Transportation agencies are familiar with traditional traffic data (e.g., speed, volume) produced from traditional data collection methods (e.g., tube counts) and the traditional methods to analyze the data to produce origin-destination tables, segment speed delay etc. However, there are new and emerging traffic data sets (e.g., ubiquitous speed, vehicle specific data) collected from new and emerging data sets (e.g., third-party probe data, sensors) and corresponding alternate methods to analyze the data to understand, for example harsh braking, delays, or level of service/return to normal. The new and emerging traffic data collection methods produce a lot of data (often referred to as Big Data), and some transportation agencies have hired data scientists and artificial intelligence (AI) specialists to conduct data analysis. The analyses and processing of these large sets of data often require additional skills and tools beyond traditional data analysis methods. This is not only due to the large volumes of data, but also because of additional factors such as the conflation of multiple data sets together. The objective of this project was to understand and document different transportation agency examples of new and emerging alternate methods of traffic data analysis through a literature review, interviews, and related webinars.
Enterprise