Search

Copyright of Journal of Railway Science & Engineering is the property of Journal of Railway Science & Engineering Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

In order to improve the accuracy and efficiency of customer churn prediction of railway scattered freight, according to the loss characteristics of railway scattered freight customers, this paper proposed a customer churn identification method based on CDL model. On this basis, facing the problem of big data, it proposed a C4. 5 decision tree customer churn prediction model based on Hadoop parallel framework. Simulation results show that the model has good accuracy and predictive ability, and as the number of samples increases, obviously improves the efficiency of Hadoop parallel framework, and doesn’t affect the accuracy and prediction ability of churn prediction model. [ABSTRACT FROM AUTHOR]

To further resolve the problems that were brought by the existing research tools of complex system brittleness theory, such as system state describe difficulties or too critical constraint conditions about system boundary, this paper introduced colored Petri nets into the research on complex system brittleness measurement. The colored Petri nets,its simulation tool CPN Tools and the existing advanced state space tools were helpful to reduce the system complexity in modeling and quantification. This paper brought forward complex system brittleness measurement index,and gave the programming workflow. Lastly a numerical example illustrates that the node brittleness propagation process and its influence range in state space can reflect the system brittleness. [ABSTRACT FROM AUTHOR]

Regard passenger crowding caused by interruptions of urban rail transit network, this paper developed a quantitative framework for assessing vulnerability of urban rail transit network. The framework utilized dynamic transit assignment to describe the time-dependent distribution of passengers in the system and used generalized travel cost growth as the indicator of vulnerability of urban rail transit network. Stations and time period of access restriction control could be determined by the waiting passenger amount in stations. It performed simulation experiments to examine the effectiveness of this approach using data from Beijing Metro. The simulation test results show that this proposed quantitative framework is able to describe the time-dependent passengers crowding situation after interruptions and can serve as data and decision support for emergency passenger organization plan. [ABSTRACT FROM AUTHOR]