A Review of Classification Algorithms for EEG-based Brain-Computer Interfaces: A 10-year Update

Fabien Lotte 1, 2 Laurent Bougrain 2, 3 Andrzej Cichocki 4, 2, 5 Maureen Clerc 6 Marco Congedo 7 Alain Rakotomamonjy 8 Florian Yger 9, 10
1 Potioc - Popular interaction with 3d content
LaBRI - Laboratoire Bordelais de Recherche en Informatique, Inria Bordeaux - Sud-Ouest
3 NEUROSYS - Analysis and modeling of neural systems by a system neuroscience approach
Inria Nancy - Grand Est, LORIA - AIS - Department of Complex Systems, Artificial Intelligence & Robotics
6 ATHENA - Computational Imaging of the Central Nervous System
CRISAM - Inria Sophia Antipolis - Méditerranée
GIPSA-DIS - Département Images et Signal
8 DocApp - LITIS - Equipe Apprentissage
LITIS - Laboratoire d'Informatique, de Traitement de l'Information et des Systèmes
Abstract : Objective: Most current Electroencephalography (EEG)-based Brain-Computer Interfaces (BCIs) are based on machine learning algorithms. There is a large diversity of classifier types that are used in this field, as described in our 2007 review paper. Now, approximately 10 years after this review publication, many new algorithms have been developed and tested to classify EEG signals in BCIs. The time is therefore ripe for an updated review of EEG classification algorithms for BCIs. Approach: We surveyed the BCI and machine learning literature from 2007 to 2017 to identify the new classification approaches that have been investigated to design BCIs. We synthesize these studies in order to present such algorithms, to report how they were used for BCIs, what were the outcomes, and to identify their pros and cons. Main results: We found that the recently designed classification algorithms for EEG-based BCIs can be divided into four main categories: adaptive classifiers, matrix and tensor classifiers, transfer learning and deep learning, plus a few other miscellaneous classifiers. Among these, adaptive classifiers were demonstrated to be generally superior to static ones, even with unsupervised adaptation. Transfer learning can also prove useful although the benefits of transfer learning remain unpredictable. Riemannian geometry-based methods have reached state-of-the-art performances on multiple BCI problems and deserve to be explored more thoroughly, along with tensor-based methods. Shrinkage linear discriminant analysis and random forests also appear particularly useful for small training samples settings. On the other hand, deep learning methods have not yet shown convincing improvement over state-of-the-art BCI methods. Significance: This paper provides a comprehensive overview of the modern classification algorithms used in EEG-based BCIs, presents the principles of these Review of Classification Algorithms for EEG-based BCI 2 methods and guidelines on when and how to use them. It also identifies a number of challenges to further advance EEG classification in BCI.
Complete list of metadatas

Cited literature [120 references]  Display  Hide  Download

Contributor : Fabien Lotte <>
Submitted on : Saturday, July 21, 2018 - 11:34:26 PM
Last modification on : Thursday, May 9, 2019 - 4:16:17 PM
Long-term archiving on : Monday, October 22, 2018 - 1:09:44 PM


Files produced by the author(s)



Fabien Lotte, Laurent Bougrain, Andrzej Cichocki, Maureen Clerc, Marco Congedo, et al.. A Review of Classification Algorithms for EEG-based Brain-Computer Interfaces: A 10-year Update. Journal of Neural Engineering, IOP Publishing, 2018, pp.55. ⟨10.1088/1741-2552/aab2f2⟩. ⟨hal-01846433⟩



Record views


Files downloads