No abstract

This paper presents a new mobile guide system for visually disabled persons. The system utilizes the latest technologies such as data-carriers, mobile communication and portable computers. Data-carriers are embedded at many places in the station such as floors, platforms and walls. Coded data recorded in datacarriers are transferred to users via a reader installed in the cane of the user. The data are interpreted by a portable computer, which generates appropriate guide messages utilizing geographical information and user's personal data stored in it beforehand. Guide messages are finally conveyed orally to the user via a portable speaker.

The ability to obtain passenger flow information in real time is expected to prove useful in application to railway traffic operations. In this report, forecasting of the number of gate passages according to the time of day was attempted using past data from automatic ticket-checking gates, and the number of passages by each origin station was estimated using the number of gate passages. As attributes of daily passage data were apparent, two prediction approaches were found to be applicable to stable data and irregular data. Consequently, the applicability criteria for each approach were clarified. Moreover, accurate forecasting of the number of OD (combination of Origin and Destination) passages was performed using the forecasting model developed.

In order to improve railway diagrams, it is necessary to grasp the flow of railway passengers in detail. However, it is impossible to accomplish this goal only by counting the number of on-board passengers. We have developed a method to estimate the passenger flow based on OD (Origin & Destination) matrix data collected from ticket gates in hundreds of stations and timetables of thousands of trains. By analyzing the estimated results, it is possible to obtain the histograms of the number of passengers aboard each train for each destination, the number of passengers boarding and disembarking at each station, the number of transfer passengers at each station and other relevant factors. We have also developed a proto-type system based on this method assuming that all passengers choose shorter time paths. The estimated number of on-board passengers with this prototype system has a strong correlation with the number reported by train conductors.

No abstract