Speaker: Tirza Routtenberg, Assoc.Professor, School of Electrical and Computer Engineering, Ben-GurionUniversity, Negev, Israel, also William R. Kenan, Jr. Visiting Professor forDistinguished Teaching at the Electrical and Computer Engineering Department, PrincetonUniversity
Title: StatisticalGraph Signal Processing with Applications to Smart Grids
Time:11.00 am – 12.00pm, Thursday, January 26, 2023
Location: EE Conference Room, Mudd 1300
host: James Anderson
Abstract:
Graphs are fundamental mathematicalstructures that are widely used in various fields for network data analysis tomodel complex relationships within and between data, signals, and processes. Inparticular, graph signals arise in many modern applications, leading to theemergence of the area of graph signal processing (GSP) in the last decade. GSPtheory extends concepts and techniques from traditional digital signalprocessing (DSP) to data indexed by generic graphs, including the graph Fouriertransform (GFT), graph filter design, and sampling and recovery of graphsignals. However, most of the research effort in this field has been devoted tothe purely deterministic setting. In this study, we consider the extension ofstatistical signal processing (SSP) theory by developing graph SSP (GSSP)methods and bounds. Special attention will be given to the development of GSPmethods for monitoring the power systems, which has significant practicalimportance, in addition to its contribution to the enrichment of theoreticalGSSP tools. In particular, we will discuss the following problems (as timepermits): 1) Bayesian estimation of graph signals in non-linear models; 2) theidentification of edge disconnections in networks based on graph filterrepresentation; 3) the development of performance bounds, such as thewell-known Cramér-Rao bound (CRB), on the performance in various estimationproblems that are related to the graph structure; 4) the detection of falsedata injected (FDI) attacks on the power systems by GSP tools; 5) Laplacianlearning with applications to admittance matrix estimation. The methodsdeveloped in these works use GSP concepts, such as graph spectrum, GSP, graphfilters, and sampling over graphs.
Bio:
Tirza Routtenberg is an AssociateProfessor in the School of Electrical and Computer Engineering at Ben-GurionUniversity of the Negev, Israel. In addition, she is a William R. Kenan, Jr.,Visiting Professor for Distinguished Teaching at the Electrical and ComputerEngineering Department at Princeton University for 2022-2023. She was therecipient of four Best Student Paper Awards at international conferences. Sheis currently an Associate Editor of IEEE Transactions on Signal and InformationProcessing Over Networks and of IEEE Signal Processing Letters. In addition,she is part of the SPS Technical Directions Board Representative on theEducation Board. Her research interests include statistical signal processing,graph signal processing, and optimization and signal processing for smart grids.