• TRB 2016 Annual Conference

    Researchers of Urban Mobility and Intelligent Transportation Systems (UrbanMITS) presented 12 papers in TRB 2016 annual conference.

    See papers here


  • TRB 2016 Annual Conference

    Jingqin Gao was presenting 'Modeling Double-Parking Impact on Urban Streets'.

  • TRB 2016 Annual Conference

    Kun Xie was presenting 'A Data-Driven Method for Predicting Future Evacuation Zones in the Context of Climate Change'.

  • TRB 2016 Annual Conference

    Dr Sami Demiroluk was presenting 'Feature Selection for Ranking of Most Influential Variables for Evacuation Behavior Modeling across Disasters'.

  • TRB 2016 Annual Conference

    Dr Hong Yang was presenting: 'Modeling Evacuation Behavior under Hurricane Conditions'.

  • TRB 2016 Annual Conference

    Abdullah Kurkcu and Dr Ender Faruk Morgul @ poster session with 'Evaluating Usability of Geo-located Twitter as a Tool for Human Activity and Mobility Patterns: Case Study for New York City'.

  • TRB 2016 Annual Conference

    Yuan Zhu and Kun Xie @ poster session with 'Using Big Data to Study Resilience of Taxi and Subway Trips for Hurricanes Sandy and Irene'.

  • TRB 2015 Conference: Best Paper Award

    Kun Xie, et al. Modeling the Safety Impacts of Off-Hour Delivery Programs in Urban Areas, 94th TRB Annual Conference.

  • Crash Analysis of Manhattan

    Visualization prepared by Kun Xie.

  • New York City Boro-Taxi Pick-up Locations

    Visualization prepared by Jinqin Gao.

Mission Statement

New York University City Safety and Mobility Analytics for Resilient Transportation system (CitySMART) Laboratory is a multi-modal transportation infrastructure research and education facility combining a series of new concepts, technologies and services to integrate information, vehicles and transportation infrastructure to increase mobility, safety and comfort, and reduce energy waste and pollution. Since its inception, It has been a collaborative effort between the University, state and federal governments, and industry.

Project Highlights

Recent Papers

Modeling Double Parking Impacts

Double parking is one of the key contributors to traffic congestion on urban streets. This study utilizes parking violation records for New York City along with field data collected using video recording, and adopts a comprehensive modeling approach that combines available data with two types of models: M/M/∞ queueing model and micro-simulation model. It can provide traffic agencies a potential approach to quantify the impact of double parking in a large-scale network and insights into the management and alleviation of on-street parking problems including incentives for encouraging off-hour deliveries and more effective enforcement during peak hours.

Human Mobility Study based on Geo-Located Twitter Data

The role of location in digital world has changed as expanding numbers of internet users including location information to their posts and these digital footprints allowed researchers to study the spatial and temporal characteristics of human activity and mobility patterns. This paper introduces an approach to collecting and utilizing geo-located Twitter status updates to report a quantitative assessment of human mobility. The results show that Twitter users follow the “Lévy Flight” mobility patterns. Moreover, the estimated mobility flows are found to be similar to the ground-truth data obtained from NYMTC Regional Household Travel Survey.

Analysis of Pedestrian Safety Using Big Data

This study explores the potential of using big data including taxi trip, subway turnstile, road network, land use, socio-demographic data in advancing the pedestrian safety analysis including the investigation of contributing factors and the hotspot identification. A tobit model is developed to relate grid cell-specific contributing factors to crash costs which are left-censored at zero. The potential for safety improvement (PSI) which could be obtained by using the actual crash cost minus the cost of “similar” sites estimated by the tobit model was used as a measure to identify and rank pedestrian crash hotspots.

Data Driven Resilience Study

The study investigates spatio-temporal variations of transportation system recovery behavior, Recovery curves are estimated for each evacuation zone category to model time-dependent recovery patterns of the roadway and transit systems. The methodology proposed in this study can be used to evaluate the resilience of transportation systems to natural disasters and the findings can provide government agencies with useful insights into emergency management.