Big data analytics to aid developing livable communities.

TRCLC 14-08In transportation, ubiquitous deployment of low-cost sensors combined with powerfulcomputer hardware and high-speed network makes big data available. USDOT defines bigdata research in transportation as a number of advanced techniques applied to the capture,management and analysis of very large and diverse volumes of data. Data in transportationare usually well organized into tables and are characterized by relatively low dimensionalityand yet huge numbers of records. Therefore, big data research in transportation has uniquechallenges on how to effectively process huge amounts of data records and data streams.The purpose of this study is to conduct research on the problems caused by large datavolume and data streams and to develop applications for data analysis in transportation. Toprocess large number of records efficiently, we have proposed to aggregate the data atmultiple resolutions and to explore the data at various resolutions to balance betweenaccuracy and speed. Techniques and algorithms in statistical analysis and data visualizationhave been developed for efficient data analytics using multiresolution data aggregation.Results will be helpful in setting up a primitive stage towards a rigorous framework for generalanalytical processing of big data in transportation