English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

An ongoing, two-fold challenge involves extracting useful information from the massive amounts of highway crash data and explaining complicated statistical models to inform the public about highway safety. Highway safety is critical to the trucking industry and highway funding policy. One method to analyze complex data is through the application of visual data mining tools. In this paper, we address the following three questions: a) what existing data visualization tools can assist with highway safety theory development and in policy-making?; b) can visual data mining uncover unknown relationships to inform the development of theory or practice? and c) can a data visualization toolkit be developed to assist the stakeholders in understanding the impact of publicpolicy on transportation safety? To address these questions, we developed a visual data mining toolkit that allows for understanding safety datasets and evaluating the effectiveness of safety policies. INTRODUCTION AND LITERATURE REVIEW Transportation accidents levy a significant cost on societies in terms of personal death or injury in addition to the economic costs. Road traffic injuries are the eighth leading cause of death, and the leading cause of death for individuals aged 15-29 (Lozano et al., 2012; World Health Organization, 2008). In 2010, transportation injuries have resulted in 1.24 million fatalities worldwide according to the World Health Organization (WHO), World Health Organization (2013, p. v). In addition to the lost lives, the costs associated with road traffic crashes runs to billions of dollars (Jacobs, Aeron-Thomas, & Astrop, 2000). These numbers are unacceptably high, especially since many of these fatalities can be avoided with evidencedriven road safety interventions. Road safety interventions can be effective in reducing the number of accidents and/or mitigating their effects. The WHO states that “adopting and enforcing legislation relating to important risk factors – speed, drunk–driving, motorcycle helmets, seat-belts and child restraints – has been shown to lead to reductions in road traffic injuries” (World Health Organization, 2013, p. v). These five risk factors are a sample of a larger pool of behavioral factors that lead to accidents. There are increasing regulations worldwide that have been passed to cover these behavioral factors. However, “in many countries these laws are either not comprehensive in scope or lacking altogether. Governments must do more to ensure that their national road safety laws meet best practice, and do more to enforce these laws” (World Health Organization, 2013, p. v) The problem is complex in the U.S., since highway safety policies can be different in neighboring states and the identification of best practice is often unclear (Governors Highway Safety Association, 2013). One approach to identifying best practices is to investigate the causes of vehicle crashes, assess

Using visual data mining in highway traffic safety analysis and decision making