# chb-mit dataset montage **URL:** \ **Category:** Support & Discussions\ **Tags:** preprocessing, ica\ **Created:** [April 22, 2024, 11:38am UTC](https://mne.discourse.group/t/chb-mit-dataset-montage/8681 "2024-04-22T11:38:20Z")\ **Posts on this page:** 8\ **Page:** 1
**Author:** ![frankloyld-na](https://yyz2.discourse-cdn.com/free1/user_avatar/mne.discourse.group/frankloyld-na/32/3605_2.png) [@frankloyld-na](https://mne.discourse.group/u/frankloyld-na)\ **Post date:** [April 22, 2024, 11:38am UTC](https://mne.discourse.group/t/chb-mit-dataset-montage/8681/1 "2024-04-22T11:38:21Z")
Hi, I’m trying to run ICA on chb-mit dataset, but the MNE seems like didn’t have the bipolar montage.When I try to use the ica.find\_bads\_muscle command, I get an error:`WARNING:root:Did not find any electrode locations` I then tried adding a montage to my data but it seems that mne does not have a montage for the bipolar export. My code: > import mne > > specified\_channels = [“FP1-F7”, “F7-T7”, “T7-P7”, “P7-O1”, “FP1-F3”, “F3-C3”, “C3-P3”, “P3-O1”, “FP2-F4”, “F4-C4”, “C4-P4”, “P4-O2”, “FP2-F8”, “F8-T8”, “T8-P8-0”, “P8-O2”, “FZ-CZ”, “CZ-PZ”] > data\_path = “…/…/data/Sub01/Original\_data/chb01\_03.edf” > raw = mne.io.read\_raw\_edf(data\_path, preload=True) > raw.pick\_channels(specified\_channels) > > raw.pick(picks=“eeg”, exclude=“bads”) > raw.load\_data() > raw.filter(l\_freq=1.0, h\_freq=None) > > ica = mne.preprocessing.ICA( > n\_components=18, method=“picard”, max\_iter=“auto”, random\_state=97 > ) > ica.fit(raw) > > muscle\_idx\_auto, scores = ica.find\_bads\_muscle(raw) > ica.plot\_scores(scores, exclude=muscle\_idx\_auto) > print( > f"Automatically found muscle artifact ICA components: {muscle\_idx\_auto}" > ) ---
**Author:** ![richard](https://yyz2.discourse-cdn.com/free1/user_avatar/mne.discourse.group/richard/32/15_2.png) [@richard](https://mne.discourse.group/u/richard)\ **Post date:** [April 22, 2024, 4:23pm UTC](https://mne.discourse.group/t/chb-mit-dataset-montage/8681/2 "2024-04-22T16:23:23Z")
Hello, this is to be expected, as a bipolar reference consists of two electrodes, hence it’s unclear which location belongs to the resulting value. What you could do is drop the “-X” part from the channel names and set a template montage; this way you would be able to visualize half the electrodes… 🤔 Best wishes, Richard ---
**Author:** ![frankloyld-na](https://yyz2.discourse-cdn.com/free1/user_avatar/mne.discourse.group/frankloyld-na/32/3605_2.png) [@frankloyld-na](https://mne.discourse.group/u/frankloyld-na)\ **Post date:** [April 23, 2024, 4:09am UTC](https://mne.discourse.group/t/chb-mit-dataset-montage/8681/3 "2024-04-23T04:09:01Z")
Thanks！ I have one more question. If I drop the “-X” part from the channel names and set a template montage, and then apply ICA to the data, could this approach potentially affect the effectiveness of the ICA? ---
**Author:** ![richard](https://yyz2.discourse-cdn.com/free1/user_avatar/mne.discourse.group/richard/32/15_2.png) [@richard](https://mne.discourse.group/u/richard)\ **Post date:** [April 23, 2024, 3:56pm UTC](https://mne.discourse.group/t/chb-mit-dataset-montage/8681/4 "2024-04-23T15:56:18Z")
I’m sorry, I don’t have experience with this kind of data. Maybe @cbrnr can share some insights? Good luck, Richard ---
**Author:** ![cbrnr](https://yyz2.discourse-cdn.com/free1/user_avatar/mne.discourse.group/cbrnr/32/1409_2.png) [@cbrnr](https://mne.discourse.group/u/cbrnr)\ **Post date:** [April 23, 2024, 6:08pm UTC](https://mne.discourse.group/t/chb-mit-dataset-montage/8681/5 "2024-04-23T18:08:56Z")
ICA is completely agnostic to channel locations, so changing labels and/or the montage won’t affect its result at all. ---
**Author:** ![frankloyld-na](https://yyz2.discourse-cdn.com/free1/user_avatar/mne.discourse.group/frankloyld-na/32/3605_2.png) [@frankloyld-na](https://mne.discourse.group/u/frankloyld-na)\ **Post date:** [April 25, 2024, 4:55am UTC](https://mne.discourse.group/t/chb-mit-dataset-montage/8681/6 "2024-04-25T04:55:41Z")
Thanks for your help Richard！ ---
**Author:** ![frankloyld-na](https://yyz2.discourse-cdn.com/free1/user_avatar/mne.discourse.group/frankloyld-na/32/3605_2.png) [@frankloyld-na](https://mne.discourse.group/u/frankloyld-na)\ **Post date:** [April 25, 2024, 4:56am UTC](https://mne.discourse.group/t/chb-mit-dataset-montage/8681/7 "2024-04-25T04:56:14Z")
Thanks for your help！ Now I undersatnd! ---
**Author:** ![system](https://global.discourse-cdn.com/free1/uploads/mne/original/1X/85cc6bd2b69cb698a166dc6d880fb550510d0144.jpeg) [@system](https://mne.discourse.group/u/system)\ **Post date:** [May 2, 2024, 4:56am UTC](https://mne.discourse.group/t/chb-mit-dataset-montage/8681/8 "2024-05-02T04:56:30Z")
This topic was automatically closed 7 days after the last reply. New replies are no longer allowed.