Adaptive walk detection algorithm using activity counts

Matin Kheirkhahan; Zhiguo Chen; Duane B. Corbett; Amal A. Wanigatunga; Todd M. Manini; Sanjay Ranka

doi:10.1109/BHI.2017.7897230

Adaptive walk detection algorithm using activity counts

Matin Kheirkhahan, Zhiguo Chen, Duane B. Corbett, Amal A. Wanigatunga, Todd M. Manini, Sanjay Ranka

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

2 Scopus citations

Abstract

Accelerometers have been the dominant device used for physical activity assessment studies. They are comfortable to wear at different locations and can accurately measure acceleration. Although, accurate methods for detecting walking in the lab and free-living condition using raw acceleration data exist, these algorithms are not useful for determining indoor movements that correspond to short walking bouts (< 2 minutes). In this paper, we present a new method that is adaptive to a small window of activity count data (10-15 seconds) and robust to within and between subject variability. The adaptive walking detection algorithm is evaluated using 22 adults and walks with a variety of durations ranging from 10 seconds to 8 minutes. The proposed algorithm showed high accuracy for all the walking periods and was significantly better for intervals shorter than 2 minutes.

Original language	English (US)
Title of host publication	2017 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2017
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	161-164
Number of pages	4
ISBN (Electronic)	9781509041794
DOIs	https://doi.org/10.1109/BHI.2017.7897230
State	Published - Apr 11 2017
Externally published	Yes
Event	4th IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2017 - Orlando, United States Duration: Feb 16 2017 → Feb 19 2017

Publication series

Name	2017 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2017

Conference

Conference	4th IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2017
Country/Territory	United States
City	Orlando
Period	2/16/17 → 2/19/17

ASJC Scopus subject areas

Health Informatics
Computer Science Applications
Biomedical Engineering

Access to Document

10.1109/BHI.2017.7897230

Cite this

Kheirkhahan, M., Chen, Z., Corbett, D. B., Wanigatunga, A. A., Manini, T. M., & Ranka, S. (2017). Adaptive walk detection algorithm using activity counts. In 2017 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2017 (pp. 161-164). Article 7897230 (2017 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2017). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/BHI.2017.7897230

Adaptive walk detection algorithm using activity counts. / Kheirkhahan, Matin; Chen, Zhiguo; Corbett, Duane B. et al.
2017 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2017. Institute of Electrical and Electronics Engineers Inc., 2017. p. 161-164 7897230 (2017 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2017).

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

Kheirkhahan, M, Chen, Z, Corbett, DB, Wanigatunga, AA, Manini, TM & Ranka, S 2017, Adaptive walk detection algorithm using activity counts. in 2017 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2017., 7897230, 2017 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2017, Institute of Electrical and Electronics Engineers Inc., pp. 161-164, 4th IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2017, Orlando, United States, 2/16/17. https://doi.org/10.1109/BHI.2017.7897230

Kheirkhahan M, Chen Z, Corbett DB, Wanigatunga AA, Manini TM, Ranka S. Adaptive walk detection algorithm using activity counts. In 2017 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2017. Institute of Electrical and Electronics Engineers Inc. 2017. p. 161-164. 7897230. (2017 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2017). doi: 10.1109/BHI.2017.7897230

Kheirkhahan, Matin ; Chen, Zhiguo ; Corbett, Duane B. et al. / Adaptive walk detection algorithm using activity counts. 2017 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2017. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 161-164 (2017 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2017).

@inproceedings{10c6ffceaee242c683fad964f5f074e4,

title = "Adaptive walk detection algorithm using activity counts",

abstract = "Accelerometers have been the dominant device used for physical activity assessment studies. They are comfortable to wear at different locations and can accurately measure acceleration. Although, accurate methods for detecting walking in the lab and free-living condition using raw acceleration data exist, these algorithms are not useful for determining indoor movements that correspond to short walking bouts (< 2 minutes). In this paper, we present a new method that is adaptive to a small window of activity count data (10-15 seconds) and robust to within and between subject variability. The adaptive walking detection algorithm is evaluated using 22 adults and walks with a variety of durations ranging from 10 seconds to 8 minutes. The proposed algorithm showed high accuracy for all the walking periods and was significantly better for intervals shorter than 2 minutes.",

author = "Matin Kheirkhahan and Zhiguo Chen and Corbett, {Duane B.} and Wanigatunga, {Amal A.} and Manini, {Todd M.} and Sanjay Ranka",

note = "Publisher Copyright: {\textcopyright} 2017 IEEE.; 4th IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2017 ; Conference date: 16-02-2017 Through 19-02-2017",

year = "2017",

month = apr,

day = "11",

doi = "10.1109/BHI.2017.7897230",

language = "English (US)",

series = "2017 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2017",

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

pages = "161--164",

booktitle = "2017 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2017",

}

TY - GEN

T1 - Adaptive walk detection algorithm using activity counts

AU - Kheirkhahan, Matin

AU - Chen, Zhiguo

AU - Corbett, Duane B.

AU - Wanigatunga, Amal A.

AU - Manini, Todd M.

AU - Ranka, Sanjay

PY - 2017/4/11

Y1 - 2017/4/11

N2 - Accelerometers have been the dominant device used for physical activity assessment studies. They are comfortable to wear at different locations and can accurately measure acceleration. Although, accurate methods for detecting walking in the lab and free-living condition using raw acceleration data exist, these algorithms are not useful for determining indoor movements that correspond to short walking bouts (< 2 minutes). In this paper, we present a new method that is adaptive to a small window of activity count data (10-15 seconds) and robust to within and between subject variability. The adaptive walking detection algorithm is evaluated using 22 adults and walks with a variety of durations ranging from 10 seconds to 8 minutes. The proposed algorithm showed high accuracy for all the walking periods and was significantly better for intervals shorter than 2 minutes.

AB - Accelerometers have been the dominant device used for physical activity assessment studies. They are comfortable to wear at different locations and can accurately measure acceleration. Although, accurate methods for detecting walking in the lab and free-living condition using raw acceleration data exist, these algorithms are not useful for determining indoor movements that correspond to short walking bouts (< 2 minutes). In this paper, we present a new method that is adaptive to a small window of activity count data (10-15 seconds) and robust to within and between subject variability. The adaptive walking detection algorithm is evaluated using 22 adults and walks with a variety of durations ranging from 10 seconds to 8 minutes. The proposed algorithm showed high accuracy for all the walking periods and was significantly better for intervals shorter than 2 minutes.

UR - http://www.scopus.com/inward/record.url?scp=85018411630&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85018411630&partnerID=8YFLogxK

U2 - 10.1109/BHI.2017.7897230

DO - 10.1109/BHI.2017.7897230

M3 - Conference contribution

AN - SCOPUS:85018411630

T3 - 2017 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2017

SP - 161

EP - 164

BT - 2017 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2017

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 4th IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2017

Y2 - 16 February 2017 through 19 February 2017

ER -

Adaptive walk detection algorithm using activity counts

Abstract

Publication series

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this