Gait identification by means of box approximation geometry of reconstructed attractors in latent space

Albert Samà; Francisco J. Ruiz; N. Agell; Carlos Pérez-López; Andreu Català; Joan Cabestany

doi:10.1016/j.neucom.2012.12.042

Gait identification by means of box approximation geometry of reconstructed attractors in latent space

Albert Samà, Francisco J. Ruiz, N. Agell, Carlos Pérez-López, Andreu Català, Joan Cabestany

Producció científica: Article en revista indexada › Article › Avaluat per experts

13 Cites (Scopus)

Resum

This paper presents a novel gait recognition method which uses the signals measured by a single inertial sensor located on the waist. This method considers human gait as a dynamical system and employs a few singular values obtained by means of Singular Spectrum Analysis applied to scalar measurements from the inertial sensor. Singular values can be interpreted as the approximate edge length of the bounding box wrapping the attractor in the latent space. Effects of different parameters on the gait recognition performance using patterns from 20 different subjects are analysed.

Idioma original	Anglès
Pàgines (de-a)	79-88
Nombre de pàgines	10
Revista	Neurocomputing
Volum	121
DOIs	https://doi.org/10.1016/j.neucom.2012.12.042
Estat de la publicació	Publicada - 9 de des. 2013
Publicat externament	Sí

Accés al document

10.1016/j.neucom.2012.12.042

Altres arxius i enllaços

Link to publication in Scopus

Com citar-ho

@article{bf5df7d6e6974e9086f0b97296b49626,

title = "Gait identification by means of box approximation geometry of reconstructed attractors in latent space",

abstract = "This paper presents a novel gait recognition method which uses the signals measured by a single inertial sensor located on the waist. This method considers human gait as a dynamical system and employs a few singular values obtained by means of Singular Spectrum Analysis applied to scalar measurements from the inertial sensor. Singular values can be interpreted as the approximate edge length of the bounding box wrapping the attractor in the latent space. Effects of different parameters on the gait recognition performance using patterns from 20 different subjects are analysed.",

keywords = "Box approximation geometry, Gait recognition, Inertial sensors, Singular spectrum analysis",

author = "Albert Sam{\`a} and Ruiz, {Francisco J.} and N. Agell and Carlos P{\'e}rez-L{\'o}pez and Andreu Catal{\`a} and Joan Cabestany",

note = "Funding Information: This work is supported by the Spanish project SENSORIAL ( TIN2010-20966-C02-02 ) Spanish Ministry of Education and Science. Authors want to thank all volunteers for their participation and CETpD members that helped in the data gathering. ",

year = "2013",

month = dec,

day = "9",

doi = "10.1016/j.neucom.2012.12.042",

language = "English",

volume = "121",

pages = "79--88",

journal = "Neurocomputing",

issn = "0925-2312",

publisher = "Elsevier B.V.",

}

TY - JOUR

T1 - Gait identification by means of box approximation geometry of reconstructed attractors in latent space

AU - Samà, Albert

AU - Ruiz, Francisco J.

AU - Agell, N.

AU - Pérez-López, Carlos

AU - Català, Andreu

AU - Cabestany, Joan

N1 - Funding Information: This work is supported by the Spanish project SENSORIAL ( TIN2010-20966-C02-02 ) Spanish Ministry of Education and Science. Authors want to thank all volunteers for their participation and CETpD members that helped in the data gathering.

PY - 2013/12/9

Y1 - 2013/12/9

N2 - This paper presents a novel gait recognition method which uses the signals measured by a single inertial sensor located on the waist. This method considers human gait as a dynamical system and employs a few singular values obtained by means of Singular Spectrum Analysis applied to scalar measurements from the inertial sensor. Singular values can be interpreted as the approximate edge length of the bounding box wrapping the attractor in the latent space. Effects of different parameters on the gait recognition performance using patterns from 20 different subjects are analysed.

AB - This paper presents a novel gait recognition method which uses the signals measured by a single inertial sensor located on the waist. This method considers human gait as a dynamical system and employs a few singular values obtained by means of Singular Spectrum Analysis applied to scalar measurements from the inertial sensor. Singular values can be interpreted as the approximate edge length of the bounding box wrapping the attractor in the latent space. Effects of different parameters on the gait recognition performance using patterns from 20 different subjects are analysed.

KW - Box approximation geometry

KW - Gait recognition

KW - Inertial sensors

KW - Singular spectrum analysis

UR - http://www.scopus.com/inward/record.url?scp=84884126639&partnerID=8YFLogxK

U2 - 10.1016/j.neucom.2012.12.042

DO - 10.1016/j.neucom.2012.12.042

M3 - Article

AN - SCOPUS:84884126639

SN - 0925-2312

VL - 121

SP - 79

EP - 88

JO - Neurocomputing

JF - Neurocomputing

ER -

Gait identification by means of box approximation geometry of reconstructed attractors in latent space

Resum

Accés al document

Altres arxius i enllaços

Fingerprint

Com citar-ho