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

Table 3

Weights for nodes in input layer and hidden layer.

Weights		Hidden layer
		Node 1	Node 2	Node 3	Node 4
Input; layer	Neural 1 (0-1 km band population)
	Neural 2 (1-2 km band population)
	Neural 3 (2-3 km band population)
	Neural 4 (3-4 km band population)
	Neural 5 (4-5 km band population)
	Neural 6 (5-6 km band population)
	Neural 7 (road density)	0.0877	0.0819	−0.0822	0.0778
	Neural 8 (number of shuttle bus lines)	0.0996	−0.219	−0.132	0.0238
	Neural 9 (land use mix)	2.313	1.702	−1.369	1.608
	Neural 10 (peak-hour unidirectional train frequency)	0.0132		0.0069	−0.007
	Neural 11 (station type (terminal or not))	−0.294	1.1325	0.869	1.168