Design of momentum LMS adaptive strategy for parameter estimation of Hammerstein controlled autoregressive systems

Chaudhary, Naveed Ishtiaq; Zubair, Syed; Raja, Muhammad Asif Zahoor

doi:10.1007/s00521-016-2762-1

Cited by 19 publications

(7 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…FC relies on new feature space in comparison with the traditional integer order derivatives such as treatment of FO chaotic systems [19,20] and exploited for the solution of different problems arising in applied physics and engineering such as modified least mean square [21], complex domain LMS and NLMS algorithms for channel equalization [22], active noise control systems [23], Improved design of digital fractional-order differentiator [24], and chemotaxis model involving fractional operators [25]. The FC adaptive strategies have seen its importance in system identification of Hammerstein type and outperform the standard counterparts such as vibration control [26], uncertain chaotic systems [27], FO constant modulus blind algorithms [8], tracking of Rayleigh fading sequences [10], momentum LMS for parameter estimation of Hammerstein systems [28]. We have observed that different variants of the diffusion LMS have been proposed [12,13,29] and applied to the problems of distributed sensing and estimation [30][31][32][33], machine learning [34][35][36][37], intrusion detection [38][39][40] and target localization [41], and channel gains estimation [8,[42][43][44].…”

Section: Introductionmentioning

confidence: 99%

Diffusion Based Channel Gains Estimation in WSN Using Fractional Order Strategies

Khokhar¹,

Majeed²,

Shah³

2022

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

In this study, it is proposed that the diffusion least mean square (LMS) algorithm can be improved by applying the fractional order signal processing methodologies. Application of Caputo's fractional derivatives are considered in the optimization of cost function. It is suggested to derive a fractional order variant of the diffusion LMS algorithm. The applicability is tested for the estimation of channel parameters in a distributed environment consisting of randomly distributed sensors communicating through wireless medium. The topology of the network is selected such that a smaller number of nodes are informed. In the network, a random sleep strategy is followed to conserve the transmission power at the nodes. The proposed fractional order modified diffusion LMS algorithms are applied in the two configurations of combine-then-adapt and adapt-then-combine. The average squared error performance of the proposed algorithms along with its traditional counterparts are evaluated for the estimation of the Rayleigh channel parameters. A mathematical proof of convergence is provided showing that the addition of the nonlinear term resulting from fractional derivatives helps adjusts the autocorrelation matrix in such a way that the spread of its eigenvalues decreases. This increases the convergence as well as the steady state response even for the larger step sizes. Experimental results are shown for different number of nodes and fractional orders. The simulation results establish that the accuracy of the proposed scheme is far better than its classical counterparts, therefore, helps better solves the channel gains estimation problem in a distributed wireless environment. The algorithm has the potential to be applied in other applications related to learning and adaptation.

show abstract

Section: Introductionmentioning

confidence: 99%

Diffusion Based Channel Gains Estimation in WSN Using Fractional Order Strategies

Khokhar¹,

Majeed²,

Shah³

2022

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

show abstract

“…Numerical experiments shown that the modified FLMS algorithm outperforms the conventional LMS approaches in terms of convergence speed and estimation error. Therefore, the FLMS algorithms have recently gained much research attention and several novel algorithms have been presented by using the theories of the fractional calculus in recent years 24,25 . Zhang et al 26 proposed an optimal adaptive filtering algorithm for the FIR filter design with colored noise based on the fractional‐order derivative.…”

Section: Introductionmentioning

confidence: 99%

Design of auxiliary model and hierarchical normalized fractional adaptive algorithms for parameter estimation of bilinear‐in‐parameter systems

Yan-cheng

Chen

et al. 2022

Adaptive Control & Signal

View full text Add to dashboard Cite

This study investigates the parameter identification issues of bilinear-in-parameter systems through fractional adaptive algorithms. An auxiliary model based 𝜀-normalized modified fractional least mean square algorithm is proposed for accelerating the parameter estimation accuracy based on the auxiliary model identification idea and the introduced convergence index, a normalized modified hierarchical fractional least mean square algorithm is presented for improving the computational efficiency based on the hierarchical identification principle. The proposed normalized fractional adaptive strategies are effective and could provide more accurate parameter estimates comparing with conventional counterparts for bilinear-in-parameter identification model based on the mean square error metrics and the average predicted output error.The effectiveness and accuracy of the proposed algorithms are further verified and validated through numerical simulations for different noise variances, fractional orders and gain parameters.

show abstract

“…In Kohli and Kapoor, 15 authors conclude that LMS estimator has lower CC over RLS and Kalman filters. In addition, there are different variants of LMS algorithm such as momentum LMS, 16 fractional LMS, 17 momentum fractional LMS, 18 and Volterra LMS 19 algorithms for parameter estimation, optimization of parameters in adaptive beamforming, Hammerstein nonlinear system identification, and fractional order for system identification, respectively. Moreover, these algorithms are improved versions in terms of accuracy, convergence, robustness, and stability.…”

Section: Introductionmentioning

confidence: 99%

Capacity and BER performance improvement in integrated MIMO‐OFDM system using optimal power allocation, channel estimation, and turbo coding

Pyla

K²,

2021

Int J Communication

View full text Add to dashboard Cite

Summary Among communication systems, multiple input multiple output (MIMO) system has the capability of providing spectral efficiency, high data rates, diversity gain, and improved reliability. Suitably designed orthogonal frequency division multiplexing (OFDM) transmits the signal without inter symbol interference and multipath fading. Hence, MIMO‐OFDM is a strong candidate for 4G and 5G wireless systems. However, variations in signal‐to‐noise ratio (SNR) due to the random nature of the channel and poor capacity at low SNR are critical issues in conventional MIMO‐OFDM system. This paper explains how optimal power allocation (OPA), channel estimation, and coding improve the capacity and bit error rate (BER) performance of MIMO‐OFDM system. In OPA, the transmitter power is distributed adaptively to the channels based on the SNR statistics using singular value decomposition and water filling algorithm. In case of low SNR, less number of channels are selected for power allocation. Least squares (LS), minimum mean square error (MMSE), and least mean square (LMS) estimators are considered in comb type pilot channel estimation while turbo code is used with code rates of 1/2 and 1/3. From the simulation results, capacity improvement of 5 b/s/Hz and 11 b/s/Hz is observed for MIMO‐OFDM systems with four antennas and eight antennas, respectively. It is also found that performance of LMS estimator improved by 3.5‐dB SNR over LS and 1 dB SNR over MMSE. In this paper is shown how LMS estimator and 1/3 turbo code have been integrated with MIMO‐OFDM, and this has resulted in around 4‐dB SNR improvement over conventional MIMO‐OFDM.

show abstract

Design of momentum LMS adaptive strategy for parameter estimation of Hammerstein controlled autoregressive systems

Cited by 19 publications

References 57 publications

Diffusion Based Channel Gains Estimation in WSN Using Fractional Order Strategies

Diffusion Based Channel Gains Estimation in WSN Using Fractional Order Strategies

Design of auxiliary model and hierarchical normalized fractional adaptive algorithms for parameter estimation of bilinear‐in‐parameter systems

Capacity and BER performance improvement in integrated MIMO‐OFDM system using optimal power allocation, channel estimation, and turbo coding

Contact Info

Product

Resources

About