ivechan/PVCGN

Some questions about predicting the time step.

Closed this issue · 2 comments

custsyz commented

I'm sorry to bother you, but I'm just beginning to get in touch with deep learning. I have some doubts, hope you could reply me in your spare time.
The first question is, how to understand the 15-minute, 30-minute, 45-minute, 60-minute experiment results in your paper? The second question is, does your model support passenger flow forecasting at an interval of five minutes, and if so, what should I do?
Thank you very much again and look forward to your reply~

ivechan commented

Hi @custsyz

  1. 15 minutes indicates the flow of people from 0th to 15th minute.
    30 minutes indicates the flow of people from the 15th minute to the 30th minute, and so on.

  2. It supports I think.
    But it involves another question, whether the 5-minute traffic flow is more statistically significant.

custsyz commented

Thank you very much for your kind heartness on taking time answering my mind of doubt from your busy shedule.I really appreciate it and here I would like to offer you my thankfulness most sincerely.