퍼지이론을 이용한 유고감지 알고리즘

서지정보

ㆍ발행기관 : 대한교통학회 ㆍ수록지정보 : 대한교통학회지 / 28권
ㆍ저자명 : 이시복

목차

ABSTRACT
INTRODUCTION
METHODOLOGY
DESCRIPTION OF THE INCIDENT DETECTION MODE
INCORPORATION OF TEH INCIDECT DETECTION MODEL INTO A REAL-TIME CONTROL SYSTEM
EVALUATION OF THE INCIDENT DETECTION MODEL
CONCLUSIONS
RECOMMENDATIONS FOR FUTURE RESEARCH
ENDNOTES
LIST OF TABLES
LIST OF FIGURES

한국어 초록

This paper documents the development of a fuzzy logic based incident detection model for urban diamond interchanges. Research in incident detection for intersections and arterials is at a very initiaI stage. Existing algorithms are still far from being robust in dealing with the difficulties related with data availability and the multi-dimensional nature of the incident detection problem. The purpose of this study is to develop a new real-time incident detection model for urban diamond interchanges. The development of the algorithm is based on fuzzy logic.
The incident detection model developed through this research is capable of detecting lane-blocking incidents when their effects are manifested by certain patterns of deterioration in traffic conditions and, thereby, adjustments in signal control strategies are required. The model overcomes the boundary condition problem inherent in conventional threshold-based concepts. The model captures system-wide incident effects utilizing multiple measures for more accurate and reliable detection, and serves as a component module of a real-time traffic adaptive diamond interchange control system. The model is designed to be readily scalable and expandable for larger systems of arterial streets.
The prototype incident detection model was applied to an actual diamond interchange to investigate its performance. A simulation study was performed to evaluate the model’s performance in terms of detection rate, false alarm rate, and mean time to detect. The model’s performance was encouraging, and the fuzzy logic based approach to incident detection is promising.

영어 초록

This paper documents the development of a fuzzy logic based incident detection model for urban diamond interchanges. Research in incident detection for intersections and arterials is at a very initiaI stage. Existing algorithms are still far from being robust in dealing with the difficulties related with data availability and the multi-dimensional nature of the incident detection problem. The purpose of this study is to develop a new real-time incident detection model for urban diamond interchanges. The development of the algorithm is based on fuzzy logic. The incident detection model developed through this research is capable of detecting lane-blocking incidents when their effects are manifested by certain patterns of deterioration in traffic conditions and, thereby, adjustments in signal control strategies are required. The model overcomes the boundary condition problem inherent in conventional threshold-based concepts. The model captures system-wide incident effects utilizing multiple measures for more accurate and reliable detection, and serves as a component module of a real-time traffic adaptive diamond interchange control system. The model is designed to be readily scalable and expandable for larger systems of arterial streets. The prototype incident detection model was applied to an actual diamond interchange to investigate its performance. A simulation study was performed to evaluate the model’s performance in terms of detection rate, false alarm rate, and mean time to detect. The model’s performance was encouraging, and the fuzzy logic based approach to incident detection is promising.

참고 자료

없음