Visual Analytics for Transportation Incident Data Sets

Abstract

Transportation systems are being monitored at an unprecedented scope, which is resulting in tremendously detailed traffic and incident databases. Although the transportation community emphasizes developing standards for storing these incident data, little effort has been made to design appropriate visual analytics tools to explore the data, extract meaningful knowledge, and represent results. Analyzing these large multivariate geospatial data sets is a nontrivial task. A novel, web-based, visual analytics tool called Fervor is proposed as an application that affords sophisticated, yet user-friendly, analysis of transportation incident data sets. Interactive maps, histograms, two-dimensional plots, and parallel coordinates plots are four featured visualizations that are integrated to allow users to interact simultaneously with and see relationships among multiple visualizations. Using a rich set of filters, users can create custom conditions to filter data and focus on a smaller data set. However, because of the multivariate nature of the data, finding interesting relationships can be a time-consuming task. Therefore, a rank-by-feature framework has been adopted and further expanded to quantify the strength of relationships among the different fields describing the data. In this paper, transportation incident data collected by the Maryland State Highway Administration's CHART program are used; however, the tool can be easily modified to accept other transportation data sets.

A Review of Data Analytic Applications in Road Traffic Safety. Part 1: Descriptive and Predictive Modeling

“…This can be seen as an extension to the point-based visualization, where the point-position on the map is now used to encode count. The second technique is based on "choropleth maps" [44][45][46], where areas/regions in maps are shaded, colored, or patterned relative to the value of the metric of interest. These maps are common when comparing crash/fatality rates between larger geographic regions (e.g., counties, states, or countries).…”

“…On the lower end of the spectrum, Parallel coordinates plots (PCP) and trellis (small multiples of bar charts or scatter plots) are commonly used fast plotting tools and require less data preprocessing. For example, PCP can be applied to visualize the correlation/interaction among several crash descriptors including: cars involved, day/month effects, incident type, and road condition [45,53,55]. Additionally, the trellis plot was used by Cottrill and Thakuriah [54] to visualize variations in the number of crashes by different census tracts.…”

Enhancing the Value of an Incidents Database with an Interactive Visualization Tool

“…To borrow Olsen (1999) data use cycle, data was in a stage of chaos (raw, unorganized data). Wongsuphasawat et al (2009) make similar observations about many state departments of transportation. Unification and codification (second stage) was required to convert these data into data usable for analysis and modeling (stage 3).…”

“…Multimedia dissemination of origin-destination survey data has been initiated by Chapleau et al (1997). Several web-based visualization tools have been developed at the Center for Advanced Transportation Technology Laboratory (CATT LAB) of the University of Maryland, among which some allow the visualization of incidents (Wongsuphasawat et al 2009) and try to identify correlations between incidents and congestion (Lund et al 2010). In a more general framework, MacEachren's cube (MacEachren, 1995) details the multiple roles of visualization according to the audience (public vs. private/technical), the objective (presenting known facts vs. discovering patterns), and the level of interactivity (high vs. low).…”

Visual Analytics of Mobility and Transportation: State of the Art and Further Research Directions

“…A web-based system with similar functionality was developed more recently [74]. In these works, the events were explicitly specified in the data.…”