Estimation of Gaussian Processes in Markov-Middleton Impulsive Noise

Mirbadin, Anoush; Kiani, Ehsan; Vannucci, Armando; Colavolpe, Giulio

doi:10.1109/gpecom.2019.8778579

Cited by 6 publications

(9 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although belonging to the broad class of switching linear dynamical systems [16], the system considered here exhibits remarkable symmetry properties that allow an effective estimation of the signal samples through approximate variational inference. A simple parallel iterative schedule (PIS) of messages, including dynamically updated hard decisions on the channel states [13], was shown to provide a satisfactory, although suboptimal, performance, for many different channel conditions [14]. The more computationally costly expectation propagation (EP) [18] is also applicable to this problem albeit affected by its usual instability problems during the iterations, that can however be solved by known methods in the literature [24].…”

Section: Discussionmentioning

confidence: 99%

“…To compute the forward and backward messages, we assume that η f and η b are respectively the means of the Gaussian messages p f (s k ) and p b (s k ), and σ 2 f and σ 2 b are their variances. Equations (14), (17), and (27) yield…”

Section: Upper Fg Half: Kalman Smoothermentioning

confidence: 99%

“…The presence of memory in both signal and noise significantly complicates the detection/estimation problem and novel receivers, designed based on a factor graph (FG) approach, are an efficient solution to jointly estimate the correlated Gaussian samples and detect the correlated states of channel impulsive noise, as done for the first time in [13], in the case of Markov-Gaussian impulsive noise, later extended to Markov-Middleton impulsive noise [14]. Receivers based on message-passing algorithms [15] work iteratively, to guarantee convergence on a loopy FG.…”

Section: Introductionmentioning

confidence: 99%

“…Moreover, the message passing between discrete channel states and continuous (Gaussian) observations produces (Gaussian) mixture messages with exponentially increases complexity [16]. In [13,14], hard decisions are taken on the states of impulsive noise (i.e., the number of interfering devices); as a consequence, the mixture messages are approximated as one of their terms (the one with the largest likelihood). This is a suboptimal approach that neglects part of the information carried by messages [10].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Iterative Receiver Design for the Estimation of Gaussian Samples in Impulsive Noise

Mirbadin¹,

Vannucci²,

Colavolpe³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Impulsive noise is the main limiting factor for transmission over channels affected by electromagnetic interference. We study the estimation of (correlated) Gaussian signals in an impulsive noise scenarios. In this work, we analyze some of the existing as well as some novel estimation algorithms. Their performance is compared, for the first time, for different channel conditions, including the Markov-Middleton scenario, where the impulsive noise switches between different noise states. Following a modern approach in digital communications, the receiver design is based on a factor graph model and implements a message passing algorithm. The correlation among signal samples as well as among noise states brings about a loopy factor graph, where an iterative message passing scheme should be employed. As it is well known, approximate variational inference techniques are necessary in these cases. We propose and analyze different algorithms and provide a complete performance comparison among them, showing that both Expectation Propagation, Transparent Propagation, and the Parallel Iterative Schedule approaches reach a performance close to the optimal, at different channel conditions.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Upper Fg Half: Kalman Smoothermentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Iterative Receiver Design for the Estimation of Gaussian Samples in Impulsive Noise

Mirbadin¹,

Vannucci²,

Colavolpe³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…This is a typical situation where, as commonly done in recent years, approximate inference techniques and graphical model-based algorithms are effectively borrowed or adapted from the machine learning literature (see, e.g., [15]) to solve complicated estimation problems with many random variables. In particular, novel receivers, designed based on a factor graph (FG) approach, are an efficient solution to jointly estimate the correlated Gaussian samples and detect the correlated states of channel impulsive noise, as done for the first time in [16], in the case of Markov-Gaussian impulsive noise, later extended to Markov-Middleton impulsive noise [17]. Receivers based on message passing algorithms [18] work iteratively, to guarantee convergence on a loopy FG.…”

Section: Introductionmentioning

confidence: 99%

Iterative Receiver Design for the Estimation of Gaussian Samples in Impulsive Noise

et al. 2021

Self Cite

View full text Add to dashboard Cite

Impulsive noise is the main limiting factor for transmission over channels affected by electromagnetic interference. We study the estimation of (correlated) Gaussian signals in an impulsive noise scenario. In this work, we analyze some of the existing, as well as some novel estimation algorithms. Their performance is compared, for the first time, for different channel conditions, including the Markov–Middleton scenario, where the impulsive noise switches between different noise states. Following a modern approach in digital communications, the receiver design is based on a factor graph model and implements a message passing algorithm. The correlation among signal samples, as well as among noise states brings about a loopy factor graph, where an iterative message passing scheme should be employed. As is well known, approximate variational inference techniques are necessary in these cases. We propose and analyze different algorithms and provide a complete performance comparison among them, showing that the expectation propagation, transparent propagation, and parallel iterative schedule approaches reach a performance close to optimal, at different channel conditions.

show abstract

Frequency diversity of the power line time service system

Zou,

Ma,

Hua

et al. 2023

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

A frequency diversity technique is proposed for OFDM-modulated power line time service systems, and a variety of frequency diversity reception processing schemes are investigated to address the problem of interference caused by power line channel noise. Simulation results show that selecting the appropriate frequency diversity order can effectively reduce the system received signal bit error rate, while using the maximum ratio combining diversity reception scheme has the best effect on improving the system bit error rate performance.

show abstract

Estimation of Gaussian Processes in Markov-Middleton Impulsive Noise

Cited by 6 publications

References 12 publications

Iterative Receiver Design for the Estimation of Gaussian Samples in Impulsive Noise

Iterative Receiver Design for the Estimation of Gaussian Samples in Impulsive Noise

Iterative Receiver Design for the Estimation of Gaussian Samples in Impulsive Noise

Frequency diversity of the power line time service system

Contact Info

Product

Resources

About