Cargando…

Deep Learning Methods for Speed Estimation of Bipedal Motion from Wearable IMU Sensors

The estimation of the speed of human motion from wearable IMU sensors is required in applications such as pedestrian dead reckoning. In this paper, we test deep learning methods for the prediction of the motion speed from raw readings of a low-cost IMU sensor. Each subject was observed using three s...

Descripción completa

Detalles Bibliográficos
Autores principales: Justa, Josef, Šmídl, Václav, Hamáček, Aleš
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9144294/
https://www.ncbi.nlm.nih.gov/pubmed/35632274
http://dx.doi.org/10.3390/s22103865
_version_ 1784716013835649024
author Justa, Josef
Šmídl, Václav
Hamáček, Aleš
author_facet Justa, Josef
Šmídl, Václav
Hamáček, Aleš
author_sort Justa, Josef
collection PubMed
description The estimation of the speed of human motion from wearable IMU sensors is required in applications such as pedestrian dead reckoning. In this paper, we test deep learning methods for the prediction of the motion speed from raw readings of a low-cost IMU sensor. Each subject was observed using three sensors at the shoe, shin, and thigh. We show that existing general-purpose architectures outperform classical feature-based approaches and propose a novel architecture tailored for this task. The proposed architecture is based on a semi-supervised variational auto-encoder structure with innovated decoder in the form of a dense layer with a sinusoidal activation function. The proposed architecture achieved the lowest average error on the test data. Analysis of sensor placement reveals that the best location for the sensor is the shoe. Significant accuracy gain was observed when all three sensors were available. All data acquired in this experiment and the code of the estimation methods are available for download.
format Online
Article
Text
id pubmed-9144294
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-91442942022-05-29 Deep Learning Methods for Speed Estimation of Bipedal Motion from Wearable IMU Sensors Justa, Josef Šmídl, Václav Hamáček, Aleš Sensors (Basel) Article The estimation of the speed of human motion from wearable IMU sensors is required in applications such as pedestrian dead reckoning. In this paper, we test deep learning methods for the prediction of the motion speed from raw readings of a low-cost IMU sensor. Each subject was observed using three sensors at the shoe, shin, and thigh. We show that existing general-purpose architectures outperform classical feature-based approaches and propose a novel architecture tailored for this task. The proposed architecture is based on a semi-supervised variational auto-encoder structure with innovated decoder in the form of a dense layer with a sinusoidal activation function. The proposed architecture achieved the lowest average error on the test data. Analysis of sensor placement reveals that the best location for the sensor is the shoe. Significant accuracy gain was observed when all three sensors were available. All data acquired in this experiment and the code of the estimation methods are available for download. MDPI 2022-05-19 /pmc/articles/PMC9144294/ /pubmed/35632274 http://dx.doi.org/10.3390/s22103865 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Justa, Josef
Šmídl, Václav
Hamáček, Aleš
Deep Learning Methods for Speed Estimation of Bipedal Motion from Wearable IMU Sensors
title Deep Learning Methods for Speed Estimation of Bipedal Motion from Wearable IMU Sensors
title_full Deep Learning Methods for Speed Estimation of Bipedal Motion from Wearable IMU Sensors
title_fullStr Deep Learning Methods for Speed Estimation of Bipedal Motion from Wearable IMU Sensors
title_full_unstemmed Deep Learning Methods for Speed Estimation of Bipedal Motion from Wearable IMU Sensors
title_short Deep Learning Methods for Speed Estimation of Bipedal Motion from Wearable IMU Sensors
title_sort deep learning methods for speed estimation of bipedal motion from wearable imu sensors
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9144294/
https://www.ncbi.nlm.nih.gov/pubmed/35632274
http://dx.doi.org/10.3390/s22103865
work_keys_str_mv AT justajosef deeplearningmethodsforspeedestimationofbipedalmotionfromwearableimusensors
AT smidlvaclav deeplearningmethodsforspeedestimationofbipedalmotionfromwearableimusensors
AT hamacekales deeplearningmethodsforspeedestimationofbipedalmotionfromwearableimusensors