Traffic Accidents Prediction Models to Improve Traffic Safety in Greater Amman Area

Abstract

Highway related accidents are considered one of the most serious problems in the modern world. Traffic accidents cause serious threat to human life worldwide. According to the World Health Organization (WHO), more than 1.2 million people die each year in motor vehicle accidents and more than 50 millions are injured each year worldwide. Jordan, as one of the developing countries, has high level of traffic accidents. In Jordan, traffic accidents have caused more than 13000 fatalities between the years 1989-2012.

The main objectives of this study are: to develop traffic accidents regression prediction models in Amman Greater Area. These models relate accident numbers, as a dependent variable, with possible causes of accidents that are related to driver behavior, as independent variables. Also, to propose effective countermeasures to reduce the frequency and severity of traffic accidents in Jordan.

Accident data were collected from the General Security Directorate and from the Jordan Traffic Institute for the selected areas inside Greater Amman Area in Jordan. These data were analyzed and used in the regression models. Several regression prediction models were formed and the best models were chosen. The intersections and road segments, under this study, were arranged according to the traffic accidents severity. The most dangerous and hazardous streets and intersections were located in the study areas. Proper treatments and improvements are needed to reduce the number and severity of accidents in these areas. Preventive countermeasures were recommended to enhance traffic safety in Jordan specially Amman Area.

Key Words: Traffic Accidents, Traffic Safety, Driver Behavior, Countermeasures, Regression Models, Jordan Traffic Institute.