Transportation issues are often too complicated to be addressed by conventional parametric methods. Increasing data availability and recent advancements in machine learning provide new methods to tackle the challenging transportation problems. Readers will learn how to develop and apply different types of machine learning models to transportation related problems. Example applications include transportation data generations, traffic sensing, transportation mode recognition, transportation system management and control, traffic flow prediction, and traffic safety analysis.

Data-Driven Solutions to Transportation Problems explores the fundamental principle of analyzing different types of transportation-related data using methodologies such as the data fusion model, the big data mining approach, computer vision-enabled traffic sensing data analysis, and machine learning. The book examines the state-of-the-art in data-enabled methodologies, technologies and applications in transportation. Readers will learn how to solve problems relating to energy efficiency under connected vehicle environments, urban travel behavior, trajectory data-based travel pattern identification, public transportation analysis, traffic signal control efficiency, optimizing traffic networks network, and much more.