• Journal of Korea Spatial Information System Society
• /
• v.10 no.1
• /
• pp.41-49
• /
• 2008

This paper presents a data analysis method for the taxi telematics system which generates a greate deal of location history data. By the record consist of the basic GPS receiver-generated fields, device-added fields such as taxi operation status, and framework-attached fields such as matched link Identifier and position ratio in a link, each taxi can be represented by a state diagram. The transition and the state definition enable us to efficiently extract such information as pick-up time, pick-up distance, dispatch time, and dispatch distance. The analysis result can help to verify the efficiency of a specific taxi dispatch algorithm, while the analysis framework can invite a new challenging service including future traffic estimation, trajectory clustering, and so on.

• Journal of Korean Society of Transportation
• /
• v.26 no.3
• /
• pp.41-51
• /
• 2008

As the local bus service diagram after the bus route reform is studied by variable analysis based on traffic card data and income adjustment data, the characteristic of the local bus system is revealed in Busan Metropolitan city. The relationship between traveling length and traveling time is influenced by traveling velocity. In order to keep a headway within 10 minutes, bus service number per minute should be over 0.1013 vehicles. The traveling time of afternoon is generally longer than that of forenoon. Compared with the bus used by a lot people, the deviation of that used by a few people is larger in the all cases of length, headway, time and velocity. According to the analysis of the relationship among card trip number, average income and transfer rate, the relationship between card trip number and average income is expressed as linear function in the general bus and as exponential function in the high-grade & rapid bus. The 1% increase of transfer rate is equal to 6.3 trip/vehicle/day decrease and 4.9 trip/vehicle/day decrease in two bus types respectively. The four effective variables are defined by the discriminant analysis between the profitable routes and the unprofitable; According to discriminant size, bus service number per km, bus via suburb, subway meeting number, bus via university. In order to increase the income when the minibus will be included among public transit transfer system in 2008, it should be necessary to settle the bus network and revitalize the public transit better. In order to decrease the cost, it should be necessary to reorganize the hierarchy between the local bus and the minibus better.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.19 no.1
• /
• pp.32-43
• /
• 2020

The transfer time is an important factor in establishing public transportation planning and policy. Therefore, in this study, the influencing factors of the transfer time for transit users were identified using smart card data, and the estimation results for the transfer time using the deep learning method such as deep neural network models were compared with traditional regression models. First, the intervals and the distance to the bus stop had positive effects on the subway-to-bus transfer time, and the number of bus routes had a negative effect. This also showed that the transfer time is affected by the area in which the subway station exists. Based on the influencing factors of the transfer time, the deep learning models were developed and their estimation results were compared with the regression model. For model performance, the deep learning models were better than those of the regression models. These results can be used as basic data for transfer policies such as the differential application of transit allowance times according to region.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.29 no.4D
• /
• pp.467-472
• /
• 2009

Even if Seoul City administration improved its public transportation service, transportation model share in seoul has not been increased. Subway user is also decreasing. Therefore, policy transition into TOD(Transit Oriented Development) should be applied in oder to enhance subway modal share. This paper develops a influencing model by using variables of transportation demand and supply. In addition, it provides major influencing factors for users in subway station area and level of transportation supply based on the analysis results. The results show that: first, cluster analysis presents that traffic pattern is proved to be different according to land use characteristics(residence, non-residence); second, main transportation variables such as transferring distance, the number of bus stop, the number of short distant bus lines, and the number of bicycle are more supplied in residential area compared to non-residential areas; third, the number of lines, bus dispatching interval, operating time, and distance between subway stations are more supplied in non-residential areas than residential areas. All in all, the results will be useful for providing priority of considerations in case of decision-making on public transportation policy in subway station area.