Customized AI and Edge Computing for Safer and Smarter Transportation Infrastructure Systems
Sensors are essential for the intelligence needed by smart transportation infrastructure systems. Deployment of these sensors has increased over the past decades. Although these sensors can collect a substantial amount of data, the bandwidth and cost constraints of the communication network may not allow all these data to be transferred timely for processing on the cloud or server. Thus, it is highly desirable to process, store, and extract data at the edge where things and people produce or consume the data, and this has led to a new research field called edge computing. Due to the limited computing power at the edge devices (such as the sensors), however, conventional computation models, particularly artificial intelligence (AI) methods, cannot be effectively applied. To address this challenge, research efforts are needed to customize existing AI methods and develop new algorithms and tools for efficient data processing, analysis, and understanding. This talk introduces a couple of such research efforts made at the STAR Lab that produced example edge computing methods, including edge AI, implemented in an Internet of Things device deployable for V2X applications toward safer and smarter transportation infrastructure systems. This presentation will stimulate more researchers to invest their energy on customizing AI and developing new edge computing methods and tools for transportation safety and efficiency improvements.
Yinhai Wang, Ph.D., is a professor in transportation engineering at both Civil and Environmental Engineering and Electrical and Computer Engineering of the University of Washington (UW). He is also the founding director of the UW Smart Transportation Applications and Research Laboratory (STAR Lab) and has served as director for Pacific Northwest Transportation Consortium (PacTrans), USDOT University Transportation Center for Federal Region 10, since 2012. Dr. Wang was the 2018-2019 president of Transportation & Development Institute (T&DI) at American Society of Civil Engineers (ASCE). His active research fields include traffic sensing, artificial intelligence, transportation safety, transportation data science, big-data analytics, traffic operations and simulation, smart urban mobility, etc. He also serves as chair of the Artificial Intelligence and Advanced Computing Applications Committee of the Transportation Research Board (TRB), IEEE Smart Cities Technical Activity Committee, and associate editor for two journals, including Journal of Transportation Engineering Part A and Journal of Intelligent Transportation Systems.