A comparison between prediction power of artificial neural networks and multivariate analysis in road safety management. Issue 4 (2nd October 2017)

• Record Type: Journal Article
• Authors: De Luca, Mario
• Is Part Of: Transport. Volume 32:Issue 4(2017)
• Page Start: 379
• Page End: 385
• Publication Date: 2017-10-02
• Subjects: artificial neural network -- GIS -- non-linear model -- cluster analysis -- road safety; Transportation -- Lithuania -- Periodicals; 388.094793
• DOI: 10.3846/16484142.2014.995702
• Languages: English
• ISSNs: 1648-4142

Abstract

Abstract: This paper presents a methodology for the management of road safety on two-lane highways. The methodology is based on an experimental investigation carried out on a stretch of road located in southern Italy (the two-lane highway SS106). The study analyses accidents occurring between 2000 and 2005 and the data concerning the accidents that were acquired from police reports. The geometric data were acquired from the official cartography, while the traffic and environmental data were provided by the regional agency for roadway management. The data, organized and stored in a specific designed Geographic Information System (GIS), were processed using a series of statistical procedures, in particular, the results took out the following two models: Model 1 was produced by MultiVariate Analysis (MVA) and the Model 2 was obtained using the Artificial Neural Network (ANN) technique. Comparing the two models, it emerged that Model 2 is better than Model 1 because the total sum of the residual is lower. However, Model 1 is more efficient in estimating the more dangerous black spots.