Robust adaptive filtering algorithms for α-stable random processes

Aydin, G.; Arıkan, Orhan; Çetin, A. Enis

doi:10.1109/82.752953

Cited by 44 publications

(15 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the basis of the GNLMP algorithm 10 and our previous work (the FxMNLMP algorithm 9 ), we have proposed a FxMGNLMP algorithm for impulsive ANC. The simulation results (presented in Sec.…”

Section: Discussionmentioning

confidence: 99%

“…Hereafter, the resulting algorithm is referred to as the filtered-x modified normalized least mean p-power (FxMNLMP) algorithm. 9 As a generalization to the NLMP update equation, the following update equation for the generalized normalized least mean p-power (GNLMP) is proposed: 10 wðn þ 1Þ ¼ wðnÞ þ lðnÞpðeðnÞÞ hai ðxðnÞÞ hðqÀ1Þai ;…”

Section: Flom-based Algorithms For Anc Of Impulsive Noisementioning

confidence: 99%

See 1 more Smart Citation

Fractional lower order moment based adaptive algorithms for active noise control of impulsive noise sources

Akhtar

2012

The Journal of the Acoustical Society of America

View full text Add to dashboard Cite

This letter deals with active noise control (ANC) for impulsive noise sources being modeled using non-Gaussian stable process. The filtered-x least mean square algorithm is based on minimization of the variance of the error signal and becomes unstable for impulsive noise. The filtered-x least mean p-power algorithm—based on minimizing the fractional lower order moment—gives a robust performance for impulsive ANC; however, its convergence speed is very slow. This letter proposes modifying and employing a generalized normalized LMP algorithm for impulsive ANC. Extensive simulations are carried out which demonstrate the effectiveness of the proposed algorithm.

show abstract

“…On the basis of the GNLMP algorithm 10 and our previous work (the FxMNLMP algorithm 9 ), we have proposed a FxMGNLMP algorithm for impulsive ANC. The simulation results (presented in Sec.…”

Section: Discussionmentioning

confidence: 99%

Section: Flom-based Algorithms For Anc Of Impulsive Noisementioning

confidence: 99%

Fractional lower order moment based adaptive algorithms for active noise control of impulsive noise sources

Akhtar

2012

The Journal of the Acoustical Society of America

View full text Add to dashboard Cite

show abstract

“…Furthermore, the normalized LMP (NLMP) and generalization of the NLMP algorithms based on the fractional lower-order statistics (FLOS) are proposed in [21][22][23]. The LMP family algorithms have been successfully employed for system identification under impulsive noise disturbances [14].…”

Section: Introductionmentioning

confidence: 99%

Sparse least mean p-power algorithms for channel estimation in the presence of impulsive noise

Chen

et al. 2015

SIViP

View full text Add to dashboard Cite

The least mean p-power (LMP) is one of the most popular adaptive filtering algorithms. With a proper p value, the LMP can outperform the traditional least mean square ( p = 2), especially under the impulsive noise environments. In sparse channel estimation, the unknown channel may have a sparse impulsive (or frequency) response. In this paper, our goal is to develop new LMP algorithms that can adapt to the underlying sparsity and achieve better performance in impulsive noise environments. Particularly, the correntropy induced metric (CIM) as an excellent approximator of the l 0 -norm can be used as a sparsity penalty term. The proposed sparsity-aware LMP algorithms include the l 1 -norm, reweighted l 1 -norm and CIM penalized LMP algorithms, which are denoted as ZALMP, RZALMP and CIMLMP respectively. The mean and mean square convergence of these algorithms are analysed. Simulation results show that the proposed new algorithms perform well in sparse channel estimation under impulsive noise environments. In particular, the CIMLMP with suitable kernel width will outperform other algorithms significantly due to the superiority of the CIM approximator for the l 0 -norm. B Wentao Ma

show abstract

“…Hence impulsive noise produces more outliers than expected under the Gaussian assumption, degrading the performance of linear filtering. Several studies [1][2][3][4][5] showed that α-stable distribution is better for modeling impulsive noise than Gaussian distribution in signal processing for it has some important characteristics. Many types of noises are well modeled as α-stable distributed processes, including underwater acoustic, low-frequency atmospheric, and many man-made noises.…”

Section: Introductionmentioning

confidence: 99%