Adaptive estimation and sparse sampling for graph signals in alpha-stable noise

Nguyen, Ngoc Hung; Doğançay, Kutluyıl; Wang, Wenyuan

doi:10.1016/j.dsp.2020.102782

Cited by 20 publications

(26 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Even though the GLMS algorithm is simple, it is not optimal in time efficiency and estimation stability. The GLMP algorithm is an extension of the GLMS algorithm that has stable estimation performance compared to GLMS when estimating a graph signal under SαS noise but with additional complexity [16]. In classical adaptive filtering, the LMS algorithm is used extensively due to its simplicity of implementation, and the Sign-Error algorithm or the LMAD algorithm is an extension of the LMS algorithm to further increase run-speed and to decrease algorithm complexity, with additional robustness gained from the l 1 -norm cost function.…”

Section: Algorithm Derivation and Complexity Analysismentioning

confidence: 99%

“…In classical signal processing, online estimation of time-varying signals is often accomplished using adaptive filters [14]. Adaptive GSP algorithms are inspired by classical adaptive filters to perform online estimation of steady-state and time-varying graph signals through spectral methods [6,7,15,16]. Analogous to the famous adaptive least mean squares (LMS) algorithm in classical adaptive filtering, the GSP least mean squares algorithm (GLMS) is popular due to its simplicity of modeling the noise using Gaussian distribution and using l 2 -norm optimization to estimate the output [6].…”

Section: Introductionmentioning

confidence: 99%

“…In order to avoid the drawbacks caused by l 2 -norm optimization when the noise distribution is impulsive and non-Gaussian, the GSP least mean p th power algorithm (GLMP) further assumes the noise to be symmetric α-stable distribution (SαS). Under the SαS noise assumption, the optimal cost function of GLMP is derived based on the minimum dispersion criterion, leading to l p -norm optimization instead of l 2 -norm optimization [16]. However, there are two drawbacks of the GLMP algorithm: it has additional computations to the already expensive GLMS algorithm, and its parameter selection is still based on the prior knowledge of the noise.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Adaptive Sign Algorithm for Graph Signal Processing

Yao¹,

Kuruoğlu²,

Altınkaya³

2022

Preprint

View full text Add to dashboard Cite

Efficient and robust online processing technique of irregularly structured data is crucial in the current era of data abundance. In this paper, we propose a graph/network version of the classical adaptive Sign algorithm for online graph signal estimation under impulsive noise. Recently introduced graph adaptive least mean squares algorithm is unstable under non-Gaussian impulsive noise and has high computational complexity. The Graph-Sign algorithm proposed in this work is based on the minimum dispersion criterion and therefore impulsive noise does not hinder its estimation quality. Unlike the recently proposed graph adaptive least mean p-th power algorithm, our Graph-Sign algorithm can operate without prior knowledge of the noise distribution. The proposed Graph-Sign algorithm has a faster run time because of its low computational complexity compared to the existing adaptive graph signal processing algorithms. Experimenting on steady-state and time-varying graph signals estimation utilizing spectral properties of bandlimitedness and sampling, the Graph-Sign algorithm demonstrates fast, stable, and robust graph signal estimation performance under impulsive noise modeled by alpha stable, Cauchy, Student's t, or Laplace distributions.

show abstract

Section: Algorithm Derivation and Complexity Analysismentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Adaptive Sign Algorithm for Graph Signal Processing

Yao¹,

Kuruoğlu²,

Altınkaya³

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…where μ > 0 is a constant related to the performance of a signal receiver and α is a Rayleigh distribution noise introduced by the environmental and thermal noise in the radio receiver [18]. It should be noted that radio emission is undetectable when rss ≤ 0, representing the fact that the sensitivity of a radio receiver is limited.…”

Section: Sensor Model Of Airborne Radiomentioning

confidence: 99%

Modelling and Simulation of Distributed UAV Swarm Cooperative Planning and Perception

Ling

Luo

Chen

et al. 2021

International Journal of Aerospace Engineering

View full text Add to dashboard Cite

As an emerging topic, the swarm of autonomous unmanned aerial vehicles (UAVs) has been attracting great attention. Due to the indeterminacy of sensors, distributed cooperative swarms have been considered to be efficient and robust but challenging to design and test. To facilitate the development of distributed swarms, it has been proposed to utilise a simulation platform for cooperative UAVs using imperfect perception. However, the existing simulation platforms cannot satisfy this demand due to a few reasons. First, they are designed for a specific purpose, and their functionalities are difficult to extend. Second, the existing platforms lack compatibility to be applied to different types of scenarios. Third, the modelling of these platforms is too simplified to simulate flight motion dynamic and noisy communication accurately, which may cause a difference in performance between the simulation and real-world application. To address the mentioned issues, this paper models the problem and proposes a simulation platform for distributed swarm cooperative perception, which addresses software engineering concerns and provides a set of extendable functionalities of a cooperative swarm, including communication, estimation, perception fusion, and path planning. The applicability of the proposed platform is verified by simulations with the real-world application. The simulation results demonstrate that the proposed system is viable.

show abstract

“…The first method for sampling theory is proposed by Pesenson in [29]. On the other hand, since the adaptive algorithms are flexible [30][31][32][33][34][35], online graph signal reconstruction methods based on adaptive strategies have been proposed [36].…”

Section: Introduction 1background and Motivationmentioning

confidence: 99%

Robust Adaptive Estimation of Graph Signals Based on Welsch Loss

Wang

Sun

2022

Symmetry

Self Cite

View full text Add to dashboard Cite

This paper considers the problem of adaptive estimation of graph signals under the impulsive noise environment. The existing least mean squares (LMS) approach suffers from severe performance degradation under an impulsive environment that widely occurs in various practical applications. We present a novel adaptive estimation over graphs based on Welsch loss (WL-G) to handle the problems related to impulsive interference. The proposed WL-G algorithm can efficiently reconstruct graph signals from the observations with impulsive noises by formulating the reconstruction problem as an optimization based on Welsch loss. An analysis on the performance of the WL-G is presented to develop effective sampling strategies for graph signals. A novel graph sampling approach is also proposed and used in conjunction with the WL-G to tackle the time-varying case. The performance advantages of the proposed WL-G over the existing LMS regarding graph signal reconstruction under impulsive noise environment are demonstrated.

show abstract

Adaptive estimation and sparse sampling for graph signals in alpha-stable noise

Cited by 20 publications

References 40 publications

Adaptive Sign Algorithm for Graph Signal Processing

Adaptive Sign Algorithm for Graph Signal Processing

Modelling and Simulation of Distributed UAV Swarm Cooperative Planning and Perception

Robust Adaptive Estimation of Graph Signals Based on Welsch Loss

Contact Info

Product

Resources

About