A thesis submitted in partial fulfillment of the requirements for the degree of Master of Science in Remote Sensing and Geographic Information Systems

Thesis (M. Sc.) - Asian Institute of Technology, 2016

As a result of traffic accident, human being loses their lives or assets. Unfortunately, according to World Health Organization (WHO), Thailand is ranked as second-worst traffic accident death rate per 100,000 people in the world in 2013. It is required to mitigate the number of death by traffic accident. By the way, it has already reported dangerous driving behaviors such as speeding and sudden lane change are two of top three cause of traffic accident in Thailand. When road segment which has high potential risk for traffic accident, it can be useful to mitigate traffic accident in future. Taxi probe is the new approach to investigate traffic problem. Information of coordinate, velocity and direction are obtained by taxi probe and it becomes geospatial big data. These information are utilizing for providing traffic information and taxi service. Fortunately, there are approximately ten-thousand probe taxis in Thailand mainly in Bangkok and these taxis are gathering data in three to five second interval every day and storing in data server. This study aim to develop the algorithm to detect dangerous driving behavior by moderate accuracy Global Positioning System (GPS) then clarify the time period and place tendencies of occurrence of dangerous driving behavior in Bangkok Metropolitan Region (BMR) by taxi probe data