Seung-Neo Son

A study on the factor analysis by grade for highway traffic accident

With respect to the trend of highway traffic accident, highway accident is in decline, whileas, the fatality is on an increasing trend. Thus, many efforts to decrease highway traffic accidents and improve the safety, are required. In particular, in case of highway, the management standard by grade for accident black spot is designated. Thus, investing the effect factors by grade for highway traffic accident is required in detail. Thus, in this study, the factors affecting the traffic accidents among the environmental factors based on the graded data for the accident black spot in the applicable section targeting the Seoul-Pusan Express Highway, were reviewed; accident forecasting model which would analyze the characteristics of the accidents for determining the accident grade, was developed. As a result of establishing a model by using Quantification Theory of Type II, considering the characteristics of the dependent and independent variables based on the geometric structure, `the fixed variable` among the variables relating to the accident, for the variables influencing over the accident grade, `the type of vans, a chassis and people`, `the trailers, special vehicles and chassis people` and `the negligence of watching and cloudy weather` were analyzed as common factors, in case of `horizontal alignment`, `longitudinal slope` and, `barricade` respectively.

Drivers Detour Decision Factor Analysis with Combined Method of Decision Tree and Neural Network Algorithm

This study`s purpose is to analyse factors of determination about detouring for makinga standard model in regard of unfavorableness and uncertainty when unspecified individual recipients make a decision at the time of course detour. In order to achieve this, we surveyed SP investigation whether making a detour or not for drivers as a target who take a high way and National highway. Based on this result, we analysed detour determination factors of drivers, establishing a combination model of Decision Tree and Neural Network model. The result demonstrates the effected factors on drivers` detour determination are in ordering of the recognition of alternative routevs, reliable and frequency of using traffic information, frequency of transition routes and age. Moreover, from the outcome in comparison with an existing model and prediction through undistributed data, the rate of combination model 8.7% illustrates the most predictable way in contrast with logit model 12.8%, and Individual Model of Decision Tree 13.8% which are existed. This reveals that the analysis of drivers` detour determination factors is valid to apply. Hence, overall study considers as a practical foundation to make effective detour strategies for increasing the utility of route networking and dispersion in the volume of traffic from now on.