Efficient wavelet networks for function learning based on adaptive wavelet neuron selection

Author(s): J. Zhang ; X.P. Gao ; Y.Q. Li
DOI: 10.1049/iet-spr.2010.0186

For access to this article, please select a purchase option:

Buy article PDF

Buy Knowledge Pack

IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.

Learn more about IET membership

Recommend Title Publication to library

IET Signal Processing — Recommend this title to your library

Thank you

Your recommendation has been sent to your librarian.

Author(s): J. Zhang ^{1, 2, 3} ; X.P. Gao ¹ ; Y.Q. Li ³
- Affiliations: 1: College of Information Engineering, Xiangtan University, Xiangtan, People's Republic of China
  2: College of Information Engineering, Guangdong University of Technology, Guangzhou, People's Republic of China
  3: Center for Brain-Computer Interfaces and Brain Information Processing, College of Automation Science and Engineering, South China University of Technology, Guangzhou, People's Republic of China
Source: Volume 6, Issue 2, April 2012, p. 79 – 90
DOI: 10.1049/iet-spr.2010.0186 , Print ISSN 1751-9675, Online ISSN 1751-9683

In this study, a novel four-layer architecture of wavelet network is proposed for function learning. Compared to conventional three-layer wavelet networks, the proposed one exploits adaptive wavelet neuron selection technique according to input information, so that the widespread structural redundancy is avoided. Meanwhile, it controls the scale of problem solution. Based on the proposed architecture, two wavelet networks including single-wavelet neural network and multi-wavelet neural network are built and verified for function learning. The experimental results demonstrate that our models are remarkably superior to some of the well-established three-layer wavelet networks including Zhang's model and Pati's model in terms of both speed and accuracy. Compared with Huang's real-time neural network, the proposed models have significantly better accuracy with basically similar speed.

References

1. 1)
  - S.S. Iyengar , E.C. Cho , V.V. Phoha . (2002) Foundations of wavelet networks and applications.
2. 2)
  - M. Han , J. Yin . The hidden neurons selection of the wavelet networks using support vector machines and ridge regression. Neurocomputing , 471 - 479
3. 3)
  - C.J. Lin , C.C. Chin . Prediction and identification using wavelet-based recurrent fuzzy neural networks. IEEE Trans. Syst. Man Cybern. B, Cybern. , 5 , 2144 - 2154
4. 4)
  - Y. Oussar , G. Dreyfus . Initialization by selection for wavelet network training. Neurocomputing , 131 - 143
5. 5)
  - Q. Zhang . Using wavelet network in nonparametric estimate. IEEE Trans. Neural Netw. , 2 , 227 - 236
6. 6)
  - G.B. Huang , Q.Y. Zhu , C.K. Siew . Real-time learning capability of neural networks. IEEE Trans. Neural Netw. , 4 , 863 - 878
7. 7)
  - S.A. Billings , H.L. Wei . A new class of wavelet networks for nonlinear system identification. IEEE Trans. Neural Netw. , 4 , 862 - 874
8. 8)
  - X.P. Gao , B. Zhang . Interval-wavelets neural networks (II)–properties and experiment. J. Softw. , 4 , 245 - 250
9. 9)
  - D.W.C. Ho , P.A. Zhang , J. Xu . Fuzzy wavelet networks for function learning. IEEE Trans. Fuzzy Syst. , 1 , 200 - 211
10. 10)
  - R.K.H. Galvao , T. Yoneyama . A competitive wavelet network for signal clustering. IEEE Trans. Syst. Man Cybern. B, Cybern. , 2 , 1282 - 1288
11. 11)
  - D. Shi , F. Chen , G.S. Ng , J. Gao . The construction of wavelet network for speech signal processing. Neural Comput. Appl. , 3 , 217 - 222
12. 12)
  - R.M. Sanner , J.J.E. Slotine . Structurally dynamic wavelet networks for adaptive control of robotic systems. Int. J. Control , 3 , 405 - 422
13. 13)
  - Z. Zhang . Iterative algorithm of wavelet network learning from nonuniform data. Neurocomputing , 2979 - 2999
14. 14)
  - G.P. Liu . (2001) Nonlinear identification and control: a neural network approach.
15. 15)
  - G.B. Huang . Learning capability and storage capacity of two-hidden-layer feedforward networks. IEEE Trans. Neural Netw. , 2 , 274 - 281
16. 16)
  - K.W. Wong , A.C.S. Leung . On-line successive synthesis of wavelet networks. Neural Process. Lett. , 2 , 91 - 100
17. 17)
  - S. Postalcioglu , Y. Becerikli . Wavelet networks for nonlinear system modeling. Neural Comput. Appl. , 4 , 433 - 441
18. 18)
  - J. Xu , D.W.C. Ho . A basis selection algorithm for wavelet neural networks. Neurocomputing , 681 - 689
19. 19)
  - Clancy, D., Ozguner, U.: `Wavelet neural networks: a design perspective', Proc. IEEE Int. Symp. Intelligent Control, August 1994, p. 376–381.
20. 20)
  - Ling, S.H., Leung, F.H.F.: `Genetic algorithm-based variable translation wavelet neural network and its application', Proc. IEEE Int. Joint Conf. Neural Networks, July 2005, p. 1365–1370.
21. 21)
  - J. Zhang , G.G. Walter , Y. Miao , W.N.W. Lee . Wavelet neural networks for function learning. IEEE Trans. Signal Process. , 6 , 1485 - 1497
22. 22)
  - Y. Oysal , S. Yilmaz . An adaptive wavelet network for function learning. Neural Comput. Appl. , 3 , 383 - 392
23. 23)
  - C.D. Sousa , E.M. Hemerly , R.K.H. Galv . Adaptive control for mobile robot using wavelet networks. IEEE Trans. Syst. Man Cybern. , 4 , 493 - 504
24. 24)
  - S. Chen , C.F.N. Cowan , P.M. Grant . Orthogonal least squares learning algorithm for radial basis function networks. IEEE Trans. Neural Netw. , 2 , 302 - 309
25. 25)
  - X.P. Gao , B. Zhang . Interval-wavelets neural networks (I)–theory and implements. J. Softw. , 3 , 217 - 221
26. 26)
  - Y. He , F. Chu , B. Zhong . A hierarchical evolutionary algorithm for constructing and training wavelet networks. Neural Comput. Appl. , 4 , 357 - 366
27. 27)
  - Y.C. Pati , S. Krishnaprasad . Analysis and synthesis of feedforward neural networks using discrete affine wavelet transformations. IEEE Trans. Neural Netw. , 1 , 73 - 85
28. 28)
  - K.C. Kan , K.W. Wong . Self-construction algorithm for synthesis of wavelet networks. Electron. Lett. , 20 , 1953 - 1955
29. 29)
  - Q. Zhang , A. Benveniste . Wavelet networks. IEEE Trans. Neural Netw. , 6 , 889 - 898
30. 30)
  - L. Jiao , J. Pan , Y. Fang . Multiwavelet neural network and its approximation properties. IEEE Trans. Neural Netw. , 5 , 1060 - 1066

Efficient wavelet networks for function learning based on adaptive wavelet neuron selection

Efficient wavelet networks for function learning based on adaptive wavelet neuron selection

Buy article PDF

Buy Knowledge Pack

Thank you

References

Related content