brainhack-school2020 / alex-a14_brainhack2020 Goto Github PK

Hi @vborghe
Do you think I will need to use fmriprep or can I do everything with Nilearn?

Should I start with Nilearn and see how that goes and then decide if I need to do any preprocessing?

Thanks!

We need dataset for Academic project. It would be better if we get the dataset. Can you please help us?

HI @surchs
You mentioned in your talk that you can select specific files using AWS. If I'm using a dataset that includes both EEG and fMRI data, could I easily extract the fMRI data while still preserving the BIDS structure?
It's in the typical BIDS format so I would want to extract just the func folder (maybe anat too) from every participant.
Now that I think about it, the pathing here seems like a pain. Because they're all in the same subject folder I'd imagine even if I could extract just the functional data, I would lose the subject folder above it?

Not a serious issue, it's only 15GB, but just wondering if it's doable

Hi Alex! Your project seems cool, and this is more a comment than an issue ;) there are actually some research dealing with music Recognition and machine learning, here some references if you want some inspirations!

https://www.cell.com/neuron/fulltext/S0896-6273(18)30250-2?_returnURL=https%3A%2F%2Flinkinghub.elsevier.com%2Fretrieve%2Fpii%2FS0896627318302502%3Fshowall%3Dtrue

https://www.nature.com/articles/s41598-018-20732-3

Good Luck in your project!

Hi @vborghe
do you think a sample size of 21 is too small to do any meaningful machine learning analyses across participants?
In the music data I'm looking at now, the only behavioural data are affective response to music, and a music preferences questionnaire.

The affective response was recorded continuously as participants listened to pieces of music in the scanner (i.e. they indicated how they were feeling by moving a joystick). So there's more data for this.

For the music preferences questionnaire, participants rate their preference for variance genres of music. So if I were to focus on one specific genre, I would only have one rating for each participant (similar to if I was predicting age I guess). Is 21 too few subjects for this?
Thanks for any input!