Building Principled Decision Procedures for Urban Transit and Emergency Response Services

Lecture | January 31 | 4-5 p.m. | 290 Hearst Memorial Mining Building

 Abhishek Dubey, Vanderbilt University

 Institute of Transportation Studies

Vanderbilt University's Abhishek Dubey will present Building Principled Decision Procedures for Urban Transit and Emergency Response Services at the ITS Transportation Seminar Jan. 31, 2020 at 4 p.m. in 290 Hearst Memorial Mining Building.

Abstract: Cities worldwide are dealing with a number of stresses whose outcomes will ultimately decide the ability of humanity to maintain a sustainable and resilient future. This is particularly true of urban environments, where explosive growth and shifting demographics
is placing greater demands on the ability of critical infrastructure systems such as public transit and emergency response to perform reliably and without interruption.The solutions require principled approaches that look at the problem both from the perspective
of optimizing operations via planning and from the perspective of understanding the endogenous and exogenous uncertainties that cause service disruptions and delays. In the talk, I will cover the work done in my lab with the City of Nashville and Chattanooga to improve the transit and emergency response services. This will include our work on understanding the factors behind transit operation delays including non-recurring congestion and estimating the system-wide energy and fuel consumption costs. In the second part of the talk, I will describe mechanisms to model and predict the disruptions caused by vehicular accidents through our work with the Nashville Fire Department and the Tennessee Department of Transportation to improve response procedures. While such problems have been looked at previously, most approaches are offline and fail to capture the dynamically changing environments under which critical emergency response occurs. I will present a system that understands the changing environmental dynamics from streaming data sources while using an algorithmic framework that can compute promising actions for a given decision-theoretic model for responder dispatch. I will conclude by describing recent solutions that we are implementing in Nashville and Chattanooga for addressing the IT infrastructural challenges that city
agencies face while implementing large scale sensing and data intensive algorithms.

Bio: Dr. Abhishek Dubey is an Assistant Professor of Electrical Engineering and Computer Science at Vanderbilt University and a Senior Research Scientist at the Institute for Software-Integrated Systems. Abhishek directs the SCOPE lab at the Institute for Software Integrated Systems and is the co-lead of Vanderbilt Initiative for Smart Cities Operation and Research (VISOR). His research interests broadly lie in the area of resilient cyber physical systems. He is specially interested in performance management, online failure detection, isolation and recovery in smart and connected cyber-physical systems, with a focus on transportation networks and smart grid. His key contributions include the development and deployment of resilience decision support systems for Metropolitan Transit Authority in Nashville, a robust incident prediction and dispatch system developed for Nashville Fire Department and a privacy-preserving decentralized system for peer-to-peer energy exchange. His other contributions include middleware for online fault-detection and recovery in software intensive distributed systems and a robust software model for building cyber-physical applications, along with spatial and temporal separation among different system components, which guarantees fault isolation. Recently, this work has been adapted for fault detection and isolation in breaker assemblies in power transmission lines. His work has been funded by the National Science Foundation, NASA, DOE, ARPA-E, AFRL, DARPA, Siemens, Cisco and IBM. Abhishek completed his PhD in Electrical Engineering from Vanderbilt University in 2009 in the area of fault detection and isolation for large computing clusters. He received his M.S. in Electrical Engineering from Vanderbilt University in August 2005 and completed his undergraduate studies in Electrical Engineering from the Indian Institute of Technology, Banaras Hindu University, India in May 2001.

 syka@berkeley.edu