퍼지 이론을 이용한 교통사고 위험수준 평가모형

서지정보

ㆍ발행기관 : 대한교통학회 ㆍ수록지정보 : 대한교통학회지 / 14권 / 2호
ㆍ저자명 : 변완희, 최기주

목차

ABSTRACT
1. 서론
2. 이론적 고찰
3. 사고위험수준 평가 모형
4. 사례분석
5. 결론
〈참고문헌〉

영어 초록

The evaluation of risk level or possibility of traffic accidents is a fundamental task ill reducing the dangers associated with current transportation system. However, due to the lack of data and basic researches for identifying such factors, evaluations so far have been undertaken by only the experts who can use their judgements well in this regard. Here comes the motivation this thesis to evaluate such risk level more or less in an automatic manner. The purpose of this thesis is to test the fuzzy-logic theory in evaluating the risk level of traffic accidents.
In modeling the process of expert’s logical inference of risk level determination, only the geometric features have been considered for the simplicity of the modeling. They are the visibility of road surface, horizontal alignment, vertical grade, diverging point, and the location of pedestrian crossing. At the same time, among some inference methods, fuzzy composition inference method has been employed as a backbone inference mechanism.
In calibration, the proposed model used four sites’ data. After that, using the calibrated model, six sites’ risk levels have been identified. The results of the six sites’ outcomes were quite similar to those of real world other than some errors caused by the enforcement of the model’s output. But it seems that this kind of errors can be overcome in the future if some other factors such as driver characteristics, traffic environment, and traffic control conditions have been considered. Futhermore, the application of site’s specific time series data would produce better results.

참고 자료

없음