Examples#

These examples demonstrate how to use MOABB, and its main concepts the dataset, paradigm and evaluation. Those examples are using only a small number of subjects, and a small number of sessions, to keep the execution time short. In practice, you should use all the subjects and sessions available in the dataset.

Change Download Directory

Change Download Directory

Change Download Directory
Benchmarking with MOABB showing the CO2 footprint

Benchmarking with MOABB showing the CO2 footprint

Benchmarking with MOABB showing the CO2 footprint
Load Model (Scikit, Pytorch, Keras) with MOABB

Load Model (Scikit, Pytorch, Keras) with MOABB

Load Model (Scikit, Pytorch, Keras) with MOABB
Convert a MOABB dataset to BIDS

Convert a MOABB dataset to BIDS

Convert a MOABB dataset to BIDS
Spectral analysis of the trials

Spectral analysis of the trials

Spectral analysis of the trials
Example of P300 classification with different epoch size.

sphx_glr_auto_examples_noplot_vr_pc_p300_different_epoch_size.py

Example of P300 classification with different epoch size.
Hinss2021 classification example

Hinss2021 classification example

Hinss2021 classification example
Examples of how to use MOABB to benchmark pipelines.

Examples of how to use MOABB to benchmark pipelines.

Examples of how to use MOABB to benchmark pipelines.
Benchmarking on MOABB with Tensorflow deep net architectures

Benchmarking on MOABB with Tensorflow deep net architectures

Benchmarking on MOABB with Tensorflow deep net architectures
Benchmarking on MOABB with Braindecode (PyTorch) deep net architectures

Benchmarking on MOABB with Braindecode (PyTorch) deep net architectures

Benchmarking on MOABB with Braindecode (PyTorch) deep net architectures
Benchmarking with MOABB with Grid Search

Benchmarking with MOABB with Grid Search

Benchmarking with MOABB with Grid Search
Cross-session motor imagery with deep learning EEGNet v4 model

Cross-session motor imagery with deep learning EEGNet v4 model

Cross-session motor imagery with deep learning EEGNet v4 model
Cross-Session Motor Imagery

Cross-Session Motor Imagery

Cross-Session Motor Imagery
Cross-Session on Multiple Datasets

Cross-Session on Multiple Datasets

Cross-Session on Multiple Datasets
Cross-Subject SSVEP

Cross-Subject SSVEP

Cross-Subject SSVEP
Cache on disk intermediate data processing states

Cache on disk intermediate data processing states

Cache on disk intermediate data processing states
Explore Paradigm Object

Explore Paradigm Object

Explore Paradigm Object
Fixed interval windows processing

Fixed interval windows processing

Fixed interval windows processing
Within Session P300

Within Session P300

Within Session P300
Within Session SSVEP

Within Session SSVEP

Within Session SSVEP

Advanced examples#

These examples show various advanced topics:

  • using scikit-learn pipeline with MNE inputs

  • selecting electrodes or resampling signal

  • using filterbank approach in motor imagery

  • apply statistics for meta-analysis

  • using a gridsearch in within-subject decoding

FilterBank CSP versus CSP

FilterBank CSP versus CSP

FilterBank CSP versus CSP
GridSearch within a session

GridSearch within a session

GridSearch within a session
MNE Epochs-based pipelines

MNE Epochs-based pipelines

MNE Epochs-based pipelines
Select Electrodes and Resampling

Select Electrodes and Resampling

Select Electrodes and Resampling
Statistical Analysis

Statistical Analysis

Statistical Analysis

External examples#

You need to install external dependencies to run these examples. These consist mostly of various classifier implementations. When using poetry, you can use

poetry install --extras external

Within Session P300 with Learning Curve

Within Session P300 with Learning Curve

Within Session P300 with Learning Curve

Evaluation with learning curve#

These examples demonstrate how to make evaluations using only a subset of available example. For example, if you consider a dataset with 100 trials for each class, you could evaluate several pipelines by using only a fraction of these trials. To ensure the robustness of the results, you need to specify the number of permutations. If you use 10 trials per class and 20 permutations, each pipeline will be evaluated on a subset of 10 trials chosen randomly, that will be repeated 20 times with different trial subsets.

Within Session Motor Imagery with Learning Curve

Within Session Motor Imagery with Learning Curve

Within Session Motor Imagery with Learning Curve
Within Session P300 with Learning Curve

Within Session P300 with Learning Curve

Within Session P300 with Learning Curve

Gallery generated by Sphinx-Gallery