Accelerometer based Gait Recognition using Adapted Gaussian Mixture Models

Muhammad Muaaz; Rene Mayrhofer

doi:10.1145/3007120.3007164

Accelerometer based Gait Recognition using Adapted Gaussian Mixture Models

Muhammad Muaaz
, Rene Mayrhofer

Research Center Hagenberg

Publikation: Beitrag in Buch/Bericht/Tagungsband › Konferenzbeitrag › Begutachtung

16 Zitate (Scopus)

Abstract

Gait authentication using a cell phone based accelerometer sensor offers an unobtrusive, user-friendly, and a periodic way of authenticating individuals to their smartphones. In this paper, we present a GMM-UBM based gait recognition approach for a realistic scenario (when the phone is placed inside the trouser pocket and the user is walking) by using the magnitude data of a smartphone-based tri-axes accelerometer sensor. To evaluate our approach we use a gait data set of 35 participants collected at their respective normal walking pace in two different sessions with an average gap of 25 days between the sessions. We obtained EERs of 3.031%, 11.531%, and 14.393% for the same-day, mix-days, and cross-days, respectively.

Originalsprache	Englisch
Titel	14th International Conference on Advances in Mobile Computing and Multimedia, MoMM 2016 - Proceedings
Redakteure/-innen	Bessam Abdulrazak, Matthias Steinbauer, Ismail Khalil, Eric Pardede, Gabriele Anderst-Kotsis
Herausgeber (Verlag)	ACM Press
Seiten	288-291
Seitenumfang	4
ISBN (elektronisch)	9781450348065
ISBN (Print)	978-1-4503-4806-5
DOIs	https://doi.org/10.1145/3007120.3007164
Publikationsstatus	Veröffentlicht - 28 Nov. 2016
Veranstaltung	14th International Conference on Advances in Mobile Computing and Multimedia (MoMM 2016) - Singapore, Singapur Dauer: 28 Nov. 2016 → 30 Nov. 2016 http://www.iiwas.org/conferences/momm2016/

Publikationsreihe

Name	ACM International Conference Proceeding Series

Konferenz

Konferenz	14th International Conference on Advances in Mobile Computing and Multimedia (MoMM 2016)
Land/Gebiet	Singapur
Ort	Singapore
Zeitraum	28.11.2016 → 30.11.2016
Internetadresse	http://www.iiwas.org/conferences/momm2016/

Schlagwörter

Accelerometer
gait recognition
Gaussian Mixture Models
segmentation
variance

Zugriff auf Dokument

10.1145/3007120.3007164

Andere Dateien und Links

Link to publication in Scopus

Zitieren

Muaaz, M., & Mayrhofer, R. (2016). Accelerometer based Gait Recognition using Adapted Gaussian Mixture Models. in B. Abdulrazak, M. Steinbauer, I. Khalil, E. Pardede, & G. Anderst-Kotsis (Hrsg.), 14th International Conference on Advances in Mobile Computing and Multimedia, MoMM 2016 - Proceedings (S. 288-291). (ACM International Conference Proceeding Series). ACM Press. https://doi.org/10.1145/3007120.3007164

Muaaz, Muhammad ; Mayrhofer, Rene. / Accelerometer based Gait Recognition using Adapted Gaussian Mixture Models. 14th International Conference on Advances in Mobile Computing and Multimedia, MoMM 2016 - Proceedings. Hrsg. / Bessam Abdulrazak ; Matthias Steinbauer ; Ismail Khalil ; Eric Pardede ; Gabriele Anderst-Kotsis. ACM Press, 2016. S. 288-291 (ACM International Conference Proceeding Series).

@inproceedings{3e129e02d392480ea3d98ab6df86c58e,

title = "Accelerometer based Gait Recognition using Adapted Gaussian Mixture Models",

abstract = "Gait authentication using a cell phone based accelerometer sensor offers an unobtrusive, user-friendly, and a periodic way of authenticating individuals to their smartphones. In this paper, we present a GMM-UBM based gait recognition approach for a realistic scenario (when the phone is placed inside the trouser pocket and the user is walking) by using the magnitude data of a smartphone-based tri-axes accelerometer sensor. To evaluate our approach we use a gait data set of 35 participants collected at their respective normal walking pace in two different sessions with an average gap of 25 days between the sessions. We obtained EERs of 3.031\%, 11.531\%, and 14.393\% for the same-day, mix-days, and cross-days, respectively.",

keywords = "Accelerometer, gait recognition, Gaussian Mixture Models, segmentation, variance, Accelerometer, gait recognition, Gaussian Mixture Models, segmentation, variance, Segmentation, Gaussian mixture models, Gait recognition, Variance",

author = "Muhammad Muaaz and Rene Mayrhofer",

year = "2016",

month = nov,

day = "28",

doi = "10.1145/3007120.3007164",

language = "English",

isbn = "978-1-4503-4806-5",

series = "ACM International Conference Proceeding Series",

publisher = "ACM Press",

pages = "288--291",

editor = "Bessam Abdulrazak and Matthias Steinbauer and Ismail Khalil and Eric Pardede and Gabriele Anderst-Kotsis",

