Abstract
A new approach is proposed to improve the general identification algorithm of multidimensional systems using wavelet networks . The general algorithm involves mapping vector input into its norm to avoid problem of dimensionality in construction multidimensional wavelet basis functions. Thus, the basis functions are spherically symmetric without direction selectivity. In order to restore the direction selectivity, the improved approach weights the input variables before mapping it into a scalar form. The weights can be obtained using universal optimization algorithms. Generally, only local optimal weights are obtained. Even so, performance of identification can be improved.
Similar content being viewed by others
References
Zhang Jun, Gilbert G W, Yubo Miao. Wavelet neural networks for function learning [J]. IEEE Trans., Signal Processing, 1995, 43(6): 1485–1496.
Zhang Qinghua, Benveniste A. Wavelet networks [J]. IEEE Trans., Neural Networks, 1992, 3(6): 889–898.
Zhang Qinghua. Using wavelet network in nonparametric estimation[J]. IEEE Trans., Neural Networks, 1997, 8 (2): 227–236.
Jonas Sjöberg, Zhang Qinghua, Lennart Ljung, et al. Nonlinear block-box modeling in system identification: a unified overview [J]. Automatica, 1995, 31 (12): 1691–1724.
Chen S, Cowan C F N, Grant P M. Orthogonal least squares leaning algorithm for radial basis function networks [J]. IEEE Trans., Neural Networks, 1991, 2(2): 302–309.
Mallat S G. Matching pursuits with time-frequency dictionaries[J]. IEEE Trans., Signal Process. 1993, 41(12): 3397–3415.
Xu Jinhua, Daniel W C Ho. A basis selection algorithm for wavelet neural networks [J]. Neurocomputing, 2002, 48 (1–4): 681–689.
Author information
Authors and Affiliations
About this article
Cite this article
Shi, Hl., Cai, Yl. & Qiu, Zl. Improved system identification approach using wavelet networks. J. of Shanghai Univ. 9, 159–163 (2005). https://doi.org/10.1007/s11741-005-0070-6
Received:
Revised:
Issue Date:
DOI: https://doi.org/10.1007/s11741-005-0070-6