Abstract:
Road accident is the high rank cause of death in Thailand and should be solved hastily. Many studies and researches found that there are many involve factor such as driver, vehicle, road etc. The most important factor is driver because there are a lot of accidents occurred by a risk driving maneuver. The driver monitoring is one of the method to solve this problem in a public transport and fleet cars. This research is aimed to create a driving risk rating algorithm by velocity and acceleration factors for a driver monitoring. In this experiment,the participants drive in Bangkok expressway which allow them to drive in many ranges of velocity. Participants were informed to drive in different conditions such as hurry, safety and normal driving. There were observers who observed and rated the risk of driving in each condition. An observer was told to rate the driving in term of a driving risk score 1-5 point pattern. The drive recorder was used to record a satellite and video data. The satellite data was used along with an adjusted algorithm for rating a driving. The linear regression shows that there is a trend of driving score evaluated by algorithm and observers in term of linear equation with high correlation (r=.89). Furthermore, the reverse-predicting process shows the random error of rating score. The linear equation was test with hypothesis at 95% confidence level, we found that the algorithm can replace the observers in driver monitoring method and can be used with satellite data.