Gait Reconstruction from Motion Artefact Corrupted Fabric-Embedded Sensors

dataset

posted on 2021-09-13, 18:33 authored by Brendan Michael

This research investigates the use of unsupervised latent space learning techniques for the removal of motion artefacts in fabric embedded sensor systems. This dataset contains motion data collected during walking tasks, for two sensor systems, 1) a high-quality ground truth inertial measurement system, and 2) tri-axel linear accelleration and angular velocity measurements from sensor embedded into items of clothing.

Funding

Data collection was funded by King's College London

History

Data collection from date

2015-06-19

Data collection to date

2015-06-26

Collection method

Sensed acceleration data was collected from tri-axel inertial measurement units, streaming to a microcontroller and wiresless base station. For more information see related publication: Gait Reconstruction from Motion Artefact Corrupted Fabric-Embedded Sensors. B. Michael and M. Howard. IEEE International Conference Robotics and Automation, 2018

Language

English

Usage metrics

Keywords

machine learning Wearable sensors fabric sensors Knowledge Representation and Machine Learning

Licence

CC BY

Exports

RefWorks

BibTeX

Ref. manager

Endnote

DataCite

NLM