Sparse and low-rank feature extraction for the classification of target's tracking capability

Behnood Rasti; Karl S. Gudmundsson

doi:10.1117/12.2240282

Sparse and low-rank feature extraction for the classification of target's tracking capability

Behnood Rasti^*, Karl S. Gudmundsson

^*Corresponding author for this work

University of Iceland

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

4 Citations (Scopus)

Abstract

A feature extraction-based classification method is proposed in this paper for verifying the capability of human's neck in target tracking. Here, the target moves in predefined trajectory patterns in three difficulty levels. Dataset used for each pattern is obtained from two groups of people, one with whiplash associated disorder (WAD) and asymptomatic group, who behave in both sincere and feign manner. The aim is to verify the WAD group from asymptomatic one and also to discriminate the sincere behavior from the feigned one. Sparse and low-rank feature extraction is proposed to extract the most informative feature from training samples and then each sample is classified into the group which has the highest correlation coefficient with. The classification results are improved by fusing the results of the three patterns.

Original language	English
Title of host publication	Optics and Photonics for Information Processing X
Editors	Khan M. Iftekharuddin, Andres Marquez, Mohammad A. Matin, Abdul A. S. Awwal, Mireya Garcia Vazquez
Publisher	SPIE
ISBN (Electronic)	9781510603318
DOIs	https://doi.org/10.1117/12.2240282
Publication status	Published - 2016
Event	10th Conference on Optics and Photonics for Information Processing - San Diego, United States Duration: 29 Aug 2016 → 30 Aug 2016

Publication series

Name	Proceedings of SPIE - The International Society for Optical Engineering
Volume	9970
ISSN (Print)	0277-786X
ISSN (Electronic)	1996-756X

Conference

Conference	10th Conference on Optics and Photonics for Information Processing
Country/Territory	United States
City	San Diego
Period	29/08/16 → 30/08/16

Bibliographical note

Publisher Copyright:
© 2016 SPIE.

Other keywords

Classification
feature extraction
low-rank
sparsity
target tracking
whiplash associated disorder

Access to Document

10.1117/12.2240282

Cite this

Rasti, B., & Gudmundsson, K. S. (2016). Sparse and low-rank feature extraction for the classification of target's tracking capability. In K. M. Iftekharuddin, A. Marquez, M. A. Matin, A. A. S. Awwal, & M. G. Vazquez (Eds.), Optics and Photonics for Information Processing X [99701U] (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 9970). SPIE. https://doi.org/10.1117/12.2240282

Rasti, Behnood ; Gudmundsson, Karl S. / Sparse and low-rank feature extraction for the classification of target's tracking capability. Optics and Photonics for Information Processing X. editor / Khan M. Iftekharuddin ; Andres Marquez ; Mohammad A. Matin ; Abdul A. S. Awwal ; Mireya Garcia Vazquez. SPIE, 2016. (Proceedings of SPIE - The International Society for Optical Engineering).

@inproceedings{5933ffa2e231488f82ca742fe5156734,

title = "Sparse and low-rank feature extraction for the classification of target's tracking capability",

abstract = "A feature extraction-based classification method is proposed in this paper for verifying the capability of human's neck in target tracking. Here, the target moves in predefined trajectory patterns in three difficulty levels. Dataset used for each pattern is obtained from two groups of people, one with whiplash associated disorder (WAD) and asymptomatic group, who behave in both sincere and feign manner. The aim is to verify the WAD group from asymptomatic one and also to discriminate the sincere behavior from the feigned one. Sparse and low-rank feature extraction is proposed to extract the most informative feature from training samples and then each sample is classified into the group which has the highest correlation coefficient with. The classification results are improved by fusing the results of the three patterns.",

keywords = "Classification, feature extraction, low-rank, sparsity, target tracking, whiplash associated disorder",

author = "Behnood Rasti and Gudmundsson, {Karl S.}",

note = "Publisher Copyright: {\textcopyright} 2016 SPIE.; 10th Conference on Optics and Photonics for Information Processing ; Conference date: 29-08-2016 Through 30-08-2016",

