Multiscale PCA to distinguish regular and irregular surfaces using tri axial head and trunk acceleration signals

Gita Pendharkar; Ganesh R. Naik; Amit Acharyya; Hung T. Nguyen

doi:10.1109/EMBC.2015.7319301

Multiscale PCA to distinguish regular and irregular surfaces using tri axial head and trunk acceleration signals

Gita Pendharkar, Ganesh R. Naik, Amit Acharyya, Hung T. Nguyen

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

3 Citations (Scopus)

Abstract

This study uses multiscale principal component analysis (MSPCA) signal processing technique in order to distinguish the two different surfaces, tiled (regular) and cobbled (irregular) using accelerometry data (recorded from MTx sensors). Two MTx sensors were placed on the head and trunk of the subject while the subject walked freely over the regular and irregular surfaces during a free walk. 3D acceleration signals, vertical, medio lateral (ML) and anterior-posterior (AP) were recorded for the head and trunk segments and compared for the free walk on a defined route. The magnitude of the ML and AP acceleration obtained from the MTx sensors (for both head & trunk) was higher when walking over the irregular (cobbled) surface as compared to the regular (tiled) surface. The accelerometry data was initially analysed using MSPCA and was later classified using naïve Bayesian classifier with >86% accuracy. This research study demonstrates that MSPCA can be used to distinguish the regular and irregular surfaces. The proposed method could be very useful as an automated method for classification of the two surfaces.

Original language	English
Title of host publication	2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)
Place of Publication	Milan
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	4122-4125
Number of pages	4
ISBN (Electronic)	9781424492718, 9781424492701
DOIs	https://doi.org/10.1109/EMBC.2015.7319301
Publication status	Published - 5 Nov 2015
Externally published	Yes
Event	37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society - Milan, Italy Duration: 25 Aug 2015 → 29 Aug 2015 Conference number: 37 https://ieeexplore.ieee.org/xpl/conhome/7302811/proceeding

Publication series

Name	Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
Volume	2015-November
ISSN (Print)	1557-170X

Conference

Conference	37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society
Abbreviated title	EMBC 2015
Country/Territory	Italy
City	Milan
Period	25/08/15 → 29/08/15
Internet address	https://ieeexplore.ieee.org/xpl/conhome/7302811/proceeding

Keywords

multiscale principal component analysis (MSPCA)
accelerometry data
MTx sensors

Access to Document

10.1109/EMBC.2015.7319301Licence: In Copyright

Cite this

Pendharkar, G., Naik, G. R., Acharyya, A., & Nguyen, H. T. (2015). Multiscale PCA to distinguish regular and irregular surfaces using tri axial head and trunk acceleration signals. In 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) (pp. 4122-4125). (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS; Vol. 2015-November). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/EMBC.2015.7319301

Pendharkar, Gita ; Naik, Ganesh R. ; Acharyya, Amit et al. / Multiscale PCA to distinguish regular and irregular surfaces using tri axial head and trunk acceleration signals. 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). Milan : Institute of Electrical and Electronics Engineers Inc., 2015. pp. 4122-4125 (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS).

@inproceedings{102cbc2cd2a74202a267b00e02371aba,

title = "Multiscale PCA to distinguish regular and irregular surfaces using tri axial head and trunk acceleration signals",

abstract = "This study uses multiscale principal component analysis (MSPCA) signal processing technique in order to distinguish the two different surfaces, tiled (regular) and cobbled (irregular) using accelerometry data (recorded from MTx sensors). Two MTx sensors were placed on the head and trunk of the subject while the subject walked freely over the regular and irregular surfaces during a free walk. 3D acceleration signals, vertical, medio lateral (ML) and anterior-posterior (AP) were recorded for the head and trunk segments and compared for the free walk on a defined route. The magnitude of the ML and AP acceleration obtained from the MTx sensors (for both head & trunk) was higher when walking over the irregular (cobbled) surface as compared to the regular (tiled) surface. The accelerometry data was initially analysed using MSPCA and was later classified using na{\"i}ve Bayesian classifier with >86% accuracy. This research study demonstrates that MSPCA can be used to distinguish the regular and irregular surfaces. The proposed method could be very useful as an automated method for classification of the two surfaces.",

keywords = "multiscale principal component analysis (MSPCA), accelerometry data, MTx sensors",

author = "Gita Pendharkar and Naik, {Ganesh R.} and Amit Acharyya and Nguyen, {Hung T.}",

