Rate My Professor Saif Jabari

Jabari's research centers on the theoretical foundations of traffic flow theory, with emphasis on data analytics, modeling uncertainty, emergent phenomena, scaling laws, stochastic processes, and traffic data analysis. His applied work addresses traffic operations and control, including traffic state estimation and prediction, distributed traffic control, urban network management algorithms, and cybersecurity vulnerabilities in autonomous vehicle perception and congestion control systems. He has received the Award for Innovation and Outstanding Teaching from NYUAD Engineering Division and the 2010 Student of the Year award in Intelligent Transportation Systems from the University of Minnesota ITS Institute. Notable publications include "Nonlinear traffic prediction as a matrix completion problem with ensemble learning" (Transportation Science, 2022), "Stop and go: Exploring backdoor attacks in deep reinforcement learning-based traffic congestion control systems" (IEEE Transactions on Information Forensics and Security, 2021), "Sparse travel time estimation from streaming data" (Transportation Science, 2020), "Position weighted backpressure intersection control for urban networks" (Transportation Research Part B: Methodological, 2019), and "Traffic state estimation using stochastic Lagrangian dynamics" (Transportation Research Part B: Methodological, 2018). Jabari holds U.S. patents such as "Systems and methods for sparse travel time estimation" (US20180232650A1) and "Traffic Network Sensor Placement" (US9466209 B2). His contributions advance stochastic traffic flow modeling and intelligent transportation systems.