Presentation of Machine Learning Approaches for Predicting the Severity of Accidents to Propose the Safety Solutions on Rural Roads

The aim of the current research was to develop models predict severity accidents on rural roads in Tehran province, Iran. In this regard, using accident data from 2017 2020, machine learning algorithms, including multiple logistic regression, multilayer perceptron neural network (MLPNN), and radial basis function (RBFNN) models, as well statistical methods, Kolmogorov–Smirnov test, Friedman factor analysis, were implemented determine contributory factors accidents. Thus, nine variables affecting considered modeling, then effect each variable calculated. By comparing results artificial (ANN) it indicated that human had a remarkable severity. addition, both methods can be served guidance for safety authorities provide solutions, thereby leading reducing Finally, performances ANN analyzed by other mathematical built MATLAB programming.