Department of Computer Sciences and Automatic Control, Universidad Nacional de Educación a Distancia (UNED), Juan del Rosal 16, 28040 Madrid, Spain.
Sensors (Basel). 2019 May 18;19(10):2302. doi: 10.3390/s19102302.
The activity of the brain can be recorded by means of an electroencephalogram (EEG). An EEG is a multichannel signal related to brain activity. However, EEG presents a wide variety of undesired artefacts. Removal of these artefacts is often done using blind source separation methods (BSS) and mainly those based on Independent Component Analysis (ICA). ICA-based methods are well-accepted in the literature for filtering artefacts and have proved to be satisfactory in most scenarios of interest. Our goal is to develop a generic and unsupervised ICA-based algorithm for EEG artefacts removal.
The proposed algorithm makes use of a new unsupervised artefact detection, ICA and a statistical criterion to automatically select the artefact related independent components (ICs) requiring no human intervention. The algorithm is evaluated using both simulated and real EEG data with artefacts (SEEG and AEEG). A comparison between the proposed unsupervised selection of ICs related to the artefact and other supervised selection is also presented.
A new unsupervised ICA-based algorithm to filter artefacts, where ICs related to each artefact are automatically selected. It can be used in online applications, it preserves most of the original information among the artefacts and removes different types of artefacts.
ICA-based methods for filtering artefacts prevail in the literature. The work in this article is important insofar as it addresses the problem of automatic selection of ICs in ICA-based methods. The selection is unsupervised, avoiding the manual ICs selection or a learning process involved in other methods. Our method is a generic algorithm that allows removing EEG artefacts of various types and, unlike some ICA-based algorithms, it retains most of the original information among the artefacts. Within the algorithm, the artefact detection method implemented does not require human intervention either.
大脑活动可以通过脑电图（EEG）来记录。脑电图是一种与大脑活动相关的多通道信号。然而，脑电图呈现出各种各样的不需要的伪迹。这些伪迹的去除通常是使用盲源分离方法（BSS）完成的，主要是基于独立成分分析（ICA）的方法。基于 ICA 的方法在文献中被广泛接受用于过滤伪迹，并在大多数感兴趣的场景中被证明是令人满意的。我们的目标是开发一种通用的、无监督的基于 ICA 的 EEG 伪迹去除算法。
所提出的算法利用一种新的无监督伪迹检测、ICA 和统计准则，自动选择需要人工干预的与伪迹相关的独立成分（ICs）。该算法使用具有伪迹的模拟和真实 EEG 数据进行评估（SEEG 和 AEEG）。还提出了一种与其他监督选择相比的，针对与伪迹相关的 ICs 的无监督选择的比较。
提出了一种新的基于 ICA 的无监督算法来过滤伪迹，其中与每个伪迹相关的 IC 可以自动选择。它可以用于在线应用，在去除不同类型的伪迹的同时，保留了大部分原始信息。
基于 ICA 的方法在文献中被广泛用于过滤伪迹。本文的工作很重要，因为它解决了 ICA 方法中 IC 自动选择的问题。选择是无监督的，避免了手动选择 IC 或其他方法中涉及的学习过程。我们的方法是一种通用算法，可以去除各种类型的 EEG 伪迹，与一些基于 ICA 的算法不同，它保留了伪迹之间的大部分原始信息。在算法中，实现的伪迹检测方法也不需要人工干预。