year = "2016",

doi = "10.1117/12.2240282",

language = "English",

series = "Proceedings of SPIE - The International Society for Optical Engineering",

publisher = "SPIE",

editor = "Iftekharuddin, {Khan M.} and Andres Marquez and Matin, {Mohammad A.} and Awwal, {Abdul A. S.} and Vazquez, {Mireya Garcia}",

booktitle = "Optics and Photonics for Information Processing X",

address = "United States",

}

Rasti, B & Gudmundsson, KS 2016, Sparse and low-rank feature extraction for the classification of target's tracking capability. in KM Iftekharuddin, A Marquez, MA Matin, AAS Awwal & MG Vazquez (eds), Optics and Photonics for Information Processing X., 99701U, Proceedings of SPIE - The International Society for Optical Engineering, vol. 9970, SPIE, 10th Conference on Optics and Photonics for Information Processing, San Diego, United States, 29/08/16. https://doi.org/10.1117/12.2240282

Sparse and low-rank feature extraction for the classification of target's tracking capability. / Rasti, Behnood; Gudmundsson, Karl S.
Optics and Photonics for Information Processing X. ed. / Khan M. Iftekharuddin; Andres Marquez; Mohammad A. Matin; Abdul A. S. Awwal; Mireya Garcia Vazquez. SPIE, 2016. 99701U (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 9970).

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

TY - GEN

T1 - Sparse and low-rank feature extraction for the classification of target's tracking capability

AU - Rasti, Behnood

AU - Gudmundsson, Karl S.

PY - 2016

Y1 - 2016

N2 - A feature extraction-based classification method is proposed in this paper for verifying the capability of human's neck in target tracking. Here, the target moves in predefined trajectory patterns in three difficulty levels. Dataset used for each pattern is obtained from two groups of people, one with whiplash associated disorder (WAD) and asymptomatic group, who behave in both sincere and feign manner. The aim is to verify the WAD group from asymptomatic one and also to discriminate the sincere behavior from the feigned one. Sparse and low-rank feature extraction is proposed to extract the most informative feature from training samples and then each sample is classified into the group which has the highest correlation coefficient with. The classification results are improved by fusing the results of the three patterns.

AB - A feature extraction-based classification method is proposed in this paper for verifying the capability of human's neck in target tracking. Here, the target moves in predefined trajectory patterns in three difficulty levels. Dataset used for each pattern is obtained from two groups of people, one with whiplash associated disorder (WAD) and asymptomatic group, who behave in both sincere and feign manner. The aim is to verify the WAD group from asymptomatic one and also to discriminate the sincere behavior from the feigned one. Sparse and low-rank feature extraction is proposed to extract the most informative feature from training samples and then each sample is classified into the group which has the highest correlation coefficient with. The classification results are improved by fusing the results of the three patterns.

KW - Classification

KW - feature extraction

KW - low-rank

KW - sparsity

KW - target tracking

KW - whiplash associated disorder

UR - http://www.scopus.com/inward/record.url?scp=85011096863&partnerID=8YFLogxK

U2 - 10.1117/12.2240282

DO - 10.1117/12.2240282

M3 - Conference contribution

AN - SCOPUS:85011096863

T3 - Proceedings of SPIE - The International Society for Optical Engineering

BT - Optics and Photonics for Information Processing X

A2 - Iftekharuddin, Khan M.

A2 - Marquez, Andres

A2 - Matin, Mohammad A.

A2 - Awwal, Abdul A. S.

A2 - Vazquez, Mireya Garcia

PB - SPIE

T2 - 10th Conference on Optics and Photonics for Information Processing

Y2 - 29 August 2016 through 30 August 2016

ER -

Sparse and low-rank feature extraction for the classification of target's tracking capability

Abstract

Publication series

Conference

Bibliographical note

Other keywords

Access to Document

Fingerprint

Cite this