A Destination Prediction Network Based on Spatiotemporal Data for Bike-Sharing

Algorithm 2

Destination prediction training algorithm.

Input:construct,,

from candidate set

Output: Learned Destination Prediction Model

1:Initial the parameters in the networks

2:Repeat

3:input into the LSTM and get

4:input into the CNN and get

5:input into the FCNN and get

6:find the best with a cross-entropy loss function

7:Until get the best