GPS - Simulation Data

Questions, answers, discussions related to IEEE ICDM Contest

GPS - Simulation Data

Postby amrkabardy » Sun Jul 11, 2010 9:11 am


The training and test data represents 500 hours of simulation divided into cycles of 10 hours. Does these 10 hours represent traffic simulation of the same period on different days? And does they cover the whole week or weekends are dropped for example?
In other words, can the information of these different 10 hours cycle present information for different traffic patterns of everyday on same period? Or they are completely un-correlated?!!

Posts: 4
Joined: Wed Jun 30, 2010 6:05 pm

Re: GPS - Simulation Data

Postby Marcin » Tue Jul 13, 2010 11:16 am

Different 10-hour cycles are completely uncorrelated. They're fully independent, without any dependencies between neighboring cycles. Simulation procedure was the same in every cycle, except differences in simulation parameters, which were picked randomly, separately for each cycle (but in the same way, i.e. from the same distribution).
Posts: 115
Joined: Fri Oct 09, 2009 6:45 pm

Return to IEEE ICDM Contest: Road Traffic Prediction for Intelligent GPS Navigation

Who is online

Users browsing this forum: No registered users and 1 guest