Two Diffusion Proportionate Sign Subband Adaptive Filtering Algorithms

Shi, Long; Zhao, Haiquan

doi:10.1007/s00034-017-0494-9

Cited by 5 publications

(4 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Approximation 3: For the iteration i → ∞, the Taylor series expansion of exponential error exp[e 2 i ] can be approximated [25], [26] exp[e 2 i ] = I + 1 1! e 2 i + 1 2!…”

Section: Performance Analysismentioning

confidence: 99%

A Class of Diffusion Zero Attracting Stochastic Gradient Algorithms With Exponentiated Error Cost Functions

2020

Self Cite

View full text Add to dashboard Cite

In this paper, a class of diffusion zero-attracting stochastic gradient algorithms with exponentiated error cost functions is put forward due to its good performance for sparse system identification. Distributed estimation algorithms based on the popular mean-square error criterion have poor behavior for sparse system identification with color noise. To overcome this drawback, a class of stochastic gradient least exponentiated (LE) algorithms with exponentiated error cost functions were proposed, which achieved a low steady-state compared with the least mean square (LMS) algorithm. However, those LE algorithms may suffer from performance deterioration in the spare system. For sparse system identification in the adaptive network, a polynomial variable scaling factor improved diffusion least sum of exponentials (PZA-VSIDLSE) algorithm and an l p-norm constraint diffusion least exponentiated square (LP-DLE2) algorithm are proposed in this work. Instead of using the l 1-norm penalty, an l p-norm penalty and a polynomial zero-attractor are employed as a substitution in the cost functions of the LE algorithms. Then, we perform mean behavior model and mean square behavior modal of the LP-DLE2 algorithm with several common assumptions. Moreover, simulations in the context of distributed network sparse system identification show that the proposed algorithms have a low steady-state compared with the existing algorithms. INDEX TERMS Diffusion adaptive algorithms, exponentiated error, zero attracting, sparse system, variable scaling factor.

show abstract

“…Approximation 3: For the iteration i → ∞, the Taylor series expansion of exponential error exp[e 2 i ] can be approximated [25], [26] exp[e 2 i ] = I + 1 1! e 2 i + 1 2!…”

Section: Performance Analysismentioning

confidence: 99%

A Class of Diffusion Zero Attracting Stochastic Gradient Algorithms With Exponentiated Error Cost Functions

2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…In such cases, other power of error are used in some researches like [19,20]. In [21][22][23][24] sign operator has been used to make DLMS robust against non-Gaussian noise. In [25] the diffusion least logarithmic absolute difference (DLLAD) algorithm has been proposed which adopts both the logarithm operation and sign operation to the error.…”

Section: Introductionmentioning

confidence: 99%

Robust diffusion LMS over adaptive networks

Ashkezari-Toussi

Sadoghi-Yazdi

2019

Signal Processing

View full text Add to dashboard Cite

“…As is done in [16], if we introduce the following coefficients , , (12) we obtain the update equation for the proposed ATC-LZA-DLMS algorithm , , 1 , , ,…”

Section: Atc-lza-dlms Algorithm: By Introducing An Intermediatementioning

confidence: 99%

“…PARAMETER estimation acts as an important role in the adaptive signal processing, which has obtained much attention over the past decades [1]- [8]. Recently, distributed estimation has increased popularity since it can deal with the information extraction from the data collected at nodes over the network, and also been applied in various fields, such as environment monitoring, disaster relief management and source localization [9]- [12]. In the previous work, two strategies have been extensively studied, namely the incremental strategy [13], [14] and the diffusion strategy [15], [16], respectively.…”

Section: Introductionmentioning

confidence: 99%

Diffusion Leaky Zero Attracting Least Mean Square Algorithm and Its Performance Analysis

Shi

Zhao

2018

IEEE Access

Self Cite

View full text Add to dashboard Cite

Recently, the leaky diffusion least-mean-square (DLMS) algorithm has obtained much attention because of its good performance for high input eigenvalue spread and low signal-to-noise ratio (SNR). However, the leaky DLMS algorithm may suffer from performance deterioration in the sparse system. To overcome this drawback, the leaky zero attracting DLMS (LZA-DLMS) algorithm is developed in this paper, which adds an 1 -norm l penalty to the cost function to exploit the property of sparse system. The leaky reweighted zero attracting DLMS (LRZA-DLMS) algorithm is also put forward, which can improve the estimation performance in the presence of time-varying sparsity. Instead of using the 1 -norm l penalty, in the reweighted version, a log-sum function is employed as the substitution. Based on the weight error variance relation and several common assumptions, we analyze the transient behavior of our findings and determine the stability bound of the step-size. Moreover, we implement the steady state theoretical analysis for the proposed algorithms. Simulations in the context of distributed network system identification illustrate that the proposed schemes outperform various existing algorithms and validate the accuracy of the theoretical results.INDEX TERMS leaky, low SNR, zero attracting, sparse system, weight error variance VOLUME XX, 2017

show abstract

Two Diffusion Proportionate Sign Subband Adaptive Filtering Algorithms

Cited by 5 publications

References 29 publications

A Class of Diffusion Zero Attracting Stochastic Gradient Algorithms With Exponentiated Error Cost Functions

A Class of Diffusion Zero Attracting Stochastic Gradient Algorithms With Exponentiated Error Cost Functions

Robust diffusion LMS over adaptive networks

Diffusion Leaky Zero Attracting Least Mean Square Algorithm and Its Performance Analysis

Contact Info

Product

Resources

About