Inria, LaBRI (CNRS/Univ. Bordeaux /INP), Talence, France. RIKEN Brain Science Insitute, Wakoshi, Japan.
J Neural Eng. 2018 Jun;15(3):031005. doi: 10.1088/1741-2552/aab2f2. Epub 2018 Feb 28.
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.
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.
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.
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.
大多数当前基于脑电图（EEG）的脑机接口（BCI）都是基于机器学习算法。正如我们在 2007 年的综述论文中所述，该领域使用了大量不同类型的分类器。现在，在该综述发表大约十年后，已经开发和测试了许多新的算法来对 BCI 中的 EEG 信号进行分类。因此，现在及时对用于 BCI 的 EEG 分类算法进行更新的综述。
我们调查了 2007 年至 2017 年的 BCI 和机器学习文献，以确定已研究用于设计 BCI 的新分类方法。我们综合了这些研究，以呈现这些算法，报告它们如何用于 BCI，结果如何，并确定它们的优缺点。
我们发现，最近设计的基于 EEG 的 BCI 的分类算法可分为四大类：自适应分类器、矩阵和张量分类器、迁移学习和深度学习，以及其他一些分类器。其中，自适应分类器通常优于静态分类器，即使没有无监督自适应也是如此。迁移学习也可能证明是有用的，尽管迁移学习的好处仍然不可预测。基于黎曼几何的方法在多个 BCI 问题上达到了最新的性能水平，值得更深入地探索，以及基于张量的方法。收缩线性判别分析和随机森林在小训练样本设置中也特别有用。另一方面，深度学习方法尚未在 BCI 方法中显示出令人信服的改进。
本文全面概述了用于基于 EEG 的 BCI 的现代分类算法，介绍了这些方法的原理以及何时以及如何使用它们的指南。它还确定了进一步推进 EEG 分类在 BCI 中的一些挑战。
