Correntropy-Based Adaptive Filtering of Noncircular Complex Data

Dees, Bruno Scalzo; Xia, Yili; Douglas, S.C.; Mandic, Danilo P.

doi:10.1109/icassp.2018.8461450

Cited by 9 publications

(6 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…CC represents the kernel function. Here, the improper Gaussian kernel is used for the complex correntropy, which is defined by [38]:…”

Section: System Modelmentioning

confidence: 99%

“…Table II compares the numerical complexity of the proposed WL-MTICC algorithm with ACLMS [32], MICCC [38], WL-MCCC-APA [39], and WLC-EIMCCC [40]. It can be seen from this table that ACLMS is the most computational efficient, and WL-MTICC has higher computationally complexity than ACLMS and MICCC, but has less computational complexity than WLC-EIMCC and WL-MCCC-APA.…”

Section: Numerical Complexitymentioning

confidence: 99%

“…ACLMS and WL-RLS are the extensions of LMS and RLS in the widely linear model, respectively, which can be implemented simply, but cannot stay robust in a non-Gaussian noise environment. Xia et al further proposed the widely linear maximum improper complex correntropy algorithm [38], which can be used to combat non-Gaussian noises. To improve the performance of the complex correntropy based algorithms in the case of colored inputs, Qiu et al proposed a widely linear maximum complex correntropy criterion affine projection algorithm (WL-MCCC-APA), recently [39].…”

mentioning

confidence: 99%

See 2 more Smart Citations

Maximum Total Improper Complex Correntropy Algorithm for Widely Linear Adaptive Filtering

Fu¹,

Li²

2022

IEEE Access

View full text Add to dashboard Cite

The maximum total complex correntropy (MTCC) algorithm improves the performance of adaptive filtering under the error in variable (EIV) model by integrating both input and output noise information into the total complex correntropy. However, the MTCC algorithm cannot be applied to the widely linear model, directly. Compared with a strictly linear model, the widely linear model provides the complete statistical information of signals for adaptive filtering. This paper first constructs a novel cost function for the widely linear model by incorporating the input and output noise information into the improper complex correntropy. Then, a novel widely linear adaptive filter algorithm named widely linear maximum total improper complex correntropy (WL-MTICC) is proposed using the gradient descent method under the maximum total improper correntropy criterion. Finally, the analysis of local stability and convergence in the mean sense regarding the proposed WL-MTICC algorithm is provided. Simulations are used to show the performance advantage of the proposed WL-MTICC algorithm in the presence of both input and output noises.INDEX TERMS adaptive filter, convergence, stability, total complex correntropy, widely linear model. I. INTRODUCTIONSince adaptive filtering adjusts the filter parameters flexibly by combining the input and expected signals, it has been developed well in signal processing, control, communication, and other scenarios [1-2]. The original adaptive filtering algorithm aimed at the real-valued field, and its classical representative is the least-mean-square (LMS) [3][4][5] algorithm. LMS has the good properties of fast convergence and simple structure. Researchers have made certain improvements in developing a series of LMS algorithm variations to further improve the convergence performance and steady-state performance of LMS in a Gaussian environment [6][7][8][9]. In addition, to improve the performance of LMS type algorithms for colored inputs, affine projection algorithm (APA) and recursive least-squares (RLS) were also developed in [10][11]. However, these algorithms are not robust to non-Gaussian noises. By utilizing the kernel function, researchers have developed a series of adaptive filtering algorithms based on correntropy in [12][13][14][15][16][17][18][19][20][21] to make adaptive filtering algorithms robust in a non-Gaussian noise environment. In addition, some correntropy based spare adaptive filtering algorithms have also been proposed in [22][23][24][25], such as general zero attraction proportionate normalized maximum correntropy criterion (GZA-PNMCC) [22], correntropy induced metric maximum correntropy criterion (CIMMCC) [23], and group-constrained maximum correntropy criterion (GC-MCC) [24].Since signals are represented in the complex-valued form in many scenarios, adaptive filtering in the complex-valued domain attracts considerable critical attention of researchers, then a series of adaptive filtering algorithms are followed, including complex LMS (CLMS) algorithm [26] and complex correntr...

