search

ziyujia / MSTGCN

Multi-View Spatial-Temporal Graph Convolutional Networks with Domain Generalization for Sleep Stage Classification.
59 stars 9 forks source link

Prepare MASS-SS3 scripts #5

Open Google0007 opened 2 years ago

Google0007 commented 2 years ago

Hello， I am very interested in your project, I wonder if it is convenient for you to share the script for converting the ’Base.edf‘ and 'PSG.edf' format to the ‘npy’ format to prepare MASS-SS3 data in the first step? And I would like to know why the ISRUC-S3 data in the code only uses 10 channels, not the other two EMG channels？ Best wishes~ Looking forward to your reply, Thanks in advance!

NingXJ1999 commented 2 years ago

For the preprocessing of the MASS-SS3 dataset, please refer to https://github.com/ziyujia/GraphSleepNet/issues/2.

For the ISRUC-S3 dataset, we focus on the signals from the head, so data from the two leg-EMG channels are not used. Of course, for the baselines, the EMG channel was not used. Theoretically, these two channels can also be used, and they may also have some features that contribute to sleep stage classification.