Performance of Traffic Accidents' Prediction Models

Modeling traffic-accident frequency is a critical issue to better understand the accident trends and the effectiveness of current traffic policies and practices in different countries. The main objectives of this study are to model traffic road accidents, fatalities and injuries in Jordan, using different modeling techniques, including regression, artificial neural network (ANN) and autoregressive integrated moving average (ARIMA) models and to evaluate the safety impact of travel-restriction strategies during Covid-19 pandemic on traffic-accident statistics for the year 2020. To accomplish these objectives, data of traffic accidents, registered vehicles (REGV), population (POP) and economic gross domestic product (GDP) from 1995 through 2020 were obtained from related sources in Jordan. The analysis revealed that accidents, fatalities and injuries have an increasing trend in Jordan. Root mean of square error (RMSE), mean absolute error (MAE) and coefficient of multiple determination (R2) were sued to evaluate the performance of the developed prediction models. Based on model performance, the ANN models are the best, followed by the ARIMA models and then the regression models. Finally, it was concluded that the strategies undertaken by the government of Jordan to combat Covid-19, including complete and partial banning of travel, resulted in a considerable reduction of accidents, injuries and fatalities by about 35%, 37% and 50%, respectively. © 2023, Jordan University of Science and Technology. All rights reserved.

The Impact of COVID-19 on Road Traffic Accidents: A Case Study of Severely affected City in China

People's travel has changed greatly under the impact of COVID-19. However, it is controversial that whether traffic restrictions of COVID-19 have a positive or negative impact on traffic accidents. At present, there are few studies on the variations of traffic accidents under the impact of COVID-19 in China, and quantitative analysis is rare. Therefore, this study explores the traffic accidents characteristics of W city seriously affected COVID-19. Based on wavelet transform, traffic accident prediction model is established using property damage only accidents data to predict accident frequency without the impact of COVID-19. Compared with the actual traffic accidents frequency, this paper quantitatively analyzes the impact of COVID-19 on traffic accident. The results show that traffic accidents show a trend of decline-bottom-recovery;the frequency of accidents after the recovery is more than the previous year's level;compared with other periods in 2020, the proportion of injury accidents increased sharply during the period when traffic restrictions were gradually loose. The result of accident prediction shows that BP neural network has the best prediction effect. After the implementation of traffic restrictions, the frequency of accidents shows three stages: rapid decline, bottom and continuous rise. In the three stages, the frequency of property damage only accidents decreased by 379.06, 654.72 and 288.19 per day on average. © 2022 IEEE.