Traffic accidents are one of the main causes of death and economic loss in most of the developed countries. According to the Road Safety Action Programme of European Commission, more than one million accidents a year cause more than 40 000 deaths and nearly two million injuries on the roads. In addition, the direct and indirect cost has been estimated at 160 billion euros, which is nearly two percent of the EU’s GNP. Unfortunately these thrilling numbers are increasing every year. The number of road accidents in Turkey is approximately half million in 1998, where this number exceeds 720,000 in 2006. However, the most regretful fact is that, 97 percent of the accidents in our country is caused by driver mistakes.
The aim of the ADES project is developing a framework to reduce the rate of the accidents based on driver faults by detecting and reporting the traffic violations. If the driver violates rules, the system gives a negative response with full justification otherwise it should give a positive response.
In ADES project, the task is divided into two major parts. The first part acquires the sensor data and processes it for the use of the inference engine. The second part, which is the inference engine, uses the sensor values as facts, and comes up with the final decision according to its rules in the knowledge base. Since the rules in the knowledge base will be derived from common traffic rules for this application, they are going to be introduced by human experts. As a result, the inputs of the system are sensor values and predefined expert rules, and the output is the evaluation of the driver’s moves.
