Since the statistical properties (mean and covariance) of the subway passenger data are nearly periodic with a distinct weekly cycle, we assume that the data fall under the category of cyclostationary random variables [12].
The replacement will cost $5 million and is being done as part of a separate project to build out the subway's data network.
The CSEOF technique is applied to Seoul subway passenger data for Subway Line #2 for the purpose of analyzing the space time variability of the subway passengers.
Using the Hong Kong subway incident data from 2005 and 2009, a tree comprising 10 terminal nodes is selected to predict subway incident delays in a case study.
Thus, a space time analysis technique called Cyclostationary Empirical Orthogonal Function (CSEOF) Analysis [14 16] is employed to identify eigenfunctions of subway passenger data.
In the present study, we are specifically interested in identifying space time eigenfunctions of the subway passenger data, i.e., distinct modes of variability of subway passengers as a function of subway stations and times of the week.
To answer the first question, a GIS-based model was used to analyze subway ridership data to estimate changes in rush hour commuters at Tongzhou's subway stations under three scenarios.
However, a scenario model based on the analysis of subway ridership data suggests that the relocation could overwhelm Tongzhou's existing subway infrastructure unless it is substantially expanded or a large proportion of the relocated workers move their residences to Tongzhou.
Subway passenger data T r, t) is decomposed in terms of eigenfunctions as Tleft( {r,t} right) = mathop sum limits_{n} B_{n} left( {r,t} right)T_{n} left( t right), (1 where the eigenfunctions, B n (r, t), are called cyclostationary loading vectors (CSLV) and the corresponding amplitude, T n (t), are called principal component (PC) time series.
In EOF analysis, subway passenger data is decomposed in the form Tleft( {r,t} right) = mathop sum limits_{n} phi_{n} left( r right P_{n} left( t right), (6 where ϕ n (r) are EOF loading vectors and P n (t) are corresponding PC time series.
Half of the passengers on the M34 and M42 buses are transferring from the subway, according to data provided by Mr. Bloomberg's campaign.
