Abstract
A complex feedforward neural network (CFNN) model is proposed via energy function optimum theory and the complex frequency response of complex finite impulse response (FIR) digital filter. Then the convergence of the model is proved, and the universality of the model is studied. Simulation results show that the proposed CFNN model can achieve a good approach to an arbitrary digital filter and has universal performance.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Yumei, D., Xiquan, G.: Digital Signal Processing, pp. 195–197. Xidian University Press, Xi’an (2001)
Yan, W., Xiaofeng, L., Juebang, Y.: Complex Neural Network on Designing FIR Digital Filter. Signal Processing 15(3), 193–198 (1999)
Jiezhao, Z., Renfa, L.: Study on the Optimum Design of the High-Order Multi-Band-Pass Filter. Acta Electronica Sinica 30(1), 87–89 (2002)
Xiaohua, W., Yigang, H., Jiezhao, Z.: Optimized Design of the Four-type FIR Filter based on Neural Networks. Journal of Circuits and Systems 8(5), 97–100 (2003)
Zhaohui, H., Jiangmin, Q., Jun, Y., Jingang, H.: Design of FIR Digital Filter Using CFNN. In: The 7th ICEMI, Beijing (2005)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Xiaoyan, M., Jun, Y., Zhaohui, H., Jiangmin, Q. (2006). A Novel CFNN Model for Designing Complex FIR Digital Filters. In: Jiao, L., Wang, L., Gao, Xb., Liu, J., Wu, F. (eds) Advances in Natural Computation. ICNC 2006. Lecture Notes in Computer Science, vol 4221. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11881070_12
Download citation
DOI: https://doi.org/10.1007/11881070_12
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-45901-9
Online ISBN: 978-3-540-45902-6
eBook Packages: Computer ScienceComputer Science (R0)