A Review of Emerging Analytical Techniques for Objective Physical Activity Measurement in Humans

Physical inactivity is one of the most prevalent risk factors for non-communicable diseases in the world. A fundamental barrier to enhancing physical activity levels and decreasing sedentary behavior is limited by our understanding of associated measurement and analytical techniques. The number of analytical techniques for physical activity measurement has grown significantly, and although emerging techniques may advance analyses, little consensus is presently available and further synthesis is therefore required. The objective of this review was to identify the accuracy of emerging analytical techniques used for physical activity measurement in humans. We conducted a search of electronic databases using Web of Science, PubMed, and Google Scholar. This review included studies written in English and published between January 2010 and December 2014 that assessed physical activity using emerging analytical techniques and reported technique accuracy. A total of 2064 papers were initially retrieved from three databases. After duplicates were removed and remaining articles screened, 50 full-text articles were reviewed, resulting in the inclusion of 11 articles that met the eligibility criteria. Despite the diverse nature and the range in accuracy associated with some of the analytic techniques, the rapid development of analytics has demonstrated that more sensitive information about physical activity may be attained. However, further refinement of these techniques is needed.

[1]  Xin Yao,et al.  Evolving artificial neural networks , 1999, Proc. IEEE.

[2]  Søren Brage,et al.  A method to compare new and traditional accelerometry data in physical activity monitoring , 2010, 2010 IEEE International Symposium on "A World of Wireless, Mobile and Multimedia Networks" (WoWMoM).

[3]  Kamiar Aminian,et al.  Capturing human motion using body‐fixed sensors: outdoor measurement and clinical applications , 2004, Comput. Animat. Virtual Worlds.

[4]  Martin Egelhaaf,et al.  Identifying Prototypical Components in Behaviour Using Clustering Algorithms , 2010, PloS one.

[5]  David Howard,et al.  A Comparison of Feature Extraction Methods for the Classification of Dynamic Activities From Accelerometer Data , 2009, IEEE Transactions on Biomedical Engineering.

[6]  Weng-Keen Wong,et al.  Artificial neural networks to predict activity type and energy expenditure in youth. , 2012, Medicine and science in sports and exercise.

[7]  D. Bassett,et al.  The technology of accelerometry-based activity monitors: current and future. , 2005, Medicine and science in sports and exercise.

[8]  M. Siervo,et al.  Accuracy of predictive equations for the measurement of resting energy expenditure in older subjects , 2013, Proceedings of the Nutrition Society.

[9]  Gerhard Tröster,et al.  Eye Movement Analysis for Activity Recognition Using Electrooculography , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Greg Mori,et al.  Distinguishing the causes of falls in humans using an array of wearable tri-axial accelerometers. , 2014, Gait & posture.

[11]  Angelo M. Sabatini,et al.  Machine Learning Methods for Classifying Human Physical Activity from On-Body Accelerometers , 2010, Sensors.

[12]  Edward Sazonov,et al.  Using Sensors to Measure Activity in People with Stroke , 2011, Topics in stroke rehabilitation.

[13]  Carlo Menon,et al.  Towards the development of a wearable feedback system for monitoring the activities of the upper-extremities , 2014, Journal of NeuroEngineering and Rehabilitation.

[14]  Huw D. Summers,et al.  Automated Cell Identification and Tracking Using Nanoparticle Moving-Light-Displays , 2012, PloS one.

[15]  Mikkel Baun Kjærgaard,et al.  Detecting pedestrian flocks by fusion of multi-modal sensors in mobile phones , 2012, UbiComp.

[16]  Alexander Horsch,et al.  Separating Movement and Gravity Components in an Acceleration Signal and Implications for the Assessment of Human Daily Physical Activity , 2013, PloS one.

[17]  Yeh-Liang Hsu,et al.  A Review of Accelerometry-Based Wearable Motion Detectors for Physical Activity Monitoring , 2010, Sensors.

[18]  Dominik Schuldhaus,et al.  Hierarchical, Multi-Sensor Based Classification of Daily Life Activities: Comparison with State-of-the-Art Algorithms Using a Benchmark Dataset , 2013, PloS one.

[19]  Merryn J Mathie,et al.  Accelerometry: providing an integrated, practical method for long-term, ambulatory monitoring of human movement , 2004, Physiological measurement.

[20]  John Staudenmayer,et al.  Statistical considerations in the analysis of accelerometry-based activity monitor data. , 2012, Medicine and science in sports and exercise.

[21]  Gregory J Welk,et al.  Validation of pattern-recognition monitors in children using doubly labeled water. , 2013, Medicine and science in sports and exercise.

[22]  Gaetano Borriello,et al.  Accuracy of a novel multi-sensor board for measuring physical activity and energy expenditure , 2011, European Journal of Applied Physiology.

[23]  Stewart G Trost,et al.  Comparison of 3 accelerometer data reduction approaches, step counts, and 2 self-report measures for estimating physical activity in free-living adults. , 2013, Journal of physical activity & health.

[24]  BullingAndreas,et al.  Eye Movement Analysis for Activity Recognition Using Electrooculography , 2011 .

[25]  Mingui Sun,et al.  Physical activity recognition based on motion in images acquired by a wearable camera , 2011, Neurocomputing.

[26]  Kamiar Aminian,et al.  Mobility assessment in older people: new possibilities and challenges , 2007, European journal of ageing.

[27]  Filomena O. Soares,et al.  Preliminary study on determining stereotypical motor movements , 2012, 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[28]  S. Blair,et al.  Calibration of an accelerometer during free-living activities in children. , 2007, International journal of pediatric obesity : IJPO : an official journal of the International Association for the Study of Obesity.

[29]  G. Schofield,et al.  Convergent validity of a piezoelectric pedometer and an omnidirectional accelerometer for measuring children's physical activity. , 2011, Pediatric exercise science.