Spatiotemporal Machine Learning for Real-world Complex Systems: Enhancing Smart Transportation with Robust AI
This seminar introduces advanced machine learning approaches, including tensor methods for modeling high-dimensional mobility data and deep learning techniques designed to handle data corruptions, aiming to improve the reliability of spatiotemporal analytics for smarter transportation systems.
Overview
Data from complex systems, such as urban mobility, is inherently spatiotemporal and high-dimensional. However, real-world data is often noisy, incomplete, or even entirely missing, posing challenges for accurate environment perception and optimal decision-making. In this talk, I will introduce advanced machine learning methodologies to enhance the reliability and generalizability of spatiotemporal analytics in smart transportation. Specifically, I will present tensor-based methods for modeling high-dimensional mobility data and deep learning techniques designed to handle data corruptions. Ensuring data quality enables more robust downstream applications in analytics, decision automation, and explainability, ultimately driving smarter, more efficient, and reliable transportation systems.
Presenters
ZIyue Li, Assistant Professor, Information Systems Department, University of Cologne, Germany
Brief Biography
Dr. Ziyue Li is currently an Assistant Professor in the Information Systems Department at the University of Cologne, Germany. He will join Technical University of Munich at Department of Technology and Operation, and Department of Computer Science. He holds a Ph.D. in Industrial Engineering and Decision Analytics from The Hong Kong University of Science and Technology, with co-supervision at Arizona State University.
His research focuses on spatiotemporal data mining, with applications in smart transportation and smart cities, emphasizing generalizability, reliability, and robustness. Dr. Li has authored over 40 papers in top-tier AI conferences and journals. Recognized as one of the Top 50 most influential researchers in “Spatiotemporal Data Mining” and “Smart Mobility” (Google Scholar), he has received multiple prestigious international awards, including the IEEE CASE Best Conference Paper Award, INFORMS QSR Best Student Paper Award, and INFORMS DM Best Applied and Best Theoretical Paper Awards. Beyond academia, Dr. Li has extensive industrial experience with Bell Labs, Hong Kong Mass Transit Railway Co., and other leading corporates. Leveraging strong industry collaborations, he has also secured multiple industrial research grants, including funding from S-Lab and Sony Research.
Related People
Hosts
Di Wang
- Assistant Professor, Computer Science