A review of classification algorithms for EEG-based brain–computer interfaces: a 10 year update
Обзор алгоритмов классификации для интерфейсов «мозг–компьютер» на основе ЭЭГ: обновление за 10 лет
2018-02-28
SCID: 54.1/wr6h32fk
Discuss with AI
EEG-based brain-computer interfacesRiemannian geometry-based methodsadaptive classifiersclassification algorithmsdeep learning
Figures from the paper
Abstract (AI)
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 ten 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 methods and guidelines on when and how to use them. It also identifies a number of challenges to further advance EEG classification in BCI.
Key Findings
1
Adaptive classifiers generally outperform static classifiers, including when adaptation is performed without labeled data.
2
Riemannian geometry-based methods achieve state-of-the-art performance on multiple BCI problems, while tensor-based methods warrant further investigation.
3
Shrinkage linear discriminant analysis and random forests are particularly useful when only small training samples are available; deep learning has not convincingly surpassed state-of-the-art BCI methods.
4
The 2007–2017 literature review identifies four major categories of newer EEG-based BCI classifiers: adaptive, matrix/tensor, transfer-learning/deep-learning, and miscellaneous methods.
5
Transfer learning can improve BCI classification, but its benefits remain unpredictable across applications.
Research Object
EEG-based brain–computer interfaces and their EEG signal classification algorithms
Research Subject
The performance, applicability, outcomes, and limitations of modern EEG classification algorithms for BCIs, including adaptive, matrix/tensor, transfer-learning, and deep-learning approaches
Publication Details
Publication Date
2018-02-28
Journal
Publisher
ISSN
Cited by
2229
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai7
Book Review: Pattern Recognition and Machine Learning2007
EEGNet: a compact convolutional neural network for EEG-based brain–computer interfaces2018
Deep learning with convolutional neural networks for EEG decoding and visualization2017
A review of classification algorithms for EEG-based brain–computer interfaces2007
Convolutional Neural Networks for P300 Detection with Application to Brain-Computer Interfaces2010
Riemannian geometry for EEG-based brain-computer interfaces; a primer and a review2017
A Deep Learning Scheme for Motor Imagery Classification based on Restricted Boltzmann Machines2016
Cited by7
Current Status, Challenges, and Possible Solutions of EEG-Based Brain-Computer Interface: A Comprehensive Review2020
Progress in Brain Computer Interface: Challenges and Opportunities2021
Past, Present, and Future of EEG-Based BCI Applications2022
Wireless EEG: A survey of systems and studies2022
Implantable brain–computer interface for neuroprosthetic-enabled volitional hand grasp restoration in spinal cord injury2021
Deep Learning Approaches for EEG-Motor Imagery-Based BCIs: Current Models, Generalization Challenges, and Emerging Trends2025
Spike-Based Adaptation of EEG Foundation Models for Calibration Efficient Cross-Subject Brain-Computer Interfaces2026