Harnessing the power of big data to address transportation challenges.

Extending the work that was completed for year one funding related to “Developing Highway Safety Performance Metrics in an Advanced Connected Vehicle Environment Utilizing Near-Crash Events from the SHRP 2 Naturalistic Driving Study.”
The project suggests a bottom-up travel behavior driven approach which obtains trends in individual travel behavior first and use such information to enhance longitudinal origin-destination demand monitoring.
Exploring the potential for using a number of machine learning and data mining methods to analyze accident data.
The recent network disruptions in the Washington Metro system showed the new reality associated with aging transit infrastructure and highlighted the potential severity of such disruptions. However, relevant studies in the literature are limited and agencies need more empirical evidence to help them better planning and implementing maintenance work.
Analyzing traffic violations and traffic crash records to develop a probabilistic model that will help detect high risk drivers with the main goal of preventing future crashes.
This project develops novel data mining methodologies that integrate heterogeneous urban data for the estimation of city-wide transportation information.
Integrating machine learning, big data, sensor networks, and agent-based transportation modeling to prototype an algorithm that combines the power of a model-driven approach with the power of big data.
The project investigates how real-time conditions interact to affect driver safety performance changes. From that understanding, practitioners and drivers can make more informed decisions to reduce the likelihood of a crash.
Pooling P3 project data from various sources to build a database that can be analyzed and used to inform future decision making.
Developing a smartphone-based travel behavior data collection platform that recruits participants by rewarding users with real-time parking information.

We mine a wealth of data by employing a wide variety of methods, tools and models, including those from artificial intelligence (AI), machine learning, statistics, and database systems.  

When these methods are applied to large datasets that have been appropriately compiled and fused together, the result is invaluable and actionable information that can help improve the efficiency, safety, sustainability and resiliency of transportation systems. Our results inform and guide transportation planning, investment decisions, and transportation policies.

Changing The Way The World Works

SSISTL's Benefactor and Professor of Practice, Stephen Still, is featured in UB's We Are Boldy Buffalo Campaign. Stephen gave $4 million to support the Stephen Still Institute for Sustainable Transportation and Logistics. His gift–and many other gifts–are being immediately invested in opportunities for faculty and students to address society’s biggest transportation challenges.

Transportation News