Multimodal Gait Dataset: EEG, EMG, Kinematics and Ground Reaction Forces in Young Adults

Provider
Katmah, AlShehhi, Kosaji, Al-Rahmani, Abdullah, Hulleck and Khalaf (PhysioNet)
License
CC-BY-4.0 (source)
Format
CSV (in sampled files)
Stored at
Amazon S3, s3://physionet-open/multimodal-gait-dataset (us-east-1)
Access
Free and public. No account with the data provider is needed.
DOI
10.13026/r0ea-7161
Category
Physiology
Source
https://doi.org/10.13026/r0ea-7161

About this dataset

Treadmill walking recordings from 59 healthy adults (mean age 24 years, both sexes, several BMI categories) at three controlled speeds (0.5, 0.75 and 1.0 m/s), released by Katmah, AlShehhi, Kosaji, Al-Rahmani, Abdullah, Hulleck and Khalaf. Synchronized modalities: 19-channel scalp electroencephalography (EEG, Wearable Sensing headset, 300 Hz, raw unfiltered), surface electromyography (sEMG) of 12 lower-limb muscles, inertial measurement units (Xsens IMU kinematics, 60 Hz) and bilateral force plates giving 3D forces, moments and centre of pressure at 1000 Hz. Intended for gait analysis, brain-muscle connectivity, neuromechanical control, speed-dependent adaptation and machine learning gait classification. Measured 2026-11-13 (version 1.0.0): Dataset/ holds EEG_Data (EEG.csv and EEG.edf folders, 177 files per format per the publisher, plus an EEG_referencing.m script), EMG_Data and FP_Data as per-subject per-speed CSV files (for example EMG_S10_0.5.csv, FP_S10_0.5.csv at about 13 MB), IMU_Data as one IMU.tar.gz of 3,922,799,402 bytes, and subject-info.csv with anthropometrics. Open the CSVs with pandas and the EDF files with MNE or pyEDFlib. A few sessions are missing and are listed by the publisher. Licensed CC BY 4.0; cite Katmah et al., doi 10.13026/r0ea-7161.

How to access this dataset in Python

import boto3
from botocore import UNSIGNED
from botocore.client import Config
s3 = boto3.client('s3', region_name='us-east-1', config=Config(signature_version=UNSIGNED))
s3.list_objects_v2(Bucket='physionet-open', Prefix='multimodal-gait-dataset/', Delimiter='/')

Lists the files with anonymous access. Runs on any machine, with no cloud account.

Data structure

File types in sampled files: CSV

Files

Example file: multimodal-gait-dataset/1.0.0/Dataset/EEG_Data/EEG.csv/S10_0.5_raw.csv

Analyze this dataset without downloading it

On Scigantic, Multimodal Gait Dataset: EEG, EMG, Kinematics and Ground Reaction Forces in Young Adults opens in a hosted JupyterLab notebook with the data already mounted, so you can read files where they are stored instead of copying them first. Each notebook includes an AI assistant that can see the mounted files and write and run analysis code. Open the dataset page to launch a notebook, or browse the full catalog.

This page is also available as Markdown and as JSON.

Related Physiology datasets