Algorithm of trip destination estimation based on e-card data – A case study on taichung urban bus

Abstract

Smart card data contains a lot of useful information, so both of urban bus and intercity bus are built up the contactless smart card system in Taiwan. Although smart card data can offer useful information, it’s still limited to how the passengers are being charged. This paper focuses on the estimation of the destination of the passenger who takes the bus twice a day and presents an algorithm to estimate the destination location for each individual boarding of the bus with a smart card. To evaluate the accuracy of destination estimation algorithm, this paper selected Taichung urban bus which uses mileage charges as a case study area. According to the results, the estimated accuracy is 63% with the 600 m tolerance distance (allowable walking distance), after considering 500 m of the value of tolerance distance error the accuracy increases to 90%.