Implementation of appropriate safety measures, either from the viewpoint of a vehicle, individual or the infra-structure, it is an important issue to clearly understand the multi-dimension complicated real world accident scenarios. This study proposes a new method to easily capture and to extract the essence of such complicated multi-dimension mutual relationship by visualizing the results of accidents clustering by SOM (Self Organizing Map).
The FARS data from 2010 is used to generate a dataset comprised of 16,180 fatal passenger car drivers and 48 variables. The 16,180 fatal drivers were clustered using hierarchy cluster analysis method and mapped into a twodimensional square with one dot representing one fatal driver using SOM. From the SOM assessment of the 16,180 fatal drivers, five clusters were created, and they are characterized as follows: Cluster 1 (Interstate highway accidents), Cluster 2 (Drunk speeding), Cluster 3 (Non speeding lane departure), Cluster 4 (Vehicle to vehicle) and Cluster 5 (Intersection).
Three accident scenarios are created to study potential areas of fatal accidents reduction in the SOM map, and the accident scenarios are: [A] Skidding Straight, [B] Lane Departure N.H. (National Highway) and [C] Rear-end. The three accident scenarios mutually had coverage of totally 31% of all the fatal drivers, and the three accident scenarios had high coverage of Cluster 1 (Interstate highway accidents) and some coverage over Clusters 2, 3 & 4. ESC (Electronic Stability Control), LDW (Lane Departure Warning) and FCW (Forward Collision Warning) may be relevant to help reduce the number of fatal accidents in these three accident scenarios.
The remaining areas that the three accident scenarios [A], [B] and [C] did not completely cover were the following accidents: