PROJECT TITLE :

Intelligent Traffic Accident Prediction Model for Internet of Vehicles With Deep Learning Approach

ABSTRACT:

A high accident risk prediction model is developed for the purpose of analyzing data on traffic accidents and identifying priority intersections for improvement in this research project. A database of the traffic accidents was arranged and analyzed, and an intersection accident risk prediction model based on various mechanical learning methods was developed to estimate the possible high accident risk locations for use by traffic management departments in the process of planning countermeasures to reduce accident risk. This model was created to estimate the possible high accident risk locations for use by traffic management departments in the process of planning countermeasures. In this study, Bayes' theorem was used to identify environmental variables at intersections that affect accident risk levels. The results showed that road width, speed limit, and roadside markings are the significant risk factors for traffic accidents. Bayes' theorem was used to identify environmental variables at intersections that affect accident risk levels. In the meantime, an accident risk prediction model was developed using Naive Bayes, Decision tree C4.5, Bayesian Network, Multilayer perceptron (MLP), Deep Neural Networks (DNN), Deep Belief Network (DBN), and Convolutional Neural Network (CNN). This model can also identify the key factors that contribute to the occurrence of high-risk intersections, and it can provide departments of traffic management with a better basis for decision-making regarding the improvement of intersections. By using the same environmental characteristics as high-risk intersections as model inputs, it is possible to estimate the degree of risk that may occur in the future, which can be used to prevent traffic accidents in the future. In addition to this, it can serve as a point of reference for the design of future intersections as well as environmental enhancements.