Spectral temporal graph neural network for multivariate time-series forecasting
Multivariate time-series forecasting plays a crucial role in many real-world applications. It is
a challenging problem as one needs to consider both intra-series temporal correlations and …
a challenging problem as one needs to consider both intra-series temporal correlations and …
Fourier could be a data scientist: From graph Fourier transform to signal processing on graphs
Dealing with data and observations has always been an important aspect of discovery in
science. The idea that science is related to data was brilliantly summarised by Fourier in his …
science. The idea that science is related to data was brilliantly summarised by Fourier in his …
A graph signal processing perspective on functional brain imaging
Modern neuroimaging techniques provide us with unique views on brain structure and
function; ie, how the brain is wired, and where and when activity takes place. Data acquired …
function; ie, how the brain is wired, and where and when activity takes place. Data acquired …
Gated graph recurrent neural networks
Graph processes exhibit a temporal structure determined by the sequence index and and a
spatial structure determined by the graph support. To learn from graph processes, an …
spatial structure determined by the graph support. To learn from graph processes, an …
On semi analytical and numerical simulations for a mathematical biological model; the time-fractional nonlinear Kolmogorov–Petrovskii–Piskunov (KPP) equation
MMA Khater, MS Mohamed, RAM Attia - Chaos, Solitons & Fractals, 2021 - Elsevier
Through five latest numerical schemes (Adomian decomposition (AD), El Kalla (EK), cubic B-
spline (CBS), expanded Cubic B-Spline (ECBS), exponential cubic B-spline (ExCBS), this …
spline (CBS), expanded Cubic B-Spline (ECBS), exponential cubic B-spline (ExCBS), this …
On the solitary wave solutions and physical characterization of gas diffusion in a homogeneous medium via some efficient techniques
M Khater, B Ghanbari - The European Physical Journal Plus, 2021 - Springer
This paper aims to determine some novel solitary wave solutions of the Chaffee–Infante
equation, which have not yet been presented for this equation. This equation arises in …
equation, which have not yet been presented for this equation. This equation arises in …
Graph filters for signal processing and machine learning on graphs
Filters are fundamental in extracting information from data. For time series and image data
that reside on Euclidean domains, filters are the crux of many signal processing and …
that reside on Euclidean domains, filters are the crux of many signal processing and …
Graph Signal Processing: History, development, impact, and outlook
Signal processing (SP) excels at analyzing, processing, and inferring information defined
over regular (first continuous, later discrete) domains such as time or space. Indeed, the last …
over regular (first continuous, later discrete) domains such as time or space. Indeed, the last …
Graph reduction with spectral and cut guarantees
A Loukas - Journal of Machine Learning Research, 2019 - jmlr.org
Can one reduce the size of a graph without significantly altering its basic properties? The
graph reduction problem is hereby approached from the perspective of restricted spectral …
graph reduction problem is hereby approached from the perspective of restricted spectral …
Grid-graph signal processing (grid-GSP): A graph signal processing framework for the power grid
R Ramakrishna, A Scaglione - IEEE Transactions on Signal …, 2021 - ieeexplore.ieee.org
The underlying theme of this paper is to explore the various facets of power systems data
through the lens of graph signal processing (GSP), laying down the foundations of the Grid …
through the lens of graph signal processing (GSP), laying down the foundations of the Grid …