Optimal Placement of Accelerometers for the Detection of Everyday Activities

Ian Cleland, Basel Kikhia, CD Nugent, Andrey Boytsov, Josef Hallberg, Kåre Synnes, Sally McClean, D Finlay

Research output: Research - peer-reviewArticle

  • 113 Citations

Abstract

This article describes an investigation to determine the optimal placement of accelerometers for the purpose of detecting a range of everyday activities. The paper investigates the effect of combining data from accelerometers placed at various bodily locations on the accuracy of activity detection. Eight healthy males participated within the study. Data were collected from six wireless tri-axial accelerometers placed at the chest, wrist, lower back, hip, thigh and foot. Activities included walking, running on a motorized treadmill, sitting, lying, standing and walking up and down stairs. The Support Vector Machine provided the most accurate detection of activities of all the machine learning algorithms investigated. Although data from all locations provided similar levels of accuracy, the hip was the best single location to record data for activity detection using a Support Vector Machine, providing small but significantly better accuracy than the other investigated locations. Increasing the number of sensing locations from one to two or more statistically increased the accuracy of classification. There was no significant difference in accuracy when using two or more sensors. It was noted, however, that the difference in activity detection using single or multiple accelerometers may be more pronounced when trying to detect finer grain activities. Future work shall therefore investigate the effects of accelerometer placement on a larger range of these activities.
LanguageEnglish
Pages9183
JournalSensors
Volume13
Issue number7
DOIs
StatePublished - 2013

Fingerprint

accelerometers
Accelerometers
Walking
Hip
Thigh
Wrist
Running
Foot
Thorax
Support vector machines
walking
Exercise equipment
Stairs
treadmills
Learning algorithms
thigh
Learning systems
wrist
machine learning
Support Vector Machine

Cite this

Cleland, Ian ; Kikhia, Basel ; Nugent, CD ; Boytsov, Andrey ; Hallberg, Josef ; Synnes, Kåre ; McClean, Sally ; Finlay, D. / Optimal Placement of Accelerometers for the Detection of Everyday Activities. 2013 ; Vol. 13, No. 7. pp. 9183
@article{80d3b0b092bb4ab5b1c40f004c09d3dc,
title = "Optimal Placement of Accelerometers for the Detection of Everyday Activities",
abstract = "This article describes an investigation to determine the optimal placement of accelerometers for the purpose of detecting a range of everyday activities. The paper investigates the effect of combining data from accelerometers placed at various bodily locations on the accuracy of activity detection. Eight healthy males participated within the study. Data were collected from six wireless tri-axial accelerometers placed at the chest, wrist, lower back, hip, thigh and foot. Activities included walking, running on a motorized treadmill, sitting, lying, standing and walking up and down stairs. The Support Vector Machine provided the most accurate detection of activities of all the machine learning algorithms investigated. Although data from all locations provided similar levels of accuracy, the hip was the best single location to record data for activity detection using a Support Vector Machine, providing small but significantly better accuracy than the other investigated locations. Increasing the number of sensing locations from one to two or more statistically increased the accuracy of classification. There was no significant difference in accuracy when using two or more sensors. It was noted, however, that the difference in activity detection using single or multiple accelerometers may be more pronounced when trying to detect finer grain activities. Future work shall therefore investigate the effects of accelerometer placement on a larger range of these activities.",
author = "Ian Cleland and Basel Kikhia and CD Nugent and Andrey Boytsov and Josef Hallberg and Kåre Synnes and Sally McClean and D Finlay",
year = "2013",
doi = "10.3390/s130709183",
volume = "13",
pages = "9183",
number = "7",

}

Optimal Placement of Accelerometers for the Detection of Everyday Activities. / Cleland, Ian; Kikhia, Basel; Nugent, CD; Boytsov, Andrey; Hallberg, Josef; Synnes, Kåre; McClean, Sally; Finlay, D.

Vol. 13, No. 7, 2013, p. 9183.

Research output: Research - peer-reviewArticle

TY - JOUR

T1 - Optimal Placement of Accelerometers for the Detection of Everyday Activities

AU - Cleland,Ian

AU - Kikhia,Basel

AU - Nugent,CD

AU - Boytsov,Andrey

AU - Hallberg,Josef

AU - Synnes,Kåre

AU - McClean,Sally

AU - Finlay,D

PY - 2013

Y1 - 2013

N2 - This article describes an investigation to determine the optimal placement of accelerometers for the purpose of detecting a range of everyday activities. The paper investigates the effect of combining data from accelerometers placed at various bodily locations on the accuracy of activity detection. Eight healthy males participated within the study. Data were collected from six wireless tri-axial accelerometers placed at the chest, wrist, lower back, hip, thigh and foot. Activities included walking, running on a motorized treadmill, sitting, lying, standing and walking up and down stairs. The Support Vector Machine provided the most accurate detection of activities of all the machine learning algorithms investigated. Although data from all locations provided similar levels of accuracy, the hip was the best single location to record data for activity detection using a Support Vector Machine, providing small but significantly better accuracy than the other investigated locations. Increasing the number of sensing locations from one to two or more statistically increased the accuracy of classification. There was no significant difference in accuracy when using two or more sensors. It was noted, however, that the difference in activity detection using single or multiple accelerometers may be more pronounced when trying to detect finer grain activities. Future work shall therefore investigate the effects of accelerometer placement on a larger range of these activities.

AB - This article describes an investigation to determine the optimal placement of accelerometers for the purpose of detecting a range of everyday activities. The paper investigates the effect of combining data from accelerometers placed at various bodily locations on the accuracy of activity detection. Eight healthy males participated within the study. Data were collected from six wireless tri-axial accelerometers placed at the chest, wrist, lower back, hip, thigh and foot. Activities included walking, running on a motorized treadmill, sitting, lying, standing and walking up and down stairs. The Support Vector Machine provided the most accurate detection of activities of all the machine learning algorithms investigated. Although data from all locations provided similar levels of accuracy, the hip was the best single location to record data for activity detection using a Support Vector Machine, providing small but significantly better accuracy than the other investigated locations. Increasing the number of sensing locations from one to two or more statistically increased the accuracy of classification. There was no significant difference in accuracy when using two or more sensors. It was noted, however, that the difference in activity detection using single or multiple accelerometers may be more pronounced when trying to detect finer grain activities. Future work shall therefore investigate the effects of accelerometer placement on a larger range of these activities.

U2 - 10.3390/s130709183

DO - 10.3390/s130709183

M3 - Article

VL - 13

SP - 9183

IS - 7

ER -

Cleland I, Kikhia B, Nugent CD, Boytsov A, Hallberg J, Synnes K et al. Optimal Placement of Accelerometers for the Detection of Everyday Activities. 2013;13(7):9183. Available from, DOI: 10.3390/s130709183