Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Investigate methods of using headway as an input to the prediction of dwell times. #74

Closed
scrudden opened this issue Jul 10, 2018 · 5 comments
Closed

Investigate methods of using headway as an input to the prediction of dwell times. #74

scrudden opened this issue Jul 10, 2018 · 5 comments
Assignees
@scrudden
Labels
experimental wip

Comments

@scrudden
Copy link
Member

No description provided.

@scrudden scrudden self-assigned this Jul 10, 2018
@scrudden
Copy link
Member Author

Working on this on branch tc_issue_72.

Trying Recursive least-squares (RLS) from smile (http://haifengl.github.io/smile) to prediction dwell times. The input to this is (headway,dwell time).

@scrudden scrudden mentioned this issue Jul 14, 2018
Merged
@scrudden
Copy link
Member Author

Running test against route 66 MBTA, which is one of their higher frequency routes.

@scrudden
Copy link
Member Author

Based on guidance from @simonberrebi I am trying (headway, log10(dwell time)) as the input to RLS.

@scrudden scrudden added the wip label Aug 26, 2018
@scrudden scrudden mentioned this issue Aug 27, 2018
Closed
@scrudden
Copy link
Member Author

scrudden commented Sep 7, 2018

This shows that there is no bias in this prediction method and the spread of prediction error grows consistently with horizon and is well contained. Based on this I am going to merge the related pull request.

This change will not effect the default prediction method.

I had this run for a number of weeks against MBTA route 66.

image

@scrudden
Copy link
Member Author

scrudden commented Sep 7, 2018

Merged.

@scrudden scrudden closed this as completed Sep 7, 2018
sheldonabrown pushed a commit to sheldonabrown/core that referenced this issue Sep 30, 2022
@carabalb
Merge pull request TheTransitClock#74 from camsys/feature/kumar/ui_bo…
dea3ba3 
…otstrap_implementation

Updated Trip RunTimes Report with the new design utilizing Bootstrap_380
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@scrudden scrudden

Labels
experimental wip
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@scrudden