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

Neurofeedbackplugin #885

Open
wants to merge 3 commits into
base: main
Choose a base branch
from

Conversation

simonmarxgut
Copy link

@simonmarxgut simonmarxgut commented Jan 28, 2022

The Neurofeedbackplugin is just for the visualisation for a neurofeedback generated by the Classifier Plugin, which is developed by Jinlong Dong (TU Ilmenau). Currently we are preparing another Plugin for the PR – Bandpower Plugin. Also this plugin could be used as input. But it could be that we split this into two separate plugins, one for continuous and one with discrete data.

There are three different types of output – Classifier, Frequency, and Balloon.

“Classifier” output allows visualisation of the classifications (Integers - Output Classifier) in the form of text or images.
“Frequency” output allows visualisation of different frequency components or frequency bands using sliders. There are some settings for the individual visualisation such as autoscaling.
The “Balloon” output is composed of two images – a background and an object with a white background. Originally, we used a landscape and a balloon, hence the name. The purpose for the white background is that the plugin removes all white pixels and puts the object on the background. Depending on the input of the Plugin, the Balloon starts to rise or sink. So, it is a Neurofeedback based on the principle of reward. Due to copyright concerns, no images are implemented by default.

During the measurement it is possible to change the channel selection, reset the autoscaling or set fixed minimum/maximum.

Best regards from Tyrol
Simon Marxgut

UMIT TIROL

@codecov
Copy link

codecov bot commented Jan 28, 2022

Codecov Report

Merging #885 (8272316) into main (bd31738) will increase coverage by 5.98%.
The diff coverage is n/a.

❗ Current head 8272316 differs from pull request most recent head f83eb34. Consider uploading reports for the commit f83eb34 to get more accurate results

Impacted file tree graph

@@            Coverage Diff             @@
##             main     #885      +/-   ##
==========================================
+ Coverage   30.20%   36.18%   +5.98%     
==========================================
  Files         452      196     -256     
  Lines       39208    11813   -27395     
==========================================
- Hits        11841     4275    -7566     
+ Misses      27367     7538   -19829     
Impacted Files Coverage Δ
libraries/fiff/fiff_types.h 0.00% <0.00%> (-100.00%) ⬇️
libraries/fiff/fiff_info_base.h 0.00% <0.00%> (-100.00%) ⬇️
libraries/mne/mne_sourcespace.h 0.00% <0.00%> (-100.00%) ⬇️
libraries/connectivity/network/network.h 0.00% <0.00%> (-100.00%) ⬇️
libraries/rtprocessing/helpers/filterkernel.h 0.00% <0.00%> (-100.00%) ⬇️
libraries/inverse/hpiFit/hpifit.h 0.00% <0.00%> (-60.00%) ⬇️
libraries/fiff/fiff_stream.h 0.00% <0.00%> (-50.00%) ⬇️
libraries/connectivity/connectivitysettings.h 50.00% <0.00%> (-50.00%) ⬇️
libraries/fiff/fiff_info.h 0.00% <0.00%> (-25.00%) ⬇️
libraries/utils/mnemath.h 0.00% <0.00%> (-16.00%) ⬇️
... and 283 more

@LorenzE
Copy link
Member

LorenzE commented Feb 7, 2022

@simonmarxgut Do you mind explaining the nature of these plugins? What kind of Neurofeedback paradigm did you implement and what kind of data acquisition did you use? Thx!

Also it seems like some of the checks are failing. You can see why by clicking on the checks and filtering through the log.

@simonmarxgut
Copy link
Author

Hey @LorenzE,

yes of course, sorry for the late reply. I had intended to write something but haven’t gotten around to it in the last few days.

The Neurofeedbackplugin is just for the visualisation for a neurofeedback generated by the Classifier Plugin, which is developed by Jinlong Dong (TU Ilmenau). Currently we are preparing another Plugin for the PR – Bandpower Plugin. Also this plugin could be used as input. But it could be that we split this into two separate plugins, one for continuous and one with discrete data.

There are three different types of output – Classifier, Frequency, and Balloon.

“Classifier” output allows visualisation of the classifications (Integers - Output Classifier) in the form of text or images.
“Frequency” output allows visualisation of different frequency components or frequency bands using sliders. There are some settings for the individual visualisation such as autoscaling.
The “Balloon” output is composed of two images – a background and an object with a white background. Originally, we used a landscape and a balloon, hence the name. The purpose for the white background is that the plugin removes all white pixels and puts the object on the background. Depending on the input of the Plugin, the Balloon starts to rise or sink. So, it is a Neurofeedback based on the principle of reward. Due to copyright concerns, no images are implemented by default.

During the measurement it is possible to change the channel selection, reset the autoscaling or set fixed minimum/maximum.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants