A Smoothed Algorithm with Convergence Analysis under Generalized Maximum Correntropy Criteria in Impulsive Interference

The generalized maximum correntropy criterion (GMCC) algorithm is computationally simple and robust against impulsive noise but it suffers from slow convergence speed as it is derived and based on stochastic gradient, which only use the current data sample. In order to deal with this issue, a smoothed GMCC algorithm (SGMCC) is proposed. In the SGMCC algorithm, instead of taking the exponential weighted average of gradient vector to approximate the expectation of the gradient vector, we take the exponential weighted average of the variable step-size so that the SGMCC algorithm can be viewed as a sign GMCC algorithm with smoothed variable step-size. Moreover, convergence performance analyses are derived in terms of variable step-size, mean-square stability and steady-state behavior to demonstrate the robustness of the proposed algorithm. At last, simulation comparisons show that the proposed algorithm is robust against impulsive noise and converges fast with lower computational complexity. Also, for the steady-state behavior, simulation results verify that the simulated value matches well with the theoretical one.

[1]  Mohamed-Slim Alouini,et al.  Ultrawide Bandwidth Receiver Based on a Multivariate Generalized Gaussian Distribution , 2015, IEEE Transactions on Wireless Communications.

[2]  Zongze Wu,et al.  Robust Hammerstein Adaptive Filtering under Maximum Correntropy Criterion , 2015, Entropy.

[3]  Behrouz Farhang-Boroujeny,et al.  A new class of gradient adaptive step-size LMS algorithms , 2001, IEEE Trans. Signal Process..

[4]  Farhan Khan,et al.  Robust adaptive algorithms for underwater acoustic channel estimation and their performance analysis , 2017, Digit. Signal Process..

[5]  Ali H. Sayed,et al.  Variable step-size NLMS and affine projection algorithms , 2004, IEEE Signal Processing Letters.

[6]  José Carlos Príncipe,et al.  Using Correntropy as a cost function in linear adaptive filters , 2009, 2009 International Joint Conference on Neural Networks.

[7]  Nanning Zheng,et al.  A variable step-size adaptive algorithm under maximum correntropy criterion , 2015, 2015 International Joint Conference on Neural Networks (IJCNN).

[8]  Konstantinos Pelekanakis,et al.  Adaptive Sparse Channel Estimation under Symmetric alpha-Stable Noise , 2014, IEEE Transactions on Wireless Communications.

[9]  Robert Price,et al.  A useful theorem for nonlinear devices having Gaussian inputs , 1958, IRE Trans. Inf. Theory.

[10]  Xiaotong Zhang,et al.  Robust Kalman Filter Algorithm Based on Generalized Correntropy for Ultra-Wideband Ranging in Industrial Environment , 2019, IEEE Access.

[11]  Anke Schmeink,et al.  A Fast Converging Channel Estimation Algorithm for Wireless Sensor Networks , 2018, IEEE Transactions on Signal Processing.

[12]  Liming Shi,et al.  Convex Combination of Adaptive Filters under the Maximum Correntropy Criterion in Impulsive Interference , 2014, IEEE Signal Processing Letters.

[13]  Badong Chen,et al.  Steady-state mean-square-deviation analysis of the sign subband adaptive filter algorithm , 2016, Signal Process..

[14]  Ta-Sung Lee,et al.  A variable step-size sign algorithm for channel estimation , 2014, Signal Process..

[15]  Nanning Zheng,et al.  Steady-State Mean-Square Error Analysis for Adaptive Filtering under the Maximum Correntropy Criterion , 2014, IEEE Signal Processing Letters.

[16]  Umberto Mengali,et al.  The modified Cramer-Rao bound in vector parameter estimation , 1998, IEEE Trans. Commun..

[17]  Vladimir V. Lukin,et al.  Estimation of parameters for generalized Gaussian distribution , 2014, 2014 6th International Symposium on Communications, Control and Signal Processing (ISCCSP).

[18]  Zhang Jingjing,et al.  Variable Step Size LMS Algorithm , 2012 .

[19]  Tareq Y. Al-Naffouri,et al.  Adaptive Filters with Error Nonlinearities: Mean-Square Analysis and Optimum Design , 2001, EURASIP J. Adv. Signal Process..

[20]  José Carlos Príncipe,et al.  Generalized correlation function: definition, properties, and application to blind equalization , 2006, IEEE Transactions on Signal Processing.

[21]  Tokunbo Ogunfunmi,et al.  The Quarternion Maximum Correntropy Algorithm , 2015, IEEE Transactions on Circuits and Systems II: Express Briefs.

[22]  Weifeng Liu,et al.  Correntropy: Properties and Applications in Non-Gaussian Signal Processing , 2007, IEEE Transactions on Signal Processing.

[23]  Kan Li,et al.  Transfer Learning in Adaptive Filters: The Nearest Instance Centroid-Estimation Kernel Least-Mean-Square Algorithm , 2017, IEEE Transactions on Signal Processing.

[24]  Wentao Ma,et al.  Maximum correntropy criterion based sparse adaptive filtering algorithms for robust channel estimation under non-Gaussian environments , 2015, J. Frankl. Inst..

[25]  Nanning Zheng,et al.  Generalized Correntropy for Robust Adaptive Filtering , 2015, IEEE Transactions on Signal Processing.

[26]  M. V. Kulikova,et al.  Square-root algorithms for maximum correntropy estimation of linear discrete-time systems in presence of non-Gaussian noise , 2016, Syst. Control. Lett..

[27]  Deniz Erdogmus,et al.  Information Theoretic Learning , 2005, Encyclopedia of Artificial Intelligence.

[28]  Zakia Jellali,et al.  Fast Fading Channel Estimation by Kalman Filtering and CIR Support Tracking , 2017, IEEE Transactions on Broadcasting.

[29]  Badong Chen,et al.  A switch kernel width method of correntropy for channel estimation , 2015, 2015 International Joint Conference on Neural Networks (IJCNN).

[30]  Badong Chen,et al.  An adaptive kernel width update method of correntropy for channel estimation , 2015, 2015 IEEE International Conference on Digital Signal Processing (DSP).

[31]  I. Song,et al.  Performance analysis of the dual sign algorithm for additive contaminated-Gaussian noise , 1994, IEEE Signal Processing Letters.

[32]  Constantine Kotropoulos,et al.  Robust Multidimensional Scaling Using a Maximum Correntropy Criterion , 2017, IEEE Transactions on Signal Processing.