Regression: New tools for prediction and analysis in the behaviour sciences, PhD. dissertation, Harvard University, Cambridge, MA, November 1974
14. L. Ericsson and T. Stepinski. Signal Processing for Ultrasonic Testing of Anisotropic Materials. Swedish Nuclear Power Inspectorate. Report SKI TR 92:1, January 1992
15. R.O. Duda and P.E. Hart.Pattern Classification and Science Analysis, Wiley (1973)
16. P.J. Huber.Robust Statistics, Wiley (1981)10.1002/0471725250 ↗
17. P. Karpur et al.Ultrasonics 25204–208 (1987)10.1016/0041-624X(87)90034-5 ↗
18. P. Karpur et al.Ultrasonics 26204–209 (1988)10.1016/0041-624X(88)90068-6 ↗
19. R. Fletcher.Practical Methods in Optimization, 2nd edition, Wiley (1987)
20. G.V. Relakitis et al.Engineering Optimization, Wiley (1983)
21. M. Gustafsson. Adaptive Split Spectrum Algorithms and Theoretical Aspects of the Split Spectrum Technique. Report UPTEC 92114R, Department of Technology, Uppsala University, Sweden (1992)
22. J. Xin et al.Materials Evaluation 8987–992 (1991)
23. J. Saniie et al.IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control 38133–140 (1991)10.1109/58.68470 ↗