Question about the ISRUC-SLEEP dataset

💬 Support & Discussions
1

:question: If you have a question or issue with MNE-Python, please include the following info:

  • MNE version: 1.5.1
  • operating system: Windows 11
  • Python 9

I’m going to do some work on sleep stages and I’m using the ISRUC-SLEEP dataset. Specifically data from Subgroup_3.

Additionally, I use the mne-python library to load the *.rec data file (transforming the root to *.edf).

Loads the data perfectly. But I can’t distinguish the channel types. All channels are assumed to be EEG. Although on the PSG I have EEG, EOG and EMG channels, when I try to use the type selection functions, it does not distinguish the type of channels and assumes that they are all EEG. Therefore I cannot apply other detection and resolution functions for EOG, EMG artifacts…

I would like to know if this is logical or I am doing something wrong.

Ex.
raw = mne.io.read_raw_edf(path, preload = True)
mne.pick_types(raw.info,eog = True)
–output–> array(, typed=int32)

2

Hello,

You can correct badly set channel types with the set_channel_types method:
https://mne.tools/stable/generated/mne.io.Raw.html#mne.io.Raw.set_channel_types

Mathieu

1 Like