Research Papers

Posture and Movement Classification: The Comparison of Tri-Axial Accelerometer Numbers and Anatomical Placement

[+] Author and Article Information
Emma Fortune, Vipul A. Lugade

Motion Analysis Laboratory,
Division of Orthopedic Research,
Mayo Clinic,
Rochester, MN 55905

Kenton R. Kaufman

Motion Analysis Laboratory,
Division of Orthopedic Research,
Mayo Clinic,
Rochester, MN 55905
e-mail: Kaufman.Kenton@mayo.edu

1Corresponding author.

Contributed by the Bioengineering Division of ASME for publication in the Journal of Biomechanical Engineering. Manuscript received August 13, 2013; final manuscript received November 26, 2013; accepted manuscript posted December 12, 2013; published online April 10, 2014. Assoc. Editor: Paul Rullkoetter.

J Biomech Eng 136(5), 051003 (Apr 10, 2014) (8 pages) Paper No: BIO-13-1363; doi: 10.1115/1.4026230 History: Received August 13, 2013; Revised November 26, 2013; Accepted December 12, 2013

Patient compliance is important when assessing movement, particularly in a free-living environment when patients are asked to don their own accelerometers. Reducing the number of accelerometers could increase patient compliance. The aims of this study were (1) to determine and compare the validity of different accelerometer combinations and placements for a previously developed posture and dynamic movement identification algorithm. Custom-built activity monitors, each containing one tri-axial accelerometer, were placed on the ankles, right thigh, and waist of 12 healthy adults. Subjects performed a protocol in the laboratory including static orientations of standing, sitting, and lying down, and dynamic movements of walking, jogging, transitions between postures, and fidgeting to simulate free-living activity. When only one accelerometer was used, the thigh was found to be the optimal placement to identify both movement and static postures, with a misclassification error of 10%, and demonstrated the greatest accuracy for walking/fidgeting and jogging classification with sensitivities and positive predictive value (PPVs) greater than 93%. When two accelerometers were used, the waist-thigh accelerometers identified movement and static postures with greater accuracy than the thigh-ankle accelerometers (with a misclassification error of 11% compared to 17%). However, the thigh-ankle accelerometers demonstrated the greatest accuracy for walking/ fidgeting and jogging classification with sensitivities and PPVs greater than 93%. Movement can be accurately classified in healthy adults using tri-axial accelerometers placed on one or two of the following sites: waist, thigh, or ankle. Posture and transitions require an accelerometer placed on the waist and an accelerometer placed on the thigh.

Copyright © 2014 by ASME
Topics: Accelerometers
Your Session has timed out. Please sign back in to continue.


