A semi-simulated EEG/EOG dataset for the comparison of EOG artifact rejection techniques

This work presents a semi-simulated EEG dataset, where artifact-free EEG signals are manually contaminated with ocular artifacts following the model proposed by [1]. The significant part of this dataset is that it contains the pre-contamination EEG signals, so the brain signals underlying the EOG artifacts are known and thus the performance of every artifact rejection technique can be objectively assessed. The main differences of the proposed dataset compared to others (p.e. see [2,3]) is that it is focused only on EOG artifacts, using a realistic model for the contamination of artifact-free EEGs and not a random procedure. [1] T. Elbert, W. Lutzenberger, B. Rockstroh, N. Birbaumer, Removal of ocular artifacts from the EEG--a biophysical approach to the EOG., Electroencephalogr. Clin. Neurophysiol. 60 (1985) 455–63. http://www.ncbi.nlm.nih.gov/pubmed/2580697 (accessed April 10, 2013). [2] X. Yong, M. Fatourechi, R.K. Ward, G.E. Birch, Automatic artefact removal in a self-paced hybrid brain- computer interface system, J. Neuroeng. Rehabil. 9 (2012) 50. doi:10.1186/1743-0003-9-50. [3] A.K. Abdullah, C.Z. Zhang, A.A.A. Abdullah, S. Lian, Automatic Extraction System for Common Artifacts in EEG Signals Based on Evolutionary Stone’s BSS Algorithm, Math. Probl. Eng. 2014 (2014) 1–25. doi:10.1155/2014/324750.

本研究构建了一套半仿真脑电信号（Electroencephalogram, EEG）数据集，即按照文献[1]提出的模型，通过人工方式向无伪迹脑电信号中混入眼动伪迹（ocular artifacts）。该数据集的核心优势在于其包含了污染前的原始脑电信号，因此眼电伪迹（Electrooculogram, EOG）所对应的脑活动信号为已知量，由此可对各类伪迹去除技术的性能进行客观评估。本数据集与现有同类数据集（如文献[2,3]）的主要差异在于：本数据集仅聚焦眼电伪迹，采用贴合实际的模型对无伪迹脑电信号进行污染处理，而非采用随机污染流程。
[1] T. Elbert, W. Lutzenberger, B. Rockstroh, N. Birbaumer. 从脑电信号中去除眼动伪迹——一种基于生物物理原理的眼电处理方法[J]. 脑电图与临床神经生理学杂志, 1985, 60: 455–463. 来源：https://pubmed.ncbi.nlm.nih.gov/2580697/（2013年4月10日访问）
[2] X. Yong, M. Fatourechi, R.K. Ward, G.E. Birch. 自主式混合型脑机接口（Brain-Computer Interface, BCI）系统中的自动伪迹去除方法[J]. 神经工程与康复杂志, 2012, 9: 50. DOI: 10.1186/1743-0003-9-50
[3] A.K. Abdullah, C.Z. Zhang, A.A.A. Abdullah, S. Lian. 基于进化Stone盲源分离（Blind Source Separation, BSS）算法的脑电信号常见伪迹自动提取系统[J]. 数学工程问题, 2014, 2014: 1–25. DOI: 10.1155/2014/324750

搜集汇总

背景与挑战

背景概述

该数据集是一个半模拟的EEG/EOG数据集，主要用于比较不同的EOG伪迹去除技术。其独特之处在于包含了人工添加眼部伪迹前的纯净EEG信号，使得研究者能够客观评估各种技术的性能。数据集采用现实模型模拟EEG污染，专注于EOG伪迹的研究。