moabb.datasets.Liu2024#

class moabb.datasets.Liu2024(break_events=False, instr_events=False, subjects=None, sessions=None, *, return_all_modalities=False, **kwargs)[source]#

Bases: BaseDataset

[source]

Dataset Snapshot

Liu2024

EEG motor imagery dataset from 50 acute stroke patients performing left- and right-handed hand-grip imagination tasks. First open dataset addressing left- and right-handed motor imagery in acute stroke patients.

Motor Imagery, 2 classes (left_hand vs right_hand)

AuthorsHaijie Liu, Penghu Wei, Haochong Wang, Xiaodong Lv, Wei Duan, Meijie Li, Yan Zhao, Qingmei Wang, Xinyuan Chen, Gaige Shi, Bo Han, Junwei Hao

🇨🇳 Xuanwu Hospital Capital Medical University, CN·2024·haojunwei@vip.163.com

Motor Imagery Code: Liu2024 50 subjects 1 session 29 ch 500 Hz 2 classes 8.0 s trials CC BY 4.0

Class Labels: left_hand, right_hand

Read Paper Compare Similar Report Issue

Overview

Dataset from the study on motor imagery

Dataset description This dataset includes data from 50 acute stroke patients (the time after stroke ranges from 1 day to 30 days) admitted to the stroke unit of Xuanwu Hospital of Capital Medical University. The patients included 39 males (78%) and 11 females (22%), aged between 31 and 77 years, with an average age of 56.70 years (SD = 10.57) Before the start of the experiment, the subject sat in a chair in a position as comfortable as possible with an EEG cap placed on their head; subjects were positioned approximately 80 cm away from a computer screen in front of them. The computer played audio instructions to the patient about the procedure. Each experiment lasted approximately 20 minutes, including preparation time and approximately 10 minutes of signal recording. Before the start of the MI experiment, the patients opened their eyes and closed their eyes for 1 minute each. The MI experiment was divided into 40 trials, and each trial took 8 seconds, which consisted of three stages (instruction, MI and break). In the instruction stage, patients were prompted to imagine grasping a spherical object with the left- or right-hand. In the MI stage, participants imagined performing this action, a video of gripping motion is played on the computer, which leads the patient imagine grabbing the ball. This video stays playing for 4 s. Patients only imagine one hand movement.In the break stage, participants were allowed to relax and rest. The MI experiments alternated between the left- and right-hand, and the patients moved onto the next stage of the experiment according to the instructions.

The EEG data were collected through a wireless multichannel EEG acquisition system (ZhenTec NT1, Xi’an ZhenTec Intelligence Technology Co., Ltd., China). The system includes an EEG cap, an EEG acquisition amplifier, a data receiver and host computer software. The EEG cap had electrodes placed according to the international 10-10 system, including 29 EEG recording electrodes and 2 electrooculography (EOG) electrodes. The reference electrode located at CPz position and the grounding electrode located at FPz position. All the EEG electrodes and grounding electrode are Ag/AgCl semi-dry EEG electrodes based on highly absorbable porous sponges that are dampened with 3% NaCl solution. The EOG electrodes are composed by Ag/AgCl electrodes and conductive adhesive hydrogel. The common-mode rejection ratio was 120 dB, the input impedance was 1 GΩ, the input noise was less than 0.4 μVrms, and the resolution was 24 bits. The acquisition impedance was less than or equal to 20 kΩ. The sampling frequency was 500 Hz.

Open in Overview tab →

Citation & Impact

Paper DOI10.1038/s41597-023-02787-8
CitationsLoading…
Public APICrossref | OpenAlex
Page Views
30d: 62 · all-time: 409
#25 of 151 · Top 17% most viewed
Updated: 2026-03-20 UTC

Stimulus Protocol

8s task window per trial · 2-class motor imagery paradigm · 1 runs/session across 1 sessions

HED Event Tags

HED tags2/2 events annotated

Source: MOABB BIDS HED annotation mapping.

Agent-action

2

Sensory-event

2

left_hand

Sensory-eventAgent-action

right_hand

Sensory-eventAgent-action

HED tree view

Tree · left_hand

├─ Sensory-event
│  ├─ Experimental-stimulus
│  └─ Visual-presentation
└─ Agent-action
   └─ Imagine
      ├─ Move
      └─ Left
         └─ Hand

Tree · right_hand

├─ Sensory-event
│  ├─ Experimental-stimulus
│  └─ Visual-presentation
└─ Agent-action
   └─ Imagine
      ├─ Move
      └─ Right
         └─ Hand

Channel Summary

Total channels29

EEG29 (semi-dry Ag/AgCl)

EOG2

Montage10-10

Sampling500 Hz

ReferenceCPz

Notch / line50 Hz

This diagram is automatically generated from MOABB metadata. Please consult the original publication to confirm the experimental protocol details.

Overview

Dataset [1] from the study on motor imagery [2].