Troiano, R. P., Berrigan, D., Dodd, K. W., Mâsse, L. C., Tilert, T., and Mcdowell, M., 2008, “Physical Activity in the United States Measured by Accelerometer,” Med. Sci. Sports Exercise, 40(1), pp. 181–188. [CrossRef]
Matthews, C. E., Hagströmer, M., Pober, D. M., and Bowles, H. R., 2012, “Best Practices for Using Physical Activity Monitors in Population-Based Research,” Med. Sci. Sports Exercise, 44(1), pp. S68–S76. [CrossRef]
Hagstromer, M., Oja, P., and Sjostrom, M., 2007, “Physical Activity and Inactivity in an Adult Population Assessed by Accelerometry,” Med. Sci. Sports Exercise, 39(9), pp. 1502–1508. [CrossRef]
Mattocks, C., Ness, A., Leary, S., Tilling, K., Blair, S., Shield, J., Deere, K., Saunders, J., Kirkby, J., and Smith, G., 2008, “Use of Accelerometers in a Large Field-Based Study of Children: Protocols, Design Issues, and Effects on Precision,” J. Phys. Activity Health, 5, pp. S98–S111.
Atallah, L., Lo, B., King, R., and Guang-Zhong, Y., 2011, “Sensor Positioning for Activity Recognition Using Wearable Accelerometers,” IEEE Trans. Biomed. Circuits Syst., 5(4), pp. 320–329. [CrossRef] [PubMed]
Allen, F. R., Ambikairajah, E., Lovell, N. H., and Celler, B. G., 2006, “Classification of a Known Sequence of Motions and Postures From Accelerometry Data Using Adapted Gaussian Mixture Models,” Physiol. Meas., 27(10), pp. 935–951. [CrossRef] [PubMed]
Godfrey, A., Conway, R., Meagher, D., and O'Laighin, G., 2008, “Direct Measurement of Human Movement by Accelerometry,” Med. Eng. Phys., 30(10), pp. 1364–1386. [CrossRef] [PubMed]
Yang, C. C., and Hsu, Y. L., 2010, “A Review of Accelerometry-Based Wearable Motion Detectors for Physical Activity Monitoring,” Sensors (Basel), 10(8), pp. 7772–7788. [CrossRef] [PubMed]
Bussmann, J. B., Martens, W. L., Tulen, J. H., Schasfoort, F. C., Van Den Berg-Emons, H. J., and Stam, H. J., 2001, “Measuring Daily Behavior Using Ambulatory Accelerometry: The Activity Monitor,” Behav. Res. Methods Instrum. Comput., 33(3), pp. 349–356. [CrossRef] [PubMed]
Bao, L., and Intille, S., 2004, “Activity Recognition From User-Annotated Acceleration Data,” IEEE Pervasive Comput., 3001, pp. 1–17. [CrossRef]
Veltink, P. H., Bussmann, H. B., De Vries, W., Martens, W. L., and Van Lummel, R. C., 1996, “Detection of Static and Dynamic Activities Using Uniaxial Accelerometers,” IEEE Trans. Rehabil. Eng., 4(4), pp. 375–385. [CrossRef] [PubMed]
Aminian, K., Robert, P., Buchser, E. E., Rutschmann, B., Hayoz, D., and Depairon, M., 1999, “Physical Activity Monitoring Based on Accelerometry: Validation and Comparison With Video Observation,” Med. Biol. Eng. Comput., 37(3), pp. 304–308. [CrossRef] [PubMed]
Foerster, F., Smeja, M., and Fahrenberg, J., 1999, “Detection of Posture and Motion by Accelerometry: A Validation Study in Ambulatory Monitoring,” Comput. Human Behav., 15(5), pp. 571–583. [CrossRef]
Grant, P. M., Ryan, C. G., Tigbe, W. W., and Granat, M. H., 2006, “The Validation of a Novel Activity Monitor in the Measurement of Posture and Motion During Everyday Activities,” Br. J. Sports Med., 40(12), pp. 992–997. [CrossRef] [PubMed]
Karantonis, D. M., Narayanan, M. R., Mathie, M., Lovell, N. H., and Celler, B. G., 2006, “Implementation of a Real-Time Human Movement Classifier Using a Triaxial Accelerometer for Ambulatory Monitoring,” IEEE Trans. Inf. Technol. Biomed., 10(1), pp. 156–167. [CrossRef] [PubMed]
Dijkstra, B., Kamsma, Y., and Zijlstra, W., 2010, “Detection of Gait and Postures Using a Miniaturised Triaxial Accelerometer-Based System: Accuracy in Community-Dwelling Older Adults,” Age Ageing, 39(2), pp. 259–262. [CrossRef] [PubMed]
Rodriguez-Martin, D., Samà, A., Perez-Lopez, C., Català, A., Cabestany, J., and Rodriguez-Molinero, A., 2013, “Svm-Based Posture Identification With a Single Waist-Located Triaxial Accelerometer,” Expert Syst. Appl., 40(18), pp. 7203–7211. [CrossRef]
Salarian, A., Russmann, H., Vingerhoets, F. J., Burkhard, P. R., and Aminian, K., 2007, “Ambulatory Monitoring of Physical Activities in Patients With Parkinson's Disease,” IEEE Trans. Biomed. Eng., 54(12), pp. 2296–2299. [CrossRef] [PubMed]
Morlock, M., Schneider, E., Bluhm, A., Vollmer, M., Bergmann, G., Muller, V., and Honl, M., 2001, “Duration and Frequency of Every Day Activities in Total Hip Patients,” J. Biomech., 34(7), pp. 873–881. [CrossRef] [PubMed]
Farr, J. N., Going, S. B., Lohman, T. G., Rankin, L., Kasle, S., Cornett, M., and Cussler, E., 2008, “Physical Activity Levels in Patients With Early Knee Osteoarthritis Measured by Accelerometry,” Arthritis Rheum., 59(9), pp. 1229–1236. [CrossRef] [PubMed]
Oliver, M., Schofield, G. M., Badland, H. M., and Shepherd, J., 2010, “Utility of Accelerometer Thresholds for Classifying Sitting in Office Workers,” Prev. Med., 51(5), pp. 357–360. [CrossRef] [PubMed]
Kang, D. W., Choi, J. S., Lee, J. W., Chung, S. C., Park, S. J., and Tack, G. R., 2010, “Real-Time Elderly Activity Monitoring System Based on a Tri-Axial Accelerometer,” Disabil. Rehabil. Assist Technol., 5(4), pp. 247–253. [CrossRef] [PubMed]
Najafi, B., Aminian, K., Paraschiv-Ionescu, A., Loew, F., Bula, C. J., and Robert, P., 2003, “Ambulatory System for Human Motion Analysis Using a Kinematic Sensor: Monitoring of Daily Physical Activity in the Elderly,” IEEE Trans. Biomed. Eng., 50(6), pp. 711–723. [CrossRef] [PubMed]
Bouten, C. V., Koekkoek, K. T., Verduin, M., Kodde, R., and Janssen, J. D., 1997, “A Triaxial Accelerometer and Portable Data Processing Unit for the Assessment of Daily Physical Activity,” IEEE Trans. Biomed. Eng., 44(3), pp. 136–147. [CrossRef] [PubMed]
Preece, S. J., Goulermas, J. Y., Kenney, L. P., and Howard, D., 2009, “A Comparison of Feature Extraction Methods for the Classification of Dynamic Activities From Accelerometer Data,” IEEE Trans. Biomed. Eng., 56(3), pp. 871–879. [CrossRef] [PubMed]
Gjoreski, H., Lustrek, M., and Gams, M., 2011, “Accelerometer Placement for Posture Recognition and Fall Detection,” 7th International Conference on Intelligent Environments, IEEE, Nottingham, UK, pp. 47–54.
Lugade, V., Fortune, E., Morrow, M., and Kaufman, K., 2013, “Validity of Using Tri-Axial Accelerometers to Measure Human Movement—Part I: Posture and Movement Detection,” Med. Eng. Phys. (in press). [CrossRef]
Bidargaddi, N., Sarela, A., Klingbeil, L., and Karunanithi, M., 2007, “Detecting Walking Activity in Cardiac Rehabilitation by Using Accelerometer,” 3rd International Conference on Intelligent Sensors, Sensor Networks and Information, IEEE, Melbourne, Australia, pp. 555–560.
Mathie, M. J., Coster, A. C., Lovell, N. H., and Celler, B. G., 2003, “Detection of Daily Physical Activities Using a Triaxial Accelerometer,” Med. Biol. Eng. Comput., 41(3), pp. 296–301. [CrossRef] [PubMed]
Lyons, G. M., Culhane, K. M., Hilton, D., Grace, P. A., and Lyons, D., 2005, “A Description of an Accelerometer-Based Mobility Monitoring Technique,” Med. Eng. Phys., 27(6), pp. 497–504. [CrossRef] [PubMed]
Hammersley, M., 1987, “Some Notes on the Terms ‘Validity’ and ‘Reliability'[1],” Br. J. Educ. Res., 13(1), pp. 73–82. [CrossRef]
Landis, J. R., and Koch, G. G., 1977, “The Measurement of Observer Agreement for Categorical Data,” Biometrics, 33, pp. 159–174. [CrossRef] [PubMed]
Ridgers, N. D., Salmon, J., Ridley, K., O'Connell, E., Arundell, L., and Timperio, A., 2012, “Agreement between Activpal and Actigraph for Assessing Children's Sedentary Time,” Int. J. Behav. Nutr. Phys. Act., 9:15, pp. 1–8. [CrossRef] [PubMed]
Bland, J. M., and Altman, D. G., 1999, “Measuring Agreement in Method Comparison Studies,” Stat. Methods Med. Res., 8(2), pp. 135–160. [CrossRef] [PubMed]
Sirard, J. R., and Slater, M. E., 2009, “Compliance With Wearing Physical Activity Accelerometers in High School Students,” J. Phys. Act. Health, 6(1), pp. S148–S155. [PubMed]
Tapia, E. M., Intille, S. S., Haskell, W., Larson, K., Wright, J., King, A., and Friedman, R., 2007, “Real-Time Recognition of Physical Activities and Their Intensities Using Wireless Accelerometers and a Heart Rate Monitor,” 11th IEEE International Symposium on Wearable Computers, pp. 37–40.
Godfrey, A., Culhane, K. M., and Lyons, G. M., 2007, “Comparison of the Performance of the Activpal Professional Physical Activity Logger to a Discrete Accelerometer-Based Activity Monitor,” Med. Eng. Phys., 29(8), pp. 930–934. [CrossRef] [PubMed]


