On order statistic least mean square algorithms

Bilcu,; Kuosmanen,; Egiazarian,

doi:10.1109/icassp.2002.1006013

Cited by 1 publication

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Here, we propose to utilise the estimated parameters of impulsive noise as stated in Section 3. A new and efficient strategy to determine the weighting coefficients can be established as

\begin{matrix} right left right left right left right left right left right left0.278em 2em 0.278em 2em 0.278em 2em 0.278em 2em 0.278em 2em 0.278em3pt \\ ϖ_{i} \overset{def}{=} \{\begin{matrix} left left1em4pt \\ 1 + ϵ (\hat{η}) & if i < K - H - L \\ ζ (i) & if K - H - L \leq i \leq K - H + L \\ ϵ (\hat{η}) & if i \geq K - H + L \end{matrix} \end{matrix}

where L , which is similar to

ξ

in (32), is the excessive‐contamination‐elimination index for the LWS algorithm;

ζ false(i false)

and

ϵ false(\overset{false^}{η} false)

can be manipulated to achieve the optimal estimation for different situations (refer to [15, 23] for how to choose the appropriate values for these parameters). Two typical choices of

ζ false(i false)

can be found as follows:

\begin{matrix} right left right left right left right left right left right left0.278em 2em 0.278em 2em 0.278em 2em 0.278em 2em 0.278em 2em 0.278em3pt \\ ζ (i) \overset{def}{=} 1 + ϵ (\hat{η}) - \frac{i - (K - H - L)}{2 L}, \end{matrix}

\begin{matrix} right left right left right left right left right left right left0.278em 2em 0.278em 2em 0.278em 2em 0.278em 2em 0.278em 2em 0.278em3pt \\ ζ (i) \overset{}{=} \end{matrix}

…”

Section: Robust Channel Estimation For Plcmentioning

confidence: 99%

“…In this paper, we propose two novel channel estimation algorithms incorporating robust‐least‐square estimation with impulsive noise estimation to address the aforementioned challenges posed by impulsive noise and multipath distortion to the PLC systems. The robust‐least‐square estimation, which was originally developed for dealing with the outliers in any regression problem, has been employed to combat the impulsive noise in the fading environments [15–17]. Deemed as a promising solution with high breakdown point, the robust‐least‐square estimator trades computational complexity for reliability.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Robust multipath channel estimation in the presence of impulsive noise

Yan

Zhang

Wu³

2018

IET Communications

View full text Add to dashboard Cite

“…Here, we propose to utilise the estimated parameters of impulsive noise as stated in Section 3. A new and efficient strategy to determine the weighting coefficients can be established as

\begin{matrix} right left right left right left right left right left right left0.278em 2em 0.278em 2em 0.278em 2em 0.278em 2em 0.278em 2em 0.278em3pt \\ ϖ_{i} \overset{def}{=} \{\begin{matrix} left left1em4pt \\ 1 + ϵ (\hat{η}) & if i < K - H - L \\ ζ (i) & if K - H - L \leq i \leq K - H + L \\ ϵ (\hat{η}) & if i \geq K - H + L \end{matrix} \end{matrix}

where L , which is similar to

ξ

in (32), is the excessive‐contamination‐elimination index for the LWS algorithm;

ζ false(i false)

and

ϵ false(\overset{false^}{η} false)

can be manipulated to achieve the optimal estimation for different situations (refer to [15, 23] for how to choose the appropriate values for these parameters). Two typical choices of