Dataset description This dataset includes data from 50 acute stroke patients (the time after stroke ranges from 1 day to 30 days) admitted to the stroke unit of Xuanwu Hospital of Capital Medical University. The patients included 39 males (78%) and 11 females (22%), aged between 31 and 77 years, with an average age of 56.70 years (SD = 10.57) Before the start of the experiment, the subject sat in a chair in a position as comfortable as possible with an EEG cap placed on their head; subjects were positioned approximately 80 cm away from a computer screen in front of them. The computer played audio instructions to the patient about the procedure. Each experiment lasted approximately 20 minutes, including preparation time and approximately 10 minutes of signal recording. Before the start of the MI experiment, the patients opened their eyes and closed their eyes for 1 minute each. The MI experiment was divided into 40 trials, and each trial took 8 seconds, which consisted of three stages (instruction, MI and break). In the instruction stage, patients were prompted to imagine grasping a spherical object with the left- or right-hand. In the MI stage, participants imagined performing this action, a video of gripping motion is played on the computer, which leads the patient imagine grabbing the ball. This video stays playing for 4 s. Patients only imagine one hand movement.In the break stage, participants were allowed to relax and rest. The MI experiments alternated between the left- and right-hand, and the patients moved onto the next stage of the experiment according to the instructions.

The EEG data were collected through a wireless multichannel EEG acquisition system (ZhenTec NT1, Xi’an ZhenTec Intelligence Technology Co., Ltd., China). The system includes an EEG cap, an EEG acquisition amplifier, a data receiver and host computer software. The EEG cap had electrodes placed according to the international 10-10 system, including 29 EEG recording electrodes and 2 electrooculography (EOG) electrodes. The reference electrode located at CPz position and the grounding electrode located at FPz position. All the EEG electrodes and grounding electrode are Ag/AgCl semi-dry EEG electrodes based on highly absorbable porous sponges that are dampened with 3% NaCl solution. The EOG electrodes are composed by Ag/AgCl electrodes and conductive adhesive hydrogel. The common-mode rejection ratio was 120 dB, the input impedance was 1 GΩ, the input noise was less than 0.4 μVrms, and the resolution was 24 bits. The acquisition impedance was less than or equal to 20 kΩ. The sampling frequency was 500 Hz.

References

[1]

Liu, Haijie; Lv, Xiaodong (2022). EEG datasets of stroke patients. figshare. Dataset. DOI: https://doi.org/10.6084/m9.figshare.21679035.v5

[2]

Liu, Haijie, Wei, P., Wang, H. et al. An EEG motor imagery dataset for brain computer interface in acute stroke patients. Sci Data 11, 131 (2024). DOI: https://doi.org/10.1038/s41597-023-02787-8

Code Examples

from moabb.datasets import Liu2024
dataset = Liu2024()
data = dataset.get_data(subjects=[1])
print(data[1])

Metadata

Dataset summary

#Subj	50
#Chan	29
#Classes	2
#Trials / class	20
Trials length	4 s
Freq	500 Hz
#Sessions	1
#Runs	1
Total_trials	2000

Participants

Population: acute stroke patients
Clinical population: acute stroke patients (1-30 days post-stroke)
Age: 56.7 (range: 31-77) years

Equipment

Amplifier: ZhenTec NT1 wireless multichannel EEG acquisition system
Electrodes: semi-dry Ag/AgCl
Montage: 10-10
Reference: CPz

Preprocessing

Data state: preprocessed
Bandpass filter: 0.5-40 Hz
Steps: baseline removal (mean removal method), FIR filtering (0.5-40 Hz)
Notes: Preprocessed with EEGLAB toolbox in MATLAB R2019b. Filtered data split into trials x channels x time-samples format by marker ‘1’. Some motion artifacts present in subjects 4, 5, 13, 14, 18, 24, 28, 33, 42, 43, 47, 48, 49.

Data Access

DOI: 10.1038/s41597-023-02787-8
Data URL: https://doi.org/10.6084/m9.figshare.21679035.v5
Repository: Figshare

Experimental Protocol

Paradigm: imagery
Feedback: none
Stimulus: video and audio

Notes

To add the break and instruction events, set the break_events and instr_events parameters to True while instantiating the class.

Added in version 1.1.1.

__init__(break_events=False, instr_events=False, subjects=None, sessions=None, *, return_all_modalities=False, **kwargs)[source]#: Initialize function for the BaseDataset.

property all_subjects#: Full list of subjects available in this dataset (unfiltered).

convert_to_bids(path=None, subjects=None, overwrite=False, format='EDF', verbose=None, generate_figures=False)[source]#

Convert the dataset to BIDS format.

Saves the raw EEG data in a BIDS-compliant directory structure. Unlike the caching mechanism (see CacheConfig), the files produced here do not contain a processing-pipeline hash (desc-<hash>) in their names, making the output a clean, shareable BIDS dataset.

Parameters:

path (str | Path | None) – Directory under which the BIDS dataset will be written. If None the default MNE data directory is used (same default as the rest of MOABB).
subjects (list of int | None) – Subject numbers to convert. If None, all subjects in subject_list are converted.
overwrite (bool) – If True, existing BIDS files for a subject are removed before saving. Default is False.
format (str) – The file format for the raw EEG data. Supported values are "EDF" (default), "BrainVision", and "EEGLAB".
verbose (str | None) – Verbosity level forwarded to MNE/MNE-BIDS.
generate_figures (bool) – If True, generate interactive neural signature HTML figures in {bids_root}/derivatives/neural_signatures/. Requires plotly (pip install moabb[interactive]). Default is False.

Returns:

bids_root – Path to the root of the written BIDS dataset.

Return type:

pathlib.Path

Examples

>>> from moabb.datasets import AlexMI
>>> dataset = AlexMI()
>>> bids_root = dataset.convert_to_bids(path='/tmp/bids', subjects=[1])