Search

As a threat for transportation system, traffic crashes have a wide range of social consequences for governments. Traffic crashes are increasing in developing countries and Iran as a developing country is not immune from this risk. There are several researches in the literature to predict traffic crash severity based on artificial neural networks (ANNs), support vector machines and decision trees. This paper attempts to investigate the crash injury severity of rural roads by using a hybrid clustering and classification approach to compare the performance of classification algorithms before and after applying the clustering. In this paper, a novel rule-based genetic algorithm (GA) is proposed to predict crash injury severity, which is evaluated by performance criteria in comparison with classification algorithms like ANN. The results obtained from analysis of 13,673 crashes (5600 property damage, 778 fatal crashes, 4690 slight injuries and 2605 severe injuries) on rural roads in Tehran Province of Iran during 2011–2013 revealed that the proposed GA method outperforms other classification algorithms based on classification metrics like precision (86%), recall (88%) and accuracy (87%). Moreover, the proposed GA method has the highest level of interpretation, is easy to understand and provides feedback to analysts. [ABSTRACT FROM PUBLISHER]

The merits for development and application of crash frequency prediction models for safety promotion on any road type, with a focus on urban collector streets, are presented in this article. The city of Yazd, a medium-sized city in the middle of Iran, was selected as a case study and the data required for modelling crash frequencies along five collector streets comprising 31 street sections were collected. Six models including Poisson and negative binomial models and their deviations along with a hybrid artificial neural networks (ANN) model were developed to predict crash frequency along each street section. The overfitting problem was addressed using appropriate sensitivity analysis methods which were also used to identify the input variables with significant impact on the model performance. The results indicated that the developed hybrid ANN model provided the best performance in terms of accuracy and the number of input variables. The application of hybrid ANN model to evaluate the safety impacts of four different strategies, each resembled by one of the input variables of this model, indicated that these models can successfully be used for this purpose. [ABSTRACT FROM AUTHOR]