EEG driver drowsiness dataset (unbalanced)

The dataset contains EEG signals from 11 subjects with labels of alert and drowsy. It can be opened with Matlab. We extracted the data for our own research purpose from another public dataset:<br>Cao, Z., et al., Multi-channel EEG recordings during a sustained-attention driving task. Scientific data, 2019. 6(1): p. 1-8.<br>If you find the dataset useful, please give credits to their works.<br>The full version of the pre-processed dataset from the original author is accessible from:<br>https://figshare.com/articles/dataset/Multi-channel_EEG_recordings_during_a_sustained-attention_driving_task_preprocessed_dataset_/7666055<br><br>This dataset is the unbalanced version of our previous version of dataset:<br>https://figshare.com/articles/dataset/EEG_driver_drowsiness_dataset/14273687<br><br>The difference from the previous version is that the samples have not been balanced for each subject. The details on how the data were extracted are described in our paper (except performing step 3 in page 3):<br>"Jian Cui, Zirui Lan, Yisi Liu, Ruilin Li, Fan Li, Olga Sourina, Wolfgang Müller-Wittig, A Compact and Interpretable Convolutional Neural Network for Cross-Subject Driver Drowsiness Detection from Single-Channel EEG, Methods, 2021, ISSN 1046-2023, https://doi.org/10.1016/j.ymeth.2021.04.017."<br>The data file contains 3 variables and they are EEGsample, substate and subindex.<br><br>"EEGsample" contains 2952 EEG samples of size 20x384 from 11 subjects. Each sample is a 3s EEG data with 128Hz from 30 EEG channels."subindex" is an array of 2952x1. It contains the subject indexes from 1-11 corresponding to each EEG sample."substate" is an array of 2952x1. It contains the labels of the samples. 0 corresponds to the alert state and 1 correspond to the drowsy state.<br>

本数据集包含来自11名受试者的脑电（EEG）信号，样本标签分为清醒与困倦两类。该数据集可通过Matlab打开。本数据集为我们出于自身研究需求，从另一公开数据集提取所得：<br>Cao, Z. 等. 持续注意力驾驶任务中的多通道脑电记录. 《科学数据》, 2019, 6(1): 1-8.<br>若您认为本数据集具有参考价值，请对其原研究成果予以引用。<br><br>原作者发布的预处理版完整数据集可通过以下链接获取：<br>https://figshare.com/articles/dataset/Multi-channel_EEG_recordings_during_a_sustained-attention_driving_task_preprocessed_dataset_/7666055<br><br>本数据集为我们此前发布的数据集版本的非均衡版本，此前版本的数据集链接为：<br>https://figshare.com/articles/dataset/EEG_driver_drowsiness_dataset/14273687<br><br>与此前版本的差异在于，本数据集未针对每名受试者的样本进行均衡处理。关于数据提取的详细细节已在我们的论文中予以说明（无需执行第3页的步骤3）：<br>崔健、蓝梓瑞、刘一思、李瑞麟、李凡、Olga Sourina、Wolfgang Müller-Wittig. 《基于单通道脑电的跨受试者驾驶员困倦检测紧凑型可解释卷积神经网络（Convolutional Neural Network）》, 《方法》, 2021, ISSN 1046-2023, https://doi.org/10.1016/j.ymeth.2021.04.017.<br><br>本数据文件包含3个变量，分别为EEGsample、substate与subindex。<br><br>"EEGsample"包含来自11名受试者的2952个脑电样本，每个样本的维度为20×384。每个样本为时长3秒、采样率128Hz的脑电数据，涵盖30个脑电通道。"subindex"为2952×1的数组，存储了每个脑电样本对应的受试者编号（1至11）。"substate"为2952×1的数组，存储了各样本的标签：0对应清醒状态，1对应困倦状态。

搜集汇总

背景与挑战

背景概述

该数据集包含11名受试者的EEG信号，标记为清醒和困倦状态，用于驾驶员困倦检测研究。数据集包含2952个EEG样本，每个样本为3秒的30通道EEG数据，采样率为128Hz，且样本未进行平衡处理。