Sie befinden Sich nicht im Netzwerk der Universität Paderborn. Der Zugriff auf elektronische Ressourcen ist gegebenenfalls nur via VPN oder Shibboleth (DFN-AAI) möglich. mehr Informationen...
The localisation of road accident hotspots (areas of the public road network, where the number of accidents is higher than expected based on the average values) is one of the main tasks of road safety experts. Analysing these locations can help to avoid further traffic accidents and personal injuries (most of all, fatal accidents). There are several already known methods in literature for this purpose and this paper contains a comparison between the most frequently used ones: sliding-window method (using constant and variable window size), 2D sliding-window method (using constant and variable window width and height), Density-based spatial clustering of applications with noise (DBSCAN) based data-mining method (which is also a spatial method). This paper takes into account the latest technical developments in the field (available high computational capability, accuracy given by the Global Positioning System, usage of graphics accelerators and further parallel devices, etc.), The evaluation contains both the qualitative and quantitative aspects; considering accuracy, processing speed, parameter sensibility, etc.