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.

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

BNCI2014009 scaling issues? #275

Closed
jsosulski opened this issue Mar 4, 2022 · 1 comment · Fixed by #318
Closed

BNCI2014009 scaling issues? #275

jsosulski opened this issue Mar 4, 2022 · 1 comment · Fixed by #318
Labels

Comments

@jsosulski
Copy link
Collaborator

The overall shape of the ERPs for Target / NonTarget seem to be plausible for this dataset. However, the absolute scalings appear to be off.

grafik

Intuitively, I would guess its off by a factor of 10, but I do not know exactly. This does not matter for most classifiers, but can impact preprocessing, e.g. when you reject epochs where minmax exceeds 100 muV or so.

@sylvchev
Copy link
Member

I think it is ok for most classifiers. Did you see any bad scaling factor in the code?

sylvchev pushed a commit to sylvchev/moabb that referenced this issue Jan 3, 2023
@sylvchev sylvchev linked a pull request Jan 4, 2023 that will close this issue
sylvchev added a commit that referenced this issue Jan 4, 2023
* fix Huebner zip error

* add whats new

* use pathlib and fix issue in script

* fix issue #275

* switch to pathlib and correct Windows path issue #300

Co-authored-by: Sylvain Chevallier <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Projects
None yet
Development

Successfully merging a pull request may close this issue.

2 participants