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

Web/update files for preview #23

Merged
merged 5 commits into from
Sep 24, 2020
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
395 changes: 372 additions & 23 deletions ai/data_generation.ipynb

Large diffs are not rendered by default.

1,795 changes: 942 additions & 853 deletions web/src/assets/data/hypnogram-openbci-electrophysiologist.csv

Large diffs are not rendered by default.

1,795 changes: 942 additions & 853 deletions web/src/assets/data/hypnogram-openbci-predicted.csv

Large diffs are not rendered by default.

41 changes: 41 additions & 0 deletions web/src/assets/data/readme.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,41 @@
# Sleep Data

This folder holds all static data needed for our visualisations. This data is used in the `Analyze my sleep` page (as the preview example) and in the `Performance` page.

## OpenBCI Data

In order to demonstrate the use of data from the OpenBCI to classify sleep stages, we will use the night of William, predicted by our classifier, as the preview. The spectrogram data is also from the data acquired with the OpenBCI.

We also have the manually labelled hypnogram of William's night, which will be used to illustrate our classifier performances.

The files used are:

- `hypnogram-openbci-predicted.csv`

Predicted hypnogram of William's night

- `hypnogram-openbci-electrophysiologist.csv`

Manually labelled hypnogram of William's night

- `spectrograms-openbci-predicted.json`

Frequencies and power spectrum densities calculated from William's EEG data

## OpenBCI Data

In order to illustrate the bias occured when manually scoring a night of sleep, we have data which allows us to compare two scorers' agreement. The manuel on which both scored is not the same.

The files used are:

- `hypnogram-labelled.csv`

Manually labelled hypnogram of a subject's night by a scorer which participated in making the dataset.

- `hypnogram-electrophysiologist.csv`

Manually labelled hypnogram of a subject's night by an electrophysiologist which we contacted.

- `hypnogram-predicted.csv`

Predicted hypnogram of a subject's night by our classifier
1 change: 1 addition & 0 deletions web/src/assets/data/spectrograms-openbci-predicted.json

Large diffs are not rendered by default.

Loading