Cargando…

Gait-Based Identification Using Deep Recurrent Neural Networks and Acceleration Patterns

This manuscript presents an approach to the challenge of biometric identification based on the acceleration patterns generated by a user while walking. The proposed approach uses the data captured by a smartphone’s accelerometer and gyroscope sensors while the users perform the gait activity and opt...

Descripción completa

Detalles Bibliográficos
Autores principales: Peinado-Contreras, Angel, Munoz-Organero, Mario
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7729817/
https://www.ncbi.nlm.nih.gov/pubmed/33287142
http://dx.doi.org/10.3390/s20236900
_version_ 1783621545282764800
author Peinado-Contreras, Angel
Munoz-Organero, Mario
author_facet Peinado-Contreras, Angel
Munoz-Organero, Mario
author_sort Peinado-Contreras, Angel
collection PubMed
description This manuscript presents an approach to the challenge of biometric identification based on the acceleration patterns generated by a user while walking. The proposed approach uses the data captured by a smartphone’s accelerometer and gyroscope sensors while the users perform the gait activity and optimizes the design of a recurrent neural network (RNN) to optimally learn the features that better characterize each individual. The database is composed of 15 users, and the acceleration data provided has a tri-axial format in the X-Y-Z axes. Data are pre-processed to estimate the vertical acceleration (in the direction of the gravity force). A deep recurrent neural network model consisting of LSTM cells divided into several layers and dense output layers is used for user recognition. The precision results obtained by the final architecture are above 97% in most executions. The proposed deep neural network-based architecture is tested in different scenarios to check its efficiency and robustness.
format Online
Article
Text
id pubmed-7729817
institution National Center for Biotechnology Information
language English
publishDate 2020
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-77298172020-12-12 Gait-Based Identification Using Deep Recurrent Neural Networks and Acceleration Patterns Peinado-Contreras, Angel Munoz-Organero, Mario Sensors (Basel) Article This manuscript presents an approach to the challenge of biometric identification based on the acceleration patterns generated by a user while walking. The proposed approach uses the data captured by a smartphone’s accelerometer and gyroscope sensors while the users perform the gait activity and optimizes the design of a recurrent neural network (RNN) to optimally learn the features that better characterize each individual. The database is composed of 15 users, and the acceleration data provided has a tri-axial format in the X-Y-Z axes. Data are pre-processed to estimate the vertical acceleration (in the direction of the gravity force). A deep recurrent neural network model consisting of LSTM cells divided into several layers and dense output layers is used for user recognition. The precision results obtained by the final architecture are above 97% in most executions. The proposed deep neural network-based architecture is tested in different scenarios to check its efficiency and robustness. MDPI 2020-12-03 /pmc/articles/PMC7729817/ /pubmed/33287142 http://dx.doi.org/10.3390/s20236900 Text en © 2020 by the authors. 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 (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Peinado-Contreras, Angel
Munoz-Organero, Mario
Gait-Based Identification Using Deep Recurrent Neural Networks and Acceleration Patterns
title Gait-Based Identification Using Deep Recurrent Neural Networks and Acceleration Patterns
title_full Gait-Based Identification Using Deep Recurrent Neural Networks and Acceleration Patterns
title_fullStr Gait-Based Identification Using Deep Recurrent Neural Networks and Acceleration Patterns
title_full_unstemmed Gait-Based Identification Using Deep Recurrent Neural Networks and Acceleration Patterns
title_short Gait-Based Identification Using Deep Recurrent Neural Networks and Acceleration Patterns
title_sort gait-based identification using deep recurrent neural networks and acceleration patterns
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7729817/
https://www.ncbi.nlm.nih.gov/pubmed/33287142
http://dx.doi.org/10.3390/s20236900
work_keys_str_mv AT peinadocontrerasangel gaitbasedidentificationusingdeeprecurrentneuralnetworksandaccelerationpatterns
AT munozorganeromario gaitbasedidentificationusingdeeprecurrentneuralnetworksandaccelerationpatterns