Research Article

Forecasting Method for Urban Rail Transit Ridership at Station Level Using Back Propagation Neural Network

Table 2

Correlation analyses of nonpopulation variables and ridership.

Correlation coefficientRoad densityNumber of shuttle bus linesLand-use
Mix
Peak-hour unidirectional train frequencyNumber of lines through stationNumber of park and ride facilitiesStation typeDistance To CBD

Ridership0.1010.04

: , generally significant.