A COMPARISON BETWEEN PREDICTION POWER OF ARTIFICIAL NEURAL NETWORKS AND MULTIVARIATE ANALYSIS IN ROAD SAFETY MANAGEMENT

Systematic review, evaluation and comparison of different approaches for the implementation of road network safety analysis

Introduction

Road safety is still a major issue all around the world. The capability to analyze the road network and identify high risk sections is crucial in road safety management. Therefore, it is essential for road administrations, practitioners, and researcher to have a clear and practical framework of the available road network safety analysis procedures. The aim of this study is to provide such a framework by carrying out an exhaustive analysis of the main procedures available all around the world.

Method

The proposed literature review has started considering a web search on Web of Science (WoS). Then, a systematic review of each publication has been carried out using the Bibliometrix software, to identify the main characteristics of the publications within the specific topic. Then, the most relevant and widespread safety analysis procedures have been considered and the following aspects have been analyzed: the type of approach (crash analysis, crash prediction models procedures, based on road safety inspections, etc.), which and how many data are required (crashes, traffic, visual inspections, geometrical data, etc.), which is the effectiveness of the procedure, and which are the segmentation criteria used (fixed length, variable length based on geometry, traffic, etc.).

Results

Ten different procedures for road network safety analysis have been considered for detailed analysis. The research findings highlight that each procedure has its own pros and cons.

Conclusions

The choice of the best procedure to use is highly related to the characteristics of the road network that need to be analyzed, to the availability of data, and to the main elements the Road Authorities (RA) wants to give priority to.

Practical applications

This collection and review of different procedures will be of great interest for RAs, practitioners, and researchers in the process of selecting the most useful procedure to use to carry out a road network safety analysis.

Evaluation of Contributing Factors Affecting Number of Vehicles Involved in Crashes Using Machine Learning Techniques in Rural Roads of Cosenza, Italy

The evaluation of road safety is a critical issue having to be conducted for successful safety management in road transport systems, whereas safety management is considered in road transportation systems as a challenging task according to the dynamic of this issue and the presence of a large number of effective parameters on road safety. Therefore, the evaluation and analysis of important contributing factors affecting the number of vehicles involved in crashes play a key role in increasing the efficiency of road safety. For this purpose, in this research work, two machine learning algorithms, including the group method of data handling (GMDH)-type neural network and a combination of support vector machine (SVM) and the grasshopper optimization algorithm (GOA), are employed. Hence, the number of vehicles involved in an accident is considered to be the output, and the seven factors affecting transport safety, including Daylight (DL), Weekday (W), Type of accident (TA), Location (L), Speed limit (SL), Average speed (AS), and Annual average daily traffic (AADT) of rural roads in Cosenza, southern Italy, are selected as the inputs. In this study, 564 data sets from rural areas were investigated, and the relevant, effective parameters were measured. In the next stage, several models were developed to investigate the parameters affecting the safety management of road transportation in rural areas. The results obtained demonstrated that the “Type of accident” has the highest level and “Location” has the lowest importance in the investigated rural area. Finally, although the results of both algorithms were the same, the GOA-SVM model showed a better degree of accuracy and robustness than the GMDH model.