A stepwise validation of a wearable system for estimating energy expenditure in field-based research

Regular physical activity (PA) is an important contributor to a healthy lifestyle. Currently, standard sensor-based methods to assess PA in field-based research rely on a single accelerometer mounted near the body's center of mass. This paper introduces a wearable system that estimates energy expenditure (EE) based on seven recognized activity types. The system was developed with data from 32 healthy subjects and consists of a chest mounted heart rate belt and two accelerometers attached to a thigh and dominant upper arm. The system was validated with 12 other subjects under restricted lab conditions and simulated free-living conditions against indirect calorimetry, as well as in subjects' habitual environments for 2 weeks against the doubly labeled water method. Our stepwise validation methodology gradually trades reference information from the lab against realistic data from the field. The average accuracy for EE estimation was 88% for restricted lab conditions, 55% for simulated free-living conditions and 87% and 91% for the estimation of average daily EE over the period of 1 and 2 weeks.

[1]  Kuan Zhang,et al.  Improving energy expenditure estimation for physical activity. , 2004, Medicine and science in sports and exercise.

[2]  Richard P Troiano,et al.  A timely meeting: objective measurement of physical activity. , 2005, Medicine and science in sports and exercise.

[3]  P. Deurenberg,et al.  A critical evaluation of heart rate monitoring to assess energy expenditure in individuals. , 1993, The American journal of clinical nutrition.

[4]  Daniel P. Siewiorek,et al.  Activity recognition and monitoring using multiple sensors on different body positions , 2006, International Workshop on Wearable and Implantable Body Sensor Networks (BSN'06).

[5]  Juha Röning,et al.  Estimation of Exercise Energy Expenditure Using a Wrist-Worn Accelerometer: A Linear Mixed Model Approach with Fixed-Effect Variable Selection , 2008, 2008 Seventh International Conference on Machine Learning and Applications.

[6]  Marc T. Hamilton,et al.  Role of Low Energy Expenditure and Sitting in Obesity, Metabolic Syndrome, Type 2 Diabetes, and Cardiovascular Disease , 2007, Diabetes.

[7]  J. B. J. Bussmann,et al.  Measuring daily behavior using ambulatory accelerometry: The Activity Monitor , 2001, Behavior research methods, instruments, & computers : a journal of the Psychonomic Society, Inc.

[8]  J. D. Janssen,et al.  Assessment of energy expenditure for physical activity using a triaxial accelerometer. , 1994, Medicine and science in sports and exercise.

[9]  B E Ainsworth,et al.  Compendium of physical activities: an update of activity codes and MET intensities. , 2000, Medicine and science in sports and exercise.

[10]  N. Wareham,et al.  Estimating energy expenditure by heart-rate monitoring without individual calibration. , 2001, Medicine and science in sports and exercise.

[11]  Ling Bao,et al.  Activity Recognition from User-Annotated Acceleration Data , 2004, Pervasive.

[12]  U. Ekelund,et al.  Branched equation modeling of simultaneous accelerometry and heart rate monitoring improves estimate of directly measured physical activity energy expenditure. , 2004, Journal of applied physiology.

[13]  Kuan Zhang,et al.  Measurement of human daily physical activity. , 2003, Obesity research.

[14]  S. Blair,et al.  Is physical activity or physical fitness more important in defining health benefits? , 2001, Medicine and science in sports and exercise.

[15]  G Plasqui,et al.  Improving assessment of daily energy expenditure by identifying types of physical activity with a single accelerometer. , 2009, Journal of applied physiology.

[16]  Hee Chan Kim,et al.  An Wearable Energy Expenditure Analysis System based on the 15-channel Whole-body Segment Acceleration Measurement , 2005, 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference.

[17]  Ling Bao,et al.  Physical activity recognition from acceleration data under semi-naturalistic conditions , 2003 .

[18]  Leena Choi,et al.  Validity of Physical Activity Intensity Predictions by ActiGraph, Actical, and RT3 Accelerometers , 2008, Obesity.

[19]  M. Goran,et al.  Experimental reliability of the doubly labeled water technique. , 1994, The American journal of physiology.

[20]  Timothy D Noakes,et al.  A novel energy expenditure prediction equation for intermittent physical activity. , 2005, Medicine and science in sports and exercise.

[21]  Zhenyu He,et al.  Weightlessness feature — a novel feature for single tri-axial accelerometer based activity recognition , 2008, 2008 19th International Conference on Pattern Recognition.

[22]  Gregory J. Welk,et al.  Physical Activity Assessments for Health-Related Research , 2002 .

