Gait patterns classification using spectral features

R. K. Ibrahim; E. Ambikairajah; B. Celler; N. H. Lovell; L. Kilmartin

doi:10.1049/cp:20080645

Gait patterns classification using spectral features

R. K. Ibrahim, E. Ambikairajah, B. Celler, N. H. Lovell, L. Kilmartin

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding contribution › peer-review

25 Citations (Scopus)

Abstract

Accelerometry has been shown to be a good tool for ambulatory activity monitoring. This paper describes the use of spectral features for classification of gait activities based on accelerometric data. The classification is performed by a Gaussian mixture model (GMM) based statistical classifier at the back end. Fifty subjects participated in the experiment and an overall classification accuracy of 86% was achieved using the proposed 25 dimensional features for five different human gait patterns including walking on level surfaces, walking up and down stairs and walking up and down ramps.

Original language	English
Title of host publication	The IET Irish Signals and Systems Conference, ISSC 2008
Subtitle of host publication	18-19 June 2008, National University Of Ireland, Galway, Ireland
Place of Publication	Stevenage
Publisher	Institution of Engineering and Technology
Pages	98-102
Number of pages	5
Edition	539 CP
ISBN (Print)	9780863419317
DOIs	https://doi.org/10.1049/cp:20080645
Publication status	Published - 2008
Externally published	Yes
Event	IET Irish Signals and Systems Conference, ISSC 2008 - Galway, Ireland Duration: 18 Jun 2008 → 19 Jun 2008

Other

Other	IET Irish Signals and Systems Conference, ISSC 2008
Country/Territory	Ireland
City	Galway
Period	18/06/08 → 19/06/08

Keywords

Accelerometry
Ambulatory monitoring
Feature extraction
Gait patterns

Access to Document

10.1049/cp:20080645

Cite this

@inproceedings{4b6a9c32f4ab4ffe809c4295632c85d6,

title = "Gait patterns classification using spectral features",

abstract = "Accelerometry has been shown to be a good tool for ambulatory activity monitoring. This paper describes the use of spectral features for classification of gait activities based on accelerometric data. The classification is performed by a Gaussian mixture model (GMM) based statistical classifier at the back end. Fifty subjects participated in the experiment and an overall classification accuracy of 86% was achieved using the proposed 25 dimensional features for five different human gait patterns including walking on level surfaces, walking up and down stairs and walking up and down ramps.",

keywords = "Accelerometry, Ambulatory monitoring, Feature extraction, Gait patterns",

author = "Ibrahim, {R. K.} and E. Ambikairajah and B. Celler and Lovell, {N. H.} and L. Kilmartin",

year = "2008",

doi = "10.1049/cp:20080645",

language = "English",

isbn = "9780863419317",

pages = "98--102",

booktitle = "The IET Irish Signals and Systems Conference, ISSC 2008",

publisher = "Institution of Engineering and Technology",

address = "United Kingdom",

edition = "539 CP",

note = "IET Irish Signals and Systems Conference, ISSC 2008 ; Conference date: 18-06-2008 Through 19-06-2008",

}

Ibrahim, RK, Ambikairajah, E, Celler, B, Lovell, NH & Kilmartin, L 2008, Gait patterns classification using spectral features. in The IET Irish Signals and Systems Conference, ISSC 2008: 18-19 June 2008, National University Of Ireland, Galway, Ireland. 539 CP edn, Institution of Engineering and Technology, Stevenage, pp. 98-102, IET Irish Signals and Systems Conference, ISSC 2008, Galway, Ireland, 18/06/08. https://doi.org/10.1049/cp:20080645

Gait patterns classification using spectral features. / Ibrahim, R. K.; Ambikairajah, E.; Celler, B. et al.
The IET Irish Signals and Systems Conference, ISSC 2008: 18-19 June 2008, National University Of Ireland, Galway, Ireland. 539 CP. ed. Stevenage: Institution of Engineering and Technology, 2008. p. 98-102.

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding contribution › peer-review

TY - GEN

T1 - Gait patterns classification using spectral features

AU - Ibrahim, R. K.

AU - Ambikairajah, E.

AU - Celler, B.

AU - Lovell, N. H.

AU - Kilmartin, L.

PY - 2008

Y1 - 2008

N2 - Accelerometry has been shown to be a good tool for ambulatory activity monitoring. This paper describes the use of spectral features for classification of gait activities based on accelerometric data. The classification is performed by a Gaussian mixture model (GMM) based statistical classifier at the back end. Fifty subjects participated in the experiment and an overall classification accuracy of 86% was achieved using the proposed 25 dimensional features for five different human gait patterns including walking on level surfaces, walking up and down stairs and walking up and down ramps.

AB - Accelerometry has been shown to be a good tool for ambulatory activity monitoring. This paper describes the use of spectral features for classification of gait activities based on accelerometric data. The classification is performed by a Gaussian mixture model (GMM) based statistical classifier at the back end. Fifty subjects participated in the experiment and an overall classification accuracy of 86% was achieved using the proposed 25 dimensional features for five different human gait patterns including walking on level surfaces, walking up and down stairs and walking up and down ramps.

KW - Accelerometry

KW - Ambulatory monitoring

KW - Feature extraction

KW - Gait patterns

UR - http://www.scopus.com/inward/record.url?scp=67649990843&partnerID=8YFLogxK

U2 - 10.1049/cp:20080645

DO - 10.1049/cp:20080645

M3 - Conference proceeding contribution

AN - SCOPUS:67649990843

SN - 9780863419317

SP - 98

EP - 102

BT - The IET Irish Signals and Systems Conference, ISSC 2008

PB - Institution of Engineering and Technology

CY - Stevenage

T2 - IET Irish Signals and Systems Conference, ISSC 2008

Y2 - 18 June 2008 through 19 June 2008

ER -

Gait patterns classification using spectral features

Abstract

Other

Keywords

Access to Document

Other files and links

Fingerprint

Cite this