The Role of a Detection of vehicles’ Speed and Net Overload in Road Traffic Accident Analysis with Data Mining Approach: Case of Addis Ababa

Abstract

From the advent of increased transportation, overloading and over speeding of vehicles has become the major causes for accidents and killing many lives. Transport authorities are employing advanced traffic management system (ATMS) to improve vehicular traffic management efficiency. ATMS currently uses intelligent traffic lights and sensors distributed along the roads to achieve its goals. Furthermore, there are other promising technologies that can be applied more efficiently in place of the above-mentioned ones, such as vehicular networks. In this study, the researcher tried to assess road traffic accident causes and control mechanisms undertaken by authorities, in Addis Ababa traffic police bureau and Addis Ababa Road Authority. As findings revealed, overload and over speed has immensely contributed to the incidence of road traffic accident in Addis Ababa. This research demonstrates that the Ethiopian traffic management system has been using very old systems which have very limited capacity. In this proposed work, monitoring driving behavior with the help of wireless sensor technology is the target. So, the proposed research work focused on developing a model for integrating wireless sensor network and vehicular social network. This paper presents a model, that can classify accidents well with a better accuracy as fatal, serious, and slight or property-damage was selected and evaluated. Experiment results reveal that the use of logistic regression is helpful in detecting causes of the accident. In this work it has been proved that driving over speed and over net load of vehicles are the major causes of traffic accidents in Addis Ababa and also the research proved that automation provides better performance than a human handled system