Hi everyone,
I would like ask a question about data analysis. I have two data sets about buses in an urban transport system.
Timestamp and Speed with GPS Coordinates.
How can I mine this data based on spatial coordinates and speed and use this to make short-term and long term-predictions about location, speed as well as using these as parameters to identify patterns for traffic bottlenecks, congestion etc before time.
I have attached two images to show an example of the data sets. Suggest me a tool as well if it can help.
Regards
Nauman.
Dear Mr. Khan,
This is a deep question, because data mining is a whole subject in itself. One very popular tool is the R language, and I would suggest the plyr package to perform operations on datasets. How to do it requires a bit more craft, more than would be advisable to explain on this forum.
Are those data publicly available, by the way? It would be interesting to have a look at them!
Cheers,
Fernando
Dear Fernando,
Thanks for your response.
No they are not publicly available unfortunately. Can you please advise further on what you have said? Any reference would be great.
Regards
Dear Mr Khan,
R is a very popular mathematics/statistics environment. It is very oriented towards data manipulation, both in its syntax and in the collection of available packages. The default distribution includes lots of libraries, and more can be found on the web, mainly in CRAN.
What particular analyses you should perform on your data is a very lengthy subject, and difficult to discuss here.
Good luck!
Cheers,
Fernando
http://www.r-project.org/
- Badges
- Science topic
- Similar topics
- Computer Science
- Data Mining