show abstract

“…CC represents the kernel function. Here, the improper Gaussian kernel is used for the complex correntropy, which is defined by [38]:…”

Section: System Modelmentioning

confidence: 99%

Section: Numerical Complexitymentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

Maximum Total Improper Complex Correntropy Algorithm for Widely Linear Adaptive Filtering

Fu¹,

Li²

2022

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Correntropy can be used as a cost function to develop novel robust adaptive filtering algorithms [ 23 , 24 , 25 ]. In practice, only finite samples of the variables

and

are given, and the joint probability density function is unknown in general.…”

Section: Preliminariesmentioning

confidence: 99%

Adaptive Extended Kalman Filter with Correntropy Loss for Robust Power System State Estimation

Zhang

Qiu

2019

Entropy

View full text Add to dashboard Cite

Monitoring the current operation status of the power system plays an essential role in the enhancement of the power grid for future requirements. Therefore, the real-time state estimation (SE) of the power system has been of widely-held concern. The Kalman filter is an outstanding method for the SE, and the noise in the system is generally assumed to be Gaussian noise. In the actual power system however, these measurements are usually disturbed by non-Gaussian noises in practice. Furthermore, it is hard to get the statistics of the state noise and measurement noise. As a result, a novel adaptive extended Kalman filter with correntropy loss is proposed and applied for power system SE in this paper. Firstly, correntropy is used to improve the robustness of the EKF algorithm in the presence of non-Gaussian noises and outliers. In addition, an adaptive update mechanism of the covariance matrixes of the measurement and process noises is introduced into the EKF with correntropy loss to enhance the accuracy of the algorithm. Extensive simulations are carried out on IEEE 14-bus and IEEE 30-bus test systems to verify the feasibility and robustness of the proposed algorithm.

show abstract

“…However, from channel measurement results, we found that the non-Gaussian model is more suitable than the Gaussian model to describe the real communication environment since the existing impulse noises and manual noises in the systems [30]. Furthermore, the impulsive noise is common in the real world, and then, the estimation performance might degrade when the signal is transmitted from the transmitter to receiver because of the noise contamination [29]- [31].…”

Section: Introductionmentioning

confidence: 99%

Active Coefficient Detection Maximum Correntropy Criterion Algorithm for Sparse Channel Estimation Under Non-Gaussian Environments

Sun

Jiang

et al. 2019

IEEE Access

View full text Add to dashboard Cite

In this paper, a kind of active coefficient detection (ACD)-based maximum correntropy criterion (MCC) algorithm is proposed to estimate a sparse multi-path channel under the non-Gaussian environments. The proposed ACD-based MCC algorithms are realized by developing an active coefficient detection mechanism, which can distinguish the active taps within the sparse channels and find out the position and the number of active taps. Therefore, only the active taps coefficient is updated while the trivial channel coefficients are set to be zeros. Various computer simulation experiments are carried out to investigate the performance of the proposed ACD-based MCC algorithms under different impulsive noises. The achieved simulation results prove that the proposed ACD-based MCC algorithms are effective and outperform the previous adaptive filtering algorithms for the sparse channel estimation with regard to both the convergence and the estimation error.INDEX TERMS Sparse channel estimation, maximum correntropy criterion, active coefficient detection, tap selection, impulsive noise environments.

show abstract

Correntropy-Based Adaptive Filtering of Noncircular Complex Data

Cited by 9 publications

References 21 publications

Maximum Total Improper Complex Correntropy Algorithm for Widely Linear Adaptive Filtering

Maximum Total Improper Complex Correntropy Algorithm for Widely Linear Adaptive Filtering

Adaptive Extended Kalman Filter with Correntropy Loss for Robust Power System State Estimation

Active Coefficient Detection Maximum Correntropy Criterion Algorithm for Sparse Channel Estimation Under Non-Gaussian Environments

Contact Info

Product

Resources

About