Abstract
The recently introduced augmented complex nonlinear gradient descent (ACNGD) algorithm for complex domain adaptive filtering which utilises the full second order statistical information is shown to be suitable for the processing of both circular and noncircular signals. By virtue of the underlying widely nonlinear model, the complex nonlinear gradient descent (CNGD) is shown to successfully model conventional system, however, unable to model the widely nonlinear system, and the ACNGD is capable to model both the conventional and widely nonlinear system. Simulations in adaptive modelling context for signals with different probability distributions and degrees of circularity support the analysis.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Mandic DP, Goh SL (2009) Complex valued nonlinear adaptive filters: noncircularity, widely linear and neural models. Wiley
Hirose A (2003) Complex-valued neural networks: theories and applications. World Scientific Publishing
Kim T, Adali T (2003) Approximation by fully complex multilayer perceptrons. Neural Comput 15(7):1641–1666
Pritzker Z, Feuer A (1991) Variable length stochastic gradient algorithm. IEEE Trans Signal Process 39(4):997–1001
Widrow B, McCool J, Ball M (1975) The complex LMS algorithm. Proc IEEE 63(4):719–720
Xia Y, Jelfs B, Van-Hulle MM, Principe JC, Mandic DP (2009) An augmented echo state network for nonlinear adaptive filtering for complex noncircular signals. IEEE Trans Neural Net
Xia Y, Javidi S, Mandic DP (2010) A Regularised Normalised Augmented Complex Least Mean Square Algorithm. In: Proceedings of the IEEE
Cheong-Took C, Mandic DP (2010) A quatemion widely linear adaptive filter. IEEE Trans Signal Process 58(8):4427–4431
Neeser FD, Massey JL (1993) Proper complex random processes with applications to information theory. IEEE Trans Inf Theory 39(4):1293–1302
Kreutz-Delgado K (2006) Complex gradient operator and the ICIR calculus, Course lecture supplement ECE275A, Department of Electrical and Computer Engineering, University of California, San Diego
Ujang BC, Took CC, Mandic DP (2014) Adaptive convex combination approach for the Identification of improper quaternion processes. IEEE Trans Neural Networks and learning system 25(1)
Goh SL and Mandic DP (2004) A class of low complexity and fast converging algorithm for complex-valued neutral networks. In: IEEE workshop on machine learning for signal processing
Xia Y, Jelfs B, Van Hulle MM, Principe JC, Mandic DP (2011) An augmented echo state network for nonlinear adaptive filtering of complex noncircular signals. IEEE Trans on Neural Net 22(1)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this paper
Cite this paper
Amadi, C.C., Ujang, B.C., Hashim, F.B. (2016). Nonlinear System Modelling Utilizing Second Order Augmented Statistics Complex Value Algorithm. In: Soh, P., Woo, W., Sulaiman, H., Othman, M., Saat, M. (eds) Advances in Machine Learning and Signal Processing. Lecture Notes in Electrical Engineering, vol 387. Springer, Cham. https://doi.org/10.1007/978-3-319-32213-1_20
Download citation
DOI: https://doi.org/10.1007/978-3-319-32213-1_20
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-32212-4
Online ISBN: 978-3-319-32213-1
eBook Packages: EngineeringEngineering (R0)