Wrist-Gathered Acceleration Data and their Correlation with Physical Activity in the Elderly
International Journal of Biomedical Science and Engineering
Volume 2, Issue 5, October 2014, Pages: 38-44
Received: Oct. 16, 2014;
Accepted: Oct. 29, 2014;
Published: Nov. 10, 2014
Views 3345 Downloads 199
Amy Papadopoulos, AFrame Digital, Inc., Vienna, VA, USA
Nicolas Vivaldi, AFrame Digital, Inc., Vienna, VA, USA; Department of Biomedical Engineering, George Washington University, Washington, DC, USA
Cindy Crump, AFrame Digital, Inc., Vienna, VA, USA; The Center for Study of Chronic Illness and Disability, George Mason University, Fairfax, VA, USA
Christine Tsien Silvers, AFrame Digital, Inc., Vienna, VA, USA; Children’s Hospital Informatics Program, Children’s Hospital, Boston, MA, USA
Estimating physical activity in the elderly from wrist-gathered acceleration data was studied. Thirty individuals (65+ years) were video-recorded while wearing a wrist device and going about their normal activities within their regular living environment for four hours each. Acceleration data were summarized into an activity value [via the “differential signal magnitude” (DSM) method] and compared to metabolic equivalent of task (MET) values determined by video analysis for each time period (“epoch”). Different sampling rates and epoch sizes were evaluated. Sampling at 4 Hz and using 60-second epochs provided the best results, with a moderate Pearson’s correlation coefficient of 0.58 between DSM activity values and MET values. The area under the receiver operating characteristic curve (AUC) for classifying each minute of data as active (MET >= 2.0) versus moderately active (MET > 1.2 and < 2.0) was 0.87 (sensitivity 80%, specificity 79%). DSM activity values (sampling at 4 Hz) were compared to the widely known signal magnitude area (SMA) values (requiring low-pass filtering and sampling at 40 Hz), with an excellent correlation of 0.994.
Christine Tsien Silvers,
Wrist-Gathered Acceleration Data and their Correlation with Physical Activity in the Elderly, International Journal of Biomedical Science and Engineering.
Vol. 2, No. 5,
2014, pp. 38-44.
Healthy People 2020, HealthyPeople.gov, managed by the U.S. Department of Health and Human Services, Washington, DC, last updated February 6, 2013.
R. Troiano, D. Berrigan, K. Dodd, L. Masse, T. Tilert, and M. McDowell, “Physical activity in the United States measured by accelerometer,” Medicine & Science in Sports & Exercise, pp. 181-188, 2007.
T. Wong, J. Webster, H. Montoye, and R. Washburn, “Portable accelerometer device for measuring human energy expenditure,” IEEE Trans. Biomed. Eng., vol. 28, pp. 467-471, 1981.
H. Gjoreski, M. Lustrek, and M. Gams, “Accelerometer placement for posture recognition and fall detection,” 2011 Seventh International Conference on Intelligent Environments, pp. 47-54, 2011.
W. Yeoh, I. Pek, Y. Yong, X. Chen, and A. Waluyo, “Ambulatory monitoring of human posture and walking speed using wearable accelerometer sensors,” 30th Annual International IEEE EMBS Conference, Vancouver, British Columbia, Canada, pp. 5184-5187, August, 2008.
G. Bieber, P. Koldrack, C. Sablowski, C. Peter, and B. Urban, “Mobile physical activity recognition of stand-up and sit-down transitions for user behavior analysis,” PETRA 2010, Samos, Greece, June 2010.
D. Kang, J. Choi, G. Tack, B. Lee, J. Lee, S. Chung, and S. Park, “Real-time elderly activity monitoring system based on a tri-axial accelerometer,” Proceedings of the 2nd International Convention on Rehabilitation Engineering & Assistive Technology, pp. 262-265, Singapore, 2008.
D. Bassett, B. Ainsworth, A. Swartz, S. Strath, W. O’Brien, and G. King, “Validity of four motion sensors in measuring moderate intensity physical activity,” Med Sci Sports Exerc., pp. S471-S480, 2000.
V.H. Stiles, P.J. Griew, A.V. Rowlands, “Use of accelerometry to classify activity beneficial to bone in premenopausal women,” Med Sci Sports Exerc., vol. 45(12), pp. 2353-2361, 2013.
S. Zhang, P. Murray, R. Zillmer, R.G. Eston, M. Catt, A.V. Rowlands, “Activity classification using the GENEA: optimum sampling frequency and number of axes,” Med Sci Sports Exerc., vol. 44(11), pp. 2228-2234, 2012.
O. Ekblom, G. Nyberg, E.E. Bak, U. Ekelund, C. Marcus, “Validity and comparability of a wrist-worn accelerometer in children,” J Phys Act Health, vol. 9(3), pp. 389-393, 2012.
D. Figo, P. Diniz, D. Ferreir, J. Cardoso, “Preprocessing techniques for context recognition from accelerometer data,” Personal and Ubiquitous Computing, vol. 14(7), pp. 645-662, 2010.
C. Bouten, K. Westerterp, M. Verduin, and J. Janssen, “Assessment of energy expenditure for physical activity using a triaxial accelerometer,” Med. Sci. Sports Exerc., vol. 26, pp. 1516-1523, 1994.
D. Karantonis, M. Narayanan, M. Mathie, N. Lovell, and B. Cellar, “Implementation of a real-time human movement classifier using a triaxial accelerometer for ambulatory monitoring,” IEEE Transactions on Information Technology in Biomedicine, vol. 10(1), pp. 156-167, 2006.
A. Jeon et al., “Implementation of the personal emergency response system,” International Journal of Biological and Medical Sciences, vol. 1(1), pp. 61-65, 2008.
C. Bouten, W. Verboeket-Van De Venne, K. Westerterp, M. Verduin, and J. Janssen, “Daily physical activity assessment: comparison between movement registration and doubly labeled water,” The American Physiological Society, pp. 1019-1026, 1996.
A. Khan, Y. Lee, and T. Kim, “Accelerometer signal-based human activity recognition using augmented autoregressive model coefficients and artificial neural nets,” 30th Annual International IEEE EMBS Conference, Vancouver, British Columbia, Canada, pp. 5172-5175, August, 2008.
B. Ainsworth et al., “Compendium of physical activities: an update of activity codes and MET intensities,” Med Sci Sports Exerc., pp. S498-S516, 2000.
J.L. Carus, V. Pelaez, G. Lopez, and V. Lobato, “JIM: a novel and efficient accelerometric magnitude to measure physical activity,” pHealth, pp. 283-288, 2012.