A Data Mining Approach to Identify Key Factors of Traffic Injury Severity
AbstractSeventy percent of the traffic crash fatalities of Iran happen on rural roads, and a significant proportion of the rural roads network of this country is constituted of the main two-lane, two-way roads. The purpose of this study is to identify the most important factors which affect injury severity of drivers involved in traffic crashes on these roads, so that by eliminating or controlling such factors an overall safety improvement can be accomplished. Using the Classification and Regression Tree (CART), one of the powerful data mining tools, the crash data pertaining to the last three years (2006-2008) were analyzed. The variable selection procedure was carried out on the basis of Variable Importance Measure (VIM) which is one of the CART method outputs. The results revealed that not using the seat belt, improper overtaking and speeding are the most important factors associated with injury severity. KEYWORDS: injury severity; traffic safety; data mining; Classification and Regression Trees (CART); Variable Importance Measure (VIM)
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).