Imagined Speech eeg data
收藏资源简介:
• Raw EEG files (.edf): Continuous 64-channel recordings with event markers. • Processed data (.mat): Trial-level epoched data (2.5 s segments), formatted for MATLAB/MNE analysis. • Event logs (.csv): Trial-by-trial metadata, including word label, cue type (visual, auditory, combined, or self-generated), condition, and session number. • All data files, including the raw recordings, can be accessed at the Mendeley Data repository. All files are contained in a main folder called “Imagined Speech eeg data”, organized and named. The final dataset folder is composed of 9 subfolders containing the session raw data, each one corresponding to a different participant. There is an additional folder, containing files obtained after the proposed processing: EEG data in a mat file format. We now proceed to describe the contents of each one of these five files along with the raw data. • Raw data. The raw data file contains the continuous recording of the entire session for all 64 channels. The .edf file contains all the EEG data and the evens with further information about the recording sampling rate, the names of the channels and the recording filters, among other information. The raw events are obtained from the raw data file and contain the tags sent by PC1, synchronized with the recorded signals The raw events are stored in a csv file, where the first column contains the word information, the second has the cue type information, the third column contains the trigger number.
• 原始脑电图(Electroencephalogram, EEG)文件(.edf格式):带有事件标记的连续64通道脑电录制信号。 • 处理后的数据(.mat格式):试次级分段脑电数据(时长2.5秒的信号片段),适配MATLAB与MNE分析环境。 • 事件日志(.csv格式):逐试次元数据,包含词语标签、线索类型(视觉、听觉、联合或自主生成)、实验条件及会话编号。 • 所有数据文件(含原始录制数据)均可在Mendeley Data知识库中获取。所有文件收纳于名为「Imagined Speech eeg data」的主文件夹内,已完成规范化命名与分类整理。最终数据集文件夹包含9个子文件夹,均存储会话原始数据,每个子文件夹对应一名不同被试。另有一个附加文件夹,存储经指定预处理流程得到的文件:即.mat格式的脑电数据。下文将逐一介绍这五类文件及原始录制数据的具体内容。 • 原始数据。原始数据文件存储全64通道的完整会话连续录制信号。.edf文件包含全部脑电数据与事件标记,同时附带录制采样率、通道名称、录制滤波参数等相关元信息。原始事件标记源自原始数据文件,包含由PC1发送的标签,且与录制信号实现同步对齐。原始事件标记存储于.csv格式文件中,其中第一列为词语信息,第二列为线索类型信息,第三列为触发编号。