[23]  M. Livingstone,et al.  Simultaneous measurement of free-living energy expenditure by the doubly labeled water method and heart-rate monitoring. , 1990, The American journal of clinical nutrition.

[24]  D A Schoeller,et al.  Reliability of the doubly labeled water method for the measurement of total daily energy expenditure in free-living subjects. , 1996, The Journal of nutrition.

[25]  K. Westerterp,et al.  Physical activity assessment: Comparison between movement registration and doubly labeled water method , 1997, Zeitschrift fur Ernahrungswissenschaft.

[26]  A. Sparti,et al.  Data-based approach for developing a physical activity frequency questionnaire. , 1998, American journal of epidemiology.

[27]  P. Freedson,et al.  Validity of accelerometry for the assessment of moderate intensity physical activity in the field. , 2000, Medicine and science in sports and exercise.

[28]  John J Reilly,et al.  Validation of Actigraph accelerometer estimates of total energy expenditure in young children. , 2006, International journal of pediatric obesity : IJPO : an official journal of the International Association for the Study of Obesity.

[29]  Wim H. M. Saris,et al.  Measuring Physical Activity and Energy Expenditure , 1996 .

[30]  John Staudenmayer,et al.  An artificial neural network to estimate physical activity energy expenditure and identify physical activity type from an accelerometer. , 2009, Journal of applied physiology.

[31]  H. Nagaraja,et al.  Evaluation of methods to assess physical activity in free-living conditions. , 2001, Medicine and science in sports and exercise.

[32]  U. Ekelund,et al.  Energy expenditure assessed by heart rate and doubly labeled water in young athletes. , 2002, Medicine and science in sports and exercise.

[33]  Yves Schutz,et al.  Validity of four short physical activity questionnaires in middle-aged persons. , 2006, Medicine and science in sports and exercise.

[34]  Kent Larson,et al.  Real-Time Recognition of Physical Activities and Their Intensities Using Wireless Accelerometers and a Heart Rate Monitor , 2007, 2007 11th IEEE International Symposium on Wearable Computers.

[35]  K. Westerterp,et al.  Physical Activity Assessment With Accelerometers: An Evaluation Against Doubly Labeled Water , 2007, Obesity.

[36]  Michael L. Littman,et al.  Activity Recognition from Accelerometer Data , 2005, AAAI.

[37]  Lu Wang,et al.  Transient and steady state estimation of human oxygen uptake based on noninvasive portable sensor measurements , 2009, Medical & Biological Engineering & Computing.

[38]  William R Leonard,et al.  Measuring human energy expenditure: What have we learned from the flex‐heart rate method? , 2003, American journal of human biology : the official journal of the Human Biology Council.

[39]  F. Péronnet,et al.  Table of nonprotein respiratory quotient: an update. , 1991, Canadian journal of sport sciences = Journal canadien des sciences du sport.

[40]  Jindong Tan,et al.  Real-time Daily Activity Classification with Wireless Sensor Networks using Hidden Markov Model , 2007, 2007 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[41]  Susan L Murphy,et al.  Review of physical activity measurement using accelerometers in older adults: considerations for research design and conduct. , 2009, Preventive medicine.

[42]  A. Prentice,et al.  Energy expenditure from minute-by-minute heart-rate recording: comparison with indirect calorimetry. , 1988, The American journal of clinical nutrition.

[43]  Gaetano Borriello,et al.  Validated caloric expenditure estimation using a single body-worn sensor , 2009, UbiComp.

[44]  Sari A Acra,et al.  Predicting energy expenditure of physical activity using hip- and wrist-worn accelerometers. , 2003, Diabetes technology & therapeutics.

[45]  S A Jebb,et al.  Contribution of a sedentary lifestyle and inactivity to the etiology of overweight and obesity: current evidence and research issues. , 1999, Medicine and science in sports and exercise.

[46]  T. Walsh,et al.  Comparison between the Datex-Ohmeda M-COVX metabolic monitor and the Deltatrac II in mechanically ventilated patients , 2002, Intensive Care Medicine.

[47]  K. Rennie,et al.  A combined heart rate and movement sensor: proof of concept and preliminary testing study , 2000, European Journal of Clinical Nutrition.

[48]  Margarita Treuth,et al.  Predicting energy expenditure from accelerometry counts in adolescent girls. , 2005, Medicine and science in sports and exercise.

[49]  David W. Mizell,et al.  Using gravity to estimate accelerometer orientation , 2003, Seventh IEEE International Symposium on Wearable Computers, 2003. Proceedings..

[50]  Scott R. Klemmer,et al.  Exiting the Cleanroom: On Ecological Validity and Ubiquitous Computing , 2008, Hum. Comput. Interact..