Abstract: In the era of Cyber-Physical Systems (CPS), sensing, communication, and computing are becoming more affordable and integrated. Many CPS have strict temporal constraints and often of massive scale. This talk discusses our recent and ongoing efforts to incorporate reliable, interpretable, and transferable machine learning and real-time scheduling techniques for CPS’s modeling, design, and analysis. With various engineering applications, those solutions shed light on handling challenges in energy efficiency, security isolation, system coordination, reliable prediction & control, etc., of modern CPS.

Short Bio: Dr. Guo received the B.Eng. degree (with honor) in computer science and technology from Tsinghua University, Beijing, China, in 2009, the M.Phil. degree in mechanical and automation engineering from The Chinese University of Hong Kong, Hong Kong, in 2011, and the Ph.D. degree in computer science from the University of North Carolina at Chapel Hill, Chapel Hill, NC, USA, in 2016. He is a tenure-track assistant professor in the Department of Electrical and Computer Engineering at the University of Central Florida (UCF). His research interests are in real-time scheduling theory and machine learning theory with applications to CPS. Since joining UCF, his group has published more than 20 papers on top-tier (csranking) conference venues in both real-time & embedded systems and AL/ML domains, and has received several awards, including the Best Paper award of EMSOFT, Best Student Paper and Outstanding Paper awards of RTSS.