year = "2015",

month = nov,

day = "5",

doi = "10.1109/EMBC.2015.7319301",

language = "English",

series = "Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "4122--4125",

booktitle = "2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)",

note = "37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2015 ; Conference date: 25-08-2015 Through 29-08-2015",

url = "https://ieeexplore.ieee.org/xpl/conhome/7302811/proceeding",

}

Pendharkar, G, Naik, GR, Acharyya, A & Nguyen, HT 2015, Multiscale PCA to distinguish regular and irregular surfaces using tri axial head and trunk acceleration signals. in 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS, vol. 2015-November, Institute of Electrical and Electronics Engineers Inc., Milan, pp. 4122-4125, 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Milan, Italy, 25/08/15. https://doi.org/10.1109/EMBC.2015.7319301

Multiscale PCA to distinguish regular and irregular surfaces using tri axial head and trunk acceleration signals. / Pendharkar, Gita; Naik, Ganesh R.; Acharyya, Amit et al.

2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). Milan : Institute of Electrical and Electronics Engineers Inc., 2015. p. 4122-4125 (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS; Vol. 2015-November).

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

TY - GEN

T1 - Multiscale PCA to distinguish regular and irregular surfaces using tri axial head and trunk acceleration signals

AU - Pendharkar, Gita

AU - Naik, Ganesh R.

AU - Acharyya, Amit

AU - Nguyen, Hung T.

N1 - Conference code: 37

PY - 2015/11/5

Y1 - 2015/11/5

N2 - This study uses multiscale principal component analysis (MSPCA) signal processing technique in order to distinguish the two different surfaces, tiled (regular) and cobbled (irregular) using accelerometry data (recorded from MTx sensors). Two MTx sensors were placed on the head and trunk of the subject while the subject walked freely over the regular and irregular surfaces during a free walk. 3D acceleration signals, vertical, medio lateral (ML) and anterior-posterior (AP) were recorded for the head and trunk segments and compared for the free walk on a defined route. The magnitude of the ML and AP acceleration obtained from the MTx sensors (for both head & trunk) was higher when walking over the irregular (cobbled) surface as compared to the regular (tiled) surface. The accelerometry data was initially analysed using MSPCA and was later classified using naïve Bayesian classifier with >86% accuracy. This research study demonstrates that MSPCA can be used to distinguish the regular and irregular surfaces. The proposed method could be very useful as an automated method for classification of the two surfaces.

AB - This study uses multiscale principal component analysis (MSPCA) signal processing technique in order to distinguish the two different surfaces, tiled (regular) and cobbled (irregular) using accelerometry data (recorded from MTx sensors). Two MTx sensors were placed on the head and trunk of the subject while the subject walked freely over the regular and irregular surfaces during a free walk. 3D acceleration signals, vertical, medio lateral (ML) and anterior-posterior (AP) were recorded for the head and trunk segments and compared for the free walk on a defined route. The magnitude of the ML and AP acceleration obtained from the MTx sensors (for both head & trunk) was higher when walking over the irregular (cobbled) surface as compared to the regular (tiled) surface. The accelerometry data was initially analysed using MSPCA and was later classified using naïve Bayesian classifier with >86% accuracy. This research study demonstrates that MSPCA can be used to distinguish the regular and irregular surfaces. The proposed method could be very useful as an automated method for classification of the two surfaces.

KW - multiscale principal component analysis (MSPCA)

KW - accelerometry data

KW - MTx sensors

UR - http://www.scopus.com/inward/record.url?scp=84953206175&partnerID=8YFLogxK

U2 - 10.1109/EMBC.2015.7319301

DO - 10.1109/EMBC.2015.7319301

M3 - Conference contribution

C2 - 26737201

AN - SCOPUS:84953206175

T3 - Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS

SP - 4122

EP - 4125

BT - 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

PB - Institute of Electrical and Electronics Engineers Inc.

CY - Milan

T2 - 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society

Y2 - 25 August 2015 through 29 August 2015

ER -

Pendharkar G, Naik GR, Acharyya A, Nguyen HT. Multiscale PCA to distinguish regular and irregular surfaces using tri axial head and trunk acceleration signals. In 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). Milan: Institute of Electrical and Electronics Engineers Inc. 2015. p. 4122-4125. (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS). https://doi.org/10.1109/EMBC.2015.7319301

Multiscale PCA to distinguish regular and irregular surfaces using tri axial head and trunk acceleration signals

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this