Communication channel equalization using wavelet network

doi:10.1016/j.dsp.2005.06.001

Digital Signal Processing

Volume 16, Issue 4, July 2006, Pages 445-452

https://doi.org/10.1016/j.dsp.2005.06.001 Get rights and content

Abstract

Wavelet network (WN) based on wavelet decomposition principle is applied to channel equalization for both linear and non-linear channels. The WN is trained by extended Kalman filter (EKF) based recursive algorithm and is compared with EKF based multi-layered perceptron (MLP) and radial basis function neural network (RBFNN). Exhaustive simulation study reveals the superiority of the WN based equalizer in terms of bit error rate performance, compared to the above equalizer scheme.

Section snippets

A.K. Pradhan received his Ph.D. degree from Sambalpur University in 2001. Currently he is with the Department of Electrical Engineering, Indian Institute of Technology, Kharagpur, India. He has served at the Department of Electrical Engineering, University College of Engineering, Burla, India, from 1992 to 2002. His research interest is in the area of signal processing applications. Dr. Pradhan received the Young Engineer Award, Indian National Academy of Engineering, India, in 2001.

References (13)

S. Chen et al.
Adaptive equalization of finite nonlinear channels using multilayer perceptrons
IEEE Trans. Signal Process.
(1990)
S.U.H. Qureshi
Adaptive equalization
IEEE Proc.
(1985)
P. Balaban et al.
Optimum diversity combining and equalization in digital data transmission with applications to cellular mobile radio—Part II: Numerical results
IEEE Trans. Commun.
(1992)
J.G. Proakis
Digital Communications
(1995)
J.C. Patra et al.
Nonlinear channel equalization of QAM constellation using artificial neural networks
IEEE Trans. Syst. Man Cyber. B
(1999)
L. Tarassenko et al.
Supervised and unsupervised learning in radial basis function classifiers
IEE Proc. Vis. Image Signal Process.
(1994)

There are more references available in the full text version of this article.

Cited by (11)

Adaptive and efficient nonlinear channel equalization for underwater acoustic communication
2017, Physical Communication
Citation Excerpt :
In addition, the major limitation of the MLP-based equalizer is its slow convergence [22]. Note that there are more advanced ANN-based methods in the wireless communications literature, e.g., functional-link ANN-based [24,25], wavelet ANN-based [26], radial basis function (RBF)-based [27], and recurrent neural network (RNN)-based [28,29] equalizers. Nevertheless, the large computational complexity due to the extensive training [22] of neural network based methods hinders their application in equalizing long underwater acoustic channels.
We investigate underwater acoustic (UWA) channel equalization and introduce hierarchical and adaptive nonlinear (piecewise linear) channel equalization algorithms that are highly efficient and provide significantly improved bit error rate (BER) performance. Due to the high complexity of conventional nonlinear equalizers and poor performance of linear ones, to equalize highly difficult underwater acoustic channels, we employ piecewise linear equalizers. However, in order to achieve the performance of the best piecewise linear model, we use a tree structure to hierarchically partition the space of the received signal. Furthermore, the equalization algorithm should be completely adaptive, since due to the highly non-stationary nature of the underwater medium, the optimal mean squared error (MSE) equalizer as well as the best piecewise linear equalizer changes in time. To this end, we introduce an adaptive piecewise linear equalization algorithm that not only adapts the linear equalizer at each region but also learns the complete hierarchical structure with a computational complexity only polynomial in the number of nodes of the tree. Furthermore, our algorithm is constructed to directly minimize the final squared error without introducing any ad-hoc parameters. We demonstrate the performance of our algorithms through highly realistic experiments performed on practical field data as well as accurately simulated underwater acoustic channels.
Robust nonlinear channel equalization using WNN trained by symbiotic organism search algorithm
2017, Applied Soft Computing Journal
Citation Excerpt :
In the last decade the WNN has been widely applied for nonlinear system identification [38], prediction of Chaotic time series [39], rainfall prediction [40], wind power forecasting [41] cancer classification of microarray gene expression data [42], human lower extremity joint moment prediction [43]. Pradhan et al. [44] applied the WNN for communication channel equalization. They reported the superior performance of WNN trained by extended Kalman filter (EKF) over multi-layered perceptron (MLP) and radial basis function neural network (RBFNN).
In the present world of ‘Big Data,’ the communication channels are always remaining busy and overloaded to transfer quintillion bytes of information. To design an effective equalizer to prevent the inter-symbol interference in such scenario is a challenging task. In this paper, we develop equalizers based on a nonlinear neural structure (wavelet neural network (WNN)) and train it's weighted by a recently developed meta-heuristic (symbiotic organisms search algorithm). The performance of the proposed equalizer is compared with WNN trained by cat swarm optimization (CSO) and clonal selection algorithm (CLONAL), particle swarm optimization (PSO) and least mean square algorithm (LMS). The performance is also compared with other equalizers with structure based on functional link artificial neural network (trigonometric FLANN), radial basis function network (RBF) and finite impulse response filter (FIR). The superior performance is demonstrated on equalization of two non-linear three taps channels and a linear twenty-three taps telephonic channel. It is observed that the performance of the gradient algorithm based equalizers fails in the presence of burst error. The robustness in the performance of the proposed equalizers to handle the burst error conditions is also demonstrated.
Nonlinear Channel Equalization Using Wavelet Neural Network Trained Using PSO
2020, SSRN
A Novel Adaptive Channel Equalizer Based on Artificial Neural Network Trained by Modified FOA
2019, 2019 IEEE 5th International Conference on Computer and Communications, ICCC 2019
Enhanced Efficiency BPSK Demodulator Based on One-Dimensional Convolutional Neural Network
2018, IEEE Access
Optical wireless communications: System and channel modelling with MATLAB®
2017, Optical Wireless Communications: System and Channel Modelling with MATLAB

View all citing articles on Scopus

S.K. Meher received his Ph.D. degree from Sambalpur University in 2003. Currently he is working in the Department of Electronics and Communication Engineering, National Institute of Science and Technology, Berhampur, India. His research interest includes signal processing and pattern recognition. Dr. Meher received the Young Scientist Award, Orissa, India, in 2003. Currently he is working as a Post Doctoral Fellow at Indian Statistical Institute, India.

A. Routray received his Ph.D. degree from Sambalpur University in 1999. Currently he is with the Department of Electrical Engineering, Indian Institute of Technology, Kharagpur, India. He has served at the Department of Electrical Engineering, Regional Engineering College, Rourkela, India, from 1992 to 1999. His research interest includes signal processing and signal classification. Dr. Routray received the Young Scientist Award, Orissa, India, in 1999. He was at Purdue University as a Post Doctoral Fellow during 2003–2004.

View full text

Communication channel equalization using wavelet network

Abstract

Section snippets

IEEE Trans. Signal Process.

Adaptive equalization

IEEE Proc.

Optimum diversity combining and equalization in digital data transmission with applications to cellular mobile radio—Part II: Numerical results

IEEE Trans. Commun.

Digital Communications

Nonlinear channel equalization of QAM constellation using artificial neural networks

IEEE Trans. Syst. Man Cyber. B

Supervised and unsupervised learning in radial basis function classifiers

IEE Proc. Vis. Image Signal Process.