Datasets
Open Access
FallAllD: A Comprehensive Dataset of Human Falls and Activities of Daily Living
- Citation Author(s):
-
MajdSALEH
Université de Rennes 1, LTSI, Rennes, 35000, France, and INSERM, U1099, Rennes, 35000, France - Submitted by:
- Majd SALEH
- Last updated:
- Tue, 05/17/2022 - 22:21
- DOI:
- 10.21227/bnya-mn34
- Data Format:
- Research Article Link:
- License:
7993 Views- Citations:
- 1
- Categories:
- Keywords:
Abstract
Description
FallAllD is a large open dataset of human falls and activities of daily living simulated by 15 participants. FallAllD consists of 26420 files collected using three data-loggers worn on the waist, wrist and neck of the subjects. Motion signals are captured using an accelerometer, gyroscope, magnetometer and barometer with efficient configurations that suit the potential applications e.g. fall detection, fall prevention and human activity recognition.
FallAllD is described in detail in the following journal article:
M. Saleh, M. Abbas and R. L. B. Jeannès, "FallAllD: An Open Dataset of Human Falls and Activities of Daily Living for Classical and Deep Learning Applications," in IEEE Sensors Journal, doi: 10.1109/JSEN.2020.3018335.
Data Acquisition
Three identical data-loggers developed by the society RF-Track have been used. They are waist, wrist and neck-worn devices equipped with:
· LSM9DS1: 3-axial accelerometer, 3-axial gyroscope and 3-axial magnetometer.
· MS5607-02BA03: barometer.
Sensors configurations
· Accelerometer: Sampling frequency = 238 Hz. Measurement range = ±8 g.
· Gyroscope: Sampling frequency = 238 Hz. Angular rate = ± 2000 dps.
· Magnetometer: Sampling frequency = 80 Hz. Full scale magnetic field = ±4 Gauss.
· Barometer: Sampling frequency = 10 Hz.
Data files are stored in comma-separated values (csv) format. We developed two tools for encapsulating the data. The first one, namely FallAllD_Files_to_Matlab_Struct, is a MATLAB script that converts the dataset into a MATLAB structure stored as a ”.mat” file. The structure contains 8 fields {SubjectID, ActivityID, TrialNo, Device, Acc, Gyr, Mag, Bar}. The second tool, namely FallAllD_Files_to_Python_Struct, is a Python script that converts the dataset into a Pandas dataframe stored in hdf (”.h5”) or pickle (”.pkl”) formats. The dataframe has the same fields as the MATLAB structure.
To get familiar with FallAllD, use the MATLAB script Plot_FallAllD_Register to show any register of this dataset.
If you use this dataset, please cite the following publication:
M. Saleh, M. Abbas and R. L. B. Jeannès, "FallAllD: An Open Dataset of Human Falls and Activities of Daily Living for Classical and Deep Learning Applications," in IEEE Sensors Journal, doi: 10.1109/JSEN.2020.3018335.
Dataset Files
Main data file FallAllD__zip.zip (401.39 MB)- Videos illustrating how falls have been simulated Videos.zip (169.64 MB)
- Useful scripts for converting the data files into MATLAB structure or Python pandas dataframe. scripts.zip (4.19 kB)
This script stores all FallAllD files (26420) in one MATLAB structure FallAllD_to_MATLAB_Structure.m (1.34 kB)
This script stores all FallAllD files (26420) in one Pandas dataframe FallAllD_to_PYTHON_Structure.py (1.92 kB)- Useful example to get familiar with this dataset Plot_FallAllD_Record.m (3.27 kB)
- This script converts an activity ID to a short text description (required by Plot_FallAllD_Record) ActivityID2Str.m (5.19 kB)
Open Access dataset files are accessible to all logged in users. Don't have a login? Create a free IEEE account. IEEE Membership is not required.
Documentation
| Attachment | Size |
|---|---|
 simulated falls and ADLs- list.pdf | 360.97 KB |
Comments
This looks like a great dataset, thank you!