booktitle = "14th International Conference on Advances in Mobile Computing and Multimedia, MoMM 2016 - Proceedings",

note = "14th International Conference on Advances in Mobile Computing and Multimedia (MoMM 2016) ; Conference date: 28-11-2016 Through 30-11-2016",

url = "http://www.iiwas.org/conferences/momm2016/",

}

Muaaz, M & Mayrhofer, R 2016, Accelerometer based Gait Recognition using Adapted Gaussian Mixture Models. in B Abdulrazak, M Steinbauer, I Khalil, E Pardede & G Anderst-Kotsis (Hrsg.), 14th International Conference on Advances in Mobile Computing and Multimedia, MoMM 2016 - Proceedings. ACM International Conference Proceeding Series, ACM Press, S. 288-291, 14th International Conference on Advances in Mobile Computing and Multimedia (MoMM 2016), Singapore, Singapur, 28.11.2016. https://doi.org/10.1145/3007120.3007164

Accelerometer based Gait Recognition using Adapted Gaussian Mixture Models. / Muaaz, Muhammad; Mayrhofer, Rene.
14th International Conference on Advances in Mobile Computing and Multimedia, MoMM 2016 - Proceedings. Hrsg. / Bessam Abdulrazak; Matthias Steinbauer; Ismail Khalil; Eric Pardede; Gabriele Anderst-Kotsis. ACM Press, 2016. S. 288-291 (ACM International Conference Proceeding Series).

Publikation: Beitrag in Buch/Bericht/Tagungsband › Konferenzbeitrag › Begutachtung

TY - GEN

T1 - Accelerometer based Gait Recognition using Adapted Gaussian Mixture Models

AU - Muaaz, Muhammad

AU - Mayrhofer, Rene

PY - 2016/11/28

Y1 - 2016/11/28

N2 - Gait authentication using a cell phone based accelerometer sensor offers an unobtrusive, user-friendly, and a periodic way of authenticating individuals to their smartphones. In this paper, we present a GMM-UBM based gait recognition approach for a realistic scenario (when the phone is placed inside the trouser pocket and the user is walking) by using the magnitude data of a smartphone-based tri-axes accelerometer sensor. To evaluate our approach we use a gait data set of 35 participants collected at their respective normal walking pace in two different sessions with an average gap of 25 days between the sessions. We obtained EERs of 3.031%, 11.531%, and 14.393% for the same-day, mix-days, and cross-days, respectively.

AB - Gait authentication using a cell phone based accelerometer sensor offers an unobtrusive, user-friendly, and a periodic way of authenticating individuals to their smartphones. In this paper, we present a GMM-UBM based gait recognition approach for a realistic scenario (when the phone is placed inside the trouser pocket and the user is walking) by using the magnitude data of a smartphone-based tri-axes accelerometer sensor. To evaluate our approach we use a gait data set of 35 participants collected at their respective normal walking pace in two different sessions with an average gap of 25 days between the sessions. We obtained EERs of 3.031%, 11.531%, and 14.393% for the same-day, mix-days, and cross-days, respectively.

KW - Accelerometer

KW - gait recognition

KW - Gaussian Mixture Models

KW - segmentation

KW - variance

KW - Accelerometer

KW - gait recognition

KW - Gaussian Mixture Models

KW - segmentation

KW - variance

KW - Segmentation

KW - Gaussian mixture models

KW - Gait recognition

KW - Variance

UR - https://www.scopus.com/pages/publications/85015009962

U2 - 10.1145/3007120.3007164

DO - 10.1145/3007120.3007164

M3 - Conference contribution

SN - 978-1-4503-4806-5

T3 - ACM International Conference Proceeding Series

SP - 288

EP - 291

BT - 14th International Conference on Advances in Mobile Computing and Multimedia, MoMM 2016 - Proceedings

A2 - Abdulrazak, Bessam

A2 - Steinbauer, Matthias

A2 - Khalil, Ismail

A2 - Pardede, Eric

A2 - Anderst-Kotsis, Gabriele

PB - ACM Press

T2 - 14th International Conference on Advances in Mobile Computing and Multimedia (MoMM 2016)

Y2 - 28 November 2016 through 30 November 2016

ER -

Muaaz M, Mayrhofer R. Accelerometer based Gait Recognition using Adapted Gaussian Mixture Models. in Abdulrazak B, Steinbauer M, Khalil I, Pardede E, Anderst-Kotsis G, Hrsg., 14th International Conference on Advances in Mobile Computing and Multimedia, MoMM 2016 - Proceedings. ACM Press. 2016. S. 288-291. (ACM International Conference Proceeding Series). doi: 10.1145/3007120.3007164

Accelerometer based Gait Recognition using Adapted Gaussian Mixture Models

Abstract

Publikationsreihe

Konferenz

Schlagwörter

Zugriff auf Dokument

Andere Dateien und Links

Fingerprint

Zitieren