vlawhern / arl-eegmodels

This is the Army Research Laboratory (ARL) EEGModels Project: A Collection of Convolutional Neural Network (CNN) models for EEG signal classification, using Keras and Tensorflow
Other
1.17k stars 287 forks source link

Request : FBCSP code #10

Closed mouadriyad closed 5 years ago

mouadriyad commented 5 years ago

Hi,

Could you share with us your FBCSP implementation?

mouadriyad commented 5 years ago

Hi could you share with us your implementation of the FBCSP because mine (based on mne and SKlearn) get always bad accuracy.

vlawhern commented 5 years ago

My original FBCSP code was written in MATLAB and would require a lot of rewriting to make it usable more generally. Perhaps you can try to use this package here, it seems to be pretty well-documented:

https://github.com/MultiScale-BCI/IV-2a

mouadriyad commented 5 years ago

I couldn't create a valid model with same performances but I solved it.

robintibor commented 5 years ago

In shameless self promotion you could also have a look at our fbcsp implementation :D https://github.com/TNTLFreiburg/fbcsp as used in https://onlinelibrary.wiley.com/doi/full/10.1002/hbm.23730

mouadriyad commented 5 years ago

In shameless self promotion you could also have a look at our fbcsp implementation :D https://github.com/TNTLFreiburg/fbcsp as used in https://onlinelibrary.wiley.com/doi/full/10.1002/hbm.23730

I will be glad to check your implementation, every help is welcome