Standard

Autoregressive Moving Average Graph Filtering. / Isufi, Elvin; Loukas, Andreas; Simonetto, Andrea; Leus, Geert.

In: IEEE Transactions on Signal Processing, Vol. 65, No. 2, 7581108, 2017, p. 274-288.

Research output: Contribution to journalArticleScientificpeer-review

Harvard

Isufi, E, Loukas, A, Simonetto, A & Leus, G 2017, 'Autoregressive Moving Average Graph Filtering' IEEE Transactions on Signal Processing, vol. 65, no. 2, 7581108, pp. 274-288. https://doi.org/10.1109/TSP.2016.2614793

APA

Vancouver

Author

Isufi, Elvin ; Loukas, Andreas ; Simonetto, Andrea ; Leus, Geert. / Autoregressive Moving Average Graph Filtering. In: IEEE Transactions on Signal Processing. 2017 ; Vol. 65, No. 2. pp. 274-288.

BibTeX

@article{84dc2593fc8f4c84868b51d4fe8dff4d,
title = "Autoregressive Moving Average Graph Filtering",
abstract = "One of the cornerstones of the field of signal processing on graphs are graph filters, direct analogs of classical filters, but intended for signals defined on graphs. This paper brings forth new insights on the distributed graph filtering problem. We design a family of autoregressive moving average (ARMA) recursions, which are able to approximate any desired graph frequency response, and give exact solutions for specific graph signal denoising and interpolation problems. The philosophy to design the ARMA coefficients independently from the underlying graph renders the ARMA graph filters suitable in static and, particularly, time-varying settings. The latter occur when the graph signal and/or graph topology are changing over time. We show that in case of a time-varying graph signal, our approach extends naturally to a two-dimensional filter, operating concurrently in the graph and regular time domain. We also derive the graph filter behavior, as well as sufficient conditions for filter stability when the graph and signal are time varying. The analytical and numerical results presented in this paper illustrate that ARMA graph filters are practically appealing for static and time-varying settings, as predicted by theoretical derivations.",
keywords = "autoregressive moving average graph filters, Distributed graph filtering, infinite impulse response graph filters, signal processing on graphs, time-varying graph signals, time-varying graphs",
author = "Elvin Isufi and Andreas Loukas and Andrea Simonetto and Geert Leus",
year = "2017",
doi = "10.1109/TSP.2016.2614793",
language = "English",
volume = "65",
pages = "274--288",
journal = "IEEE Transactions on Signal Processing",
issn = "1053-587X",
publisher = "IEEE",
number = "2",

}

RIS

TY - JOUR

T1 - Autoregressive Moving Average Graph Filtering

AU - Isufi, Elvin

AU - Loukas, Andreas

AU - Simonetto, Andrea

AU - Leus, Geert

PY - 2017

Y1 - 2017

N2 - One of the cornerstones of the field of signal processing on graphs are graph filters, direct analogs of classical filters, but intended for signals defined on graphs. This paper brings forth new insights on the distributed graph filtering problem. We design a family of autoregressive moving average (ARMA) recursions, which are able to approximate any desired graph frequency response, and give exact solutions for specific graph signal denoising and interpolation problems. The philosophy to design the ARMA coefficients independently from the underlying graph renders the ARMA graph filters suitable in static and, particularly, time-varying settings. The latter occur when the graph signal and/or graph topology are changing over time. We show that in case of a time-varying graph signal, our approach extends naturally to a two-dimensional filter, operating concurrently in the graph and regular time domain. We also derive the graph filter behavior, as well as sufficient conditions for filter stability when the graph and signal are time varying. The analytical and numerical results presented in this paper illustrate that ARMA graph filters are practically appealing for static and time-varying settings, as predicted by theoretical derivations.

AB - One of the cornerstones of the field of signal processing on graphs are graph filters, direct analogs of classical filters, but intended for signals defined on graphs. This paper brings forth new insights on the distributed graph filtering problem. We design a family of autoregressive moving average (ARMA) recursions, which are able to approximate any desired graph frequency response, and give exact solutions for specific graph signal denoising and interpolation problems. The philosophy to design the ARMA coefficients independently from the underlying graph renders the ARMA graph filters suitable in static and, particularly, time-varying settings. The latter occur when the graph signal and/or graph topology are changing over time. We show that in case of a time-varying graph signal, our approach extends naturally to a two-dimensional filter, operating concurrently in the graph and regular time domain. We also derive the graph filter behavior, as well as sufficient conditions for filter stability when the graph and signal are time varying. The analytical and numerical results presented in this paper illustrate that ARMA graph filters are practically appealing for static and time-varying settings, as predicted by theoretical derivations.

KW - autoregressive moving average graph filters

KW - Distributed graph filtering

KW - infinite impulse response graph filters

KW - signal processing on graphs

KW - time-varying graph signals

KW - time-varying graphs

UR - http://www.scopus.com/inward/record.url?scp=85012240051&partnerID=8YFLogxK

U2 - 10.1109/TSP.2016.2614793

DO - 10.1109/TSP.2016.2614793

M3 - Article

VL - 65

SP - 274

EP - 288

JO - IEEE Transactions on Signal Processing

T2 - IEEE Transactions on Signal Processing

JF - IEEE Transactions on Signal Processing

SN - 1053-587X

IS - 2

M1 - 7581108

ER -

ID: 28022134