Noise-Tagging Toolbox

A Python/Matlab toolbox for brain-computer interfaces using code-modulated evoked potentials.

PyNT

The Python noise-tagging toolbox (PyNT) contains custom software to setup a code-modulated evoked response BCI. For instance, it contains routines to create stimulus sequences (i.e., noise-tags) and to analyse and decode code-modulated (visual) evoked potentials. The toolbox is compatible with the Scikit-Learn API. The toolbox can be taken from GitLab here.

import pynt
rcca = pynt.classifiers.rCCA(codes=codes, fs=fs)
rcca.fit(X_trn, y_trn)
yh_tst = rcca.predict(X_tst)

MaNT

The Matlab noise-tagging toolbox (MaNT) contains custom software to setup a code-modulated evoked response BCI. For instance, it contains routines to create stimulus sequences (i.e., noise-tags), to analyse and decode code-modulated (visual) evoked potentials, as well as sophisticated methods for statics and dynamic stopping, optimized code subsets, and optimized code layouts. The toolbox can be taken from GitLab here.

addpath('mant');
classifier = jt_tmc_train(struct('X', X_trn, 'y', y_trn, 'V', codes), cfg);
yh_tst = jt_tmc_apply(classifier, X_tst);

10th International BCI Meeting (June 2023)

Workshop W6 Small Datasets (Wednesday 7th of June)

The pdf file of the presentation (“Efficient decoding of code-modulated evoked responses”) can be found here. The tutorial in this workshops follows the tutorial that can be found in the PyNT library.

Poster 3-C-22 (Friday 9th of June)

The pdf file of the presented poster (“A comparison of stimulus sequences for c-VEP based BCI”) can be found here.

International Work-conference on Artificial Neural Networks (June 2023)

Talk session A.1 Real World Applications of BCI Systems

The pdf file of the presentation (“Effects of stimulus sequences on brain-computer interfaces using code-modulated visual evoked potentials: an offline simulation”) can be found here.

Jordy Thielen
Jordy Thielen
Assistant Professor