"Discovering and Communicating Temporal Patterns within Incident Data "
Catherine Plaisant - PI
Computer Science
While the transportation community emphasizes developing standards for archiving and transmitting raw incident data, little effort has been made to design appropriate visual analytics tools to explore the data, extract meaningful knowledge, and represent results. To improve the integrated management of transportation facilities we believe that novel designs are needed for (1) enabling exploratory search of rich incident data, (2) providing user-controlled visualizations of results, and (3) facilitating cause and effect analysis. Traditional safety and incident analysis has mostly focused on incident attributes data (such as the location and time of the incident or type of vehicle involved). In this project we will focus on exploring temporal aspects that are often overlooked e.g. the length of time there has been water on the road, how long it took for responders and equipment to arrive on scene, the length of time that lanes were blocked or closed, etc.)
By bridging the worlds of databases, user interface design and information visualization, we believe that we can create the next generation of potent visual analytic tools for temporal data exploration of incident data. After 30 years in which SQL was the dominant query framework, we offer a fresh visual approach that promises to impact theory and practice for temporal data exploration, which can in turn help identify both effective countermeasures and improve the integrated management of transportation systems
