Human-Centered Cyber-Physical Systems with Applications in Delivery and Logistics

A C2SR Colloquia Series | Distinguished Webinar Series.
The Distinguished Speaker Webinar Series aims to advance state-of-the-art concepts and methods in artificial intelligence and cyber security. It is jointly hosted by the Centers for Cyber Security and AI Research and the School of Electrical Engineering and Computer Science (SEECS) at the University of North Dakota College of Engineering & Mines.
Speaker Biography:
Yi Ding is a Tenure-Track Assistant Professor in Computer Science at The University of Texas at Dallas. Previously, he was a Postdoctoral Associate at MIT Institute for Data, Systems, and Society (IDSS) and Media Lab from 2022 to 2023. He received his Ph.D. in Computer Science and Engineering from the University of Minnesota and Bachelor’s and Master’s degrees from Zhejiang University. His research interests lie at the intersection of cyber-physical systems (CPS), mobile computing, and data mining. He is interested in studying human behavior through smartphone sensing and machine learning in CPS and cyber-human systems (CHS) like location-based services, urban delivery, and smart cities. Yi’s technical contributions have led to more than 20 papers in premium venues and journals, including SIGCOMM, NSDI, MobiCom, UbiComp, RTSS, VLDB, KDD, and SIGSPATIAL. Yi was the recipient of the 2022 CPS Rising Star and 2021 RTSS Outstanding Paper Award.
About the Webinar:
Cyber-physical systems (CPS) have been studied for years and provide a unified view to model and study systems that involve the physical world. The deep involvement of humans in some CPS applications (e.g., location-based social networks, urban delivery, smart cities) leads to new research opportunities and challenges in building systems that not only consider system factors (e.g., accuracy, scalability, efficiency) but also consider human factors (e.g., privacy, safety). Interestingly, human behavior (e.g., mobility, activity) is a key factor in this process. State-of-the-art solutions use sensing technologies and machine learning algorithms to understand human behavior. However, for some large-scale applications in the real world, existing solutions do not work due to human behavior uncertainty and other emerging challenges like system heterogeneity. My works address these challenges from a system perspective based on a deep understanding of human behavior and related technologies. Specifically, I design systems under real-world constraints to collect data from smartphone sensors and other sources on human behavior and analyze the data in different dimensions (e.g., spatial, temporal, and contextual). In this talk, I will use urban delivery (e.g., DoorDash, Uber Eats) as an example to show (1) Why we need to study human behavior in CPS. (2) How to build systems under real-world constraints to sense and infer human behavior (i.e., couriers’ location information) in the wild. Finally, I will discuss some current and future work that interests me.