Abstract
In recent years, Freeway Electronic Toll Collection plays leading role in the development of Intelligent Transportation System (ITS) in Taiwan. In addition to significantly improving traffic efficiency and driving quality of the vehicle, it reduces maintenance and management costs of Manual Toll Collection. Currently, Taiwan ETC is third generation system. For the effect and quality improvement in service of Electronic Toll Collection, there are not only a gradual increase in public satisfaction but also the utilization rate of ETC is more than 94%. We can control Real-Time traffic information and get more convenient from data collection for the technological progress of Electronic Toll System. ETC has an excellent reputation all over the world because its successful detection rate is rising to over 99.9%. Accordingly, if we can find the identify factors of failure detection and improve the system, it will make Taiwan eTag technology better. This study aims to extract information from the driving record of eTag users via association rules. The purpose of this study is to provide a systematic approach and develop a data mining framework based on association rule to derive useful patterns and rules for our target variable - detection result. Furthermore, this study provides accuracy analysis in rule validation and search for important association rules for the business organization. We expect that the implementation of this study can serve as a reference for the freeway electronic toll system for improvement.