Predicting Number of Accidents and Black Spot of a Route Using Genetic Algorithm | Original Article
Because of its importance in saving human lives, traffic accident prediction is a motor vehicle traffic challenge. There are various studies in the literature that use artificial neural networks (ANNs), support vector machines (SVMs), decision trees (DTs), and other categorization approaches to predict the severity of traffic accidents. Indeed, the fundamental shortcoming of ANNs and SVMs is their lack of human interpretation, whereas the main disadvantage of traditional DTs like C4.5, ID3, and CART is their low accuracy. To solve these flaws, we present a Genetic Algorithm-based method to predict traffic accidents based on user preferences instead of traditional DTs in this review.We customised a genetic algorithm, to optimise and find rules based on Support, Confidence, and Comprehensibility metrics in the suggested method. The suggested method's goal is to provide facilities for users, such as traffic cops, road and transportation engineers, to make use of their knowledge while balancing all of the competing objectives. A traffic accident data set of accidents in rural and urban roadways in Tehran Province, Iran, was used to assess the suggested technique during a five-year period (2008–2013). According to the evaluation results, the proposed technique outperforms classification methods such as ANN, SVM, and traditional DTs in terms of classification metrics such as accuracy and rule performance metrics such as support and confidence.