sstober / openmiir Goto Github PK
View Code? Open in Web Editor NEWa public domain dataset of EEG recordings for music imagery information retrieval
a public domain dataset of EEG recordings for music imagery information retrieval
Hello,
I think due to version compability issues, I am not able to run the first notebook 1 RAW Dataset Preparation 512Hz.ipynb an therefore cannot generate the file OpenMIIR-Perception-512Hz.pklz. In the readme it says that there is also a link (http://www.ling.uni-potsdam.de/mlcog/OpenMIIR/rl2016/data/) to download that file and the one generated by 2 Make HDF5 Dataset.ipynb but that link does not work. Would you mind providing another link with those two files?
Thank you
Hi,
I was able to read the EEG data, bandpass it, and downsample it. I am assuming that the "RAW" data provided by your links is already referenced and that bad channel rejection has already been performed (the notebooks provided do suggest that the data was saved after doing those steps).
Then, I loaded the ICA components and computed the ICA components of the filtered, downsampled data.
Now, I want to split the final array into arrays that are synchronized with the audio stimuli. However, I cannot seem to be able to find the info that maps the EEG signal to the stimuli. The stim channel has some data, but it seems to be about the beats (as opposed to stimulus ID, start time, and end time). I need to know exactly when a specific stimulus starts (and when it ends), for every stimuli.
Thanks in advance for your attention,
Francisco
NOTE: Due to the fact that deepthought has several dependencies I don't want to install, I am using MNE directly for this.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.