Artificial Intelligence-Driven Technologies for Smart Grids and Biomedical Applications

Bio

Dr. Erchin Serpedin is currently serving as Professor in the Electrical and Computer Engineering (ECEN) Department at Texas A&M University in College Station, Texas, and as the chair of ECEN Program at Texas A&M University at Qatar. He is the author of 4 research monographs, 1 textbook, 17 book chapters, 200 journal papers and 300 conference papers. His research interests are in signal processing, machine learning and artificial intelligence and their applications in cyber security of smart grids, biomedical engineering, and wireless communications. He served as an associate editor for more than 12 journals, including journals such as the IEEE Transactions on Information Theory, IEEE Transactions on Signal Processing, IEEE Transactions on Communications, IEEE Signal Processing Letters, IEEE Communications Letters, IEEE Transactions on Wireless Communications, IEEE Signal Processing Magazine, Signal Processing (Elsevier), Physical Communications (Elsevier), and IEEE Signal Processing Magazine. He served also as editor-in-chief of EURASIP Journal on Bioinformatics and Systems Biology, an online journal edited by Springer-Nature. His research work was recognized through more than ten best paper awards. He graduated 19 PhD students and 16 MSc students. He is an elected member of the IEEE Signal Processing Society’s Committees on Machine Learning for Signal Processing and Bioimaging and Signal Processing, respectively. He is an elected IEEE Fellow.

Abstract

This talk consists of two parts. The first part of the talk will provide an overview on the traditional machine learning tools and the more recent advances in deep learning techniques for detecting and localizing electricity stealth cyber-attacks and false data injections in smart power grids. Dr. Serpedin’s research group contributions for the past five years and current research efforts in detection, localization and mitigation of cyberattacks will be presented together with a road map for future. The second part of the talk will focus on developing a sensitive, objective, and universally accepted method of measuring people’s facial deformity using machine learning. Currently, there is a lack of reliable means to assess the benefits of reconstructive facial surgeries. For the purposes of clinical evaluation and comparison of outcomes, it is necessary to create a scale of deformity across broad populations against which any face – and any facial disorder - could objectively be measured. We discuss three distinct machine learning methods that produce numerical scores highly correlated with human ratings and that assess very well the level of deformity for a wide variety of facial conditions. This work represents a joint project with Dr Mitchell Stotland, the Chief of Plastic, Craniofacial, and Hand Surgery Department at Sidra Medicine.