Grahic Jump Location
Fig. 3

Sensitivity when identifying static orientations and dynamic movements compared to video identification using (a) a waist accelerometer, (b) a thigh accelerometer, (c) an ankle accelerometer, and (d) the central line (dashed) represents the median, the edges of the box are the 25th and 75th percentiles, and the whiskers extend to ±1.5 of the interquartile range. Outliers beyond this range are labeled as +. Trans: Transitions.

Grahic Jump Location
Fig. 4

Positive predictive value (PPV) when identifying static orientations and dynamic movements compared to video identification using (a) a waist accelerometer, (b) a thigh accelerometer, (c) an ankle accelerometer, and (d) thigh and ankle accelerometers. The central line (dashed) represents the median, the edges of the box are the 25th and 75th percentiles, and the whiskers extend to ±1.5 of the interquartile range. Outliers beyond this range are labeled as +. For the PPV of jogging in (a), the median value and the 75th percentile are equal to 100%.

Grahic Jump Location
Fig. 2

Decision algorithm for the possible posture and movement classifications determined from the accelerometer data when using (a) single waist or ankle, (b) a single thigh, and (c) thigh and ankle accelerometers. SMA is signal magnitude area and CWT is continuous wavelet transform

Grahic Jump Location
Fig. 1

Mean signal magnitude area per second and corresponding movement and jogging thresholds for (a) waist, (b) thigh, and (c) acceleration data from one subject chosen at random during the simulated free living protocol

Grahic Jump Location
Fig. 5

Bland-Altman plots demonstrating error in identifying walking/fidgeting and jogging activities when using accelerometer compared to video identification for (a) a waist accelerometer, (b) a thigh accelerometer, (c) an ankle accelerometer, and (d) thigh and ankle accelerometers. The dashed line represents the mean, while the solid lines represent the repeatability coefficients (± 1.96 SD). ICC(A,1) values are also presented.



Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In