A Wireless Sensor-Based System for Self-tracking Activity Levels Among Manual Wheelchair Users

ActiDote —activity as an antidote— is a system for manual wheelchair users that uses wireless sensors to recognize activities of various intensity levels in order to allow self-tracking while providing motivation. In this paper, we describe both the hardware setup and the software pipeline that enable our system to operate. Laboratory tests using multi-modal fusion and machine learning reveal promising results attaining a F1-score classification performance of 0.97 on five different wheelchair-based activities belonging to four intensity levels. Finally, we show that such a low cost system can be used for an easy self-monitoring of physical activity levels among manual wheelchair users.

[1]  K. Patrick,et al.  Physical Activity and Public Health: A Recommendation From the Centers for Disease Control and Prevention and the American College of Sports Medicine , 1995 .

[2]  Prasant Mohapatra,et al.  Accurate energy expenditure estimation using smartphone sensors , 2013, Wireless Health.

[3]  X. García-Massó,et al.  Validation of the use of Actigraph GT3X accelerometers to estimate energy expenditure in full time manual wheelchair users with spinal cord injury , 2013, Spinal Cord.

[4]  Shivayogi V. Hiremath,et al.  Evaluation of activity monitors in manual wheelchair users with paraplegia , 2011, The journal of spinal cord medicine.

[5]  Nicole Ruch,et al.  Neural network versus activity-specific prediction equations for energy expenditure estimation in children. , 2013, Journal of applied physiology.

[6]  P. London.  Injury , 1969, Definitions.

[7]  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.

[8]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[9]  P. Kokkinos,et al.  Physical Inactivity and Mortality Risk , 2011, Cardiology research and practice.

[10]  Dan Ding,et al.  Detection of Wheelchair User Activities Using Wearable Sensors , 2011, HCI.

[11]  David R Bassett,et al.  2011 Compendium of Physical Activities: a second update of codes and MET values. , 2011, Medicine and science in sports and exercise.

[12]  Skipper Seabold,et al.  Statsmodels: Econometric and Statistical Modeling with Python , 2010, SciPy.

[13]  David Andre,et al.  Machine Learning and Sensor Fusion for Estimating Continuous Energy Expenditure , 2011, AI Mag..

[14]  T. Nightingale,et al.  Predicting physical activity energy expenditure in manual wheelchair users. , 2014, Medicine and science in sports and exercise.

[15]  Dan Ding,et al.  Regression equations for RT3 activity monitors to estimate energy expenditure in manual wheelchair users , 2011, 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[16]  S. Conger,et al.  Physical Activity Assessment in Wheelchair Users , 2011 .

[17]  Dan Ding,et al.  Detection of physical activities using a physical activity monitor system for wheelchair users. , 2015, Medical engineering & physics.

[18]  Roger B. Davis,et al.  Obesity among adults with disabling conditions. , 2002, JAMA.

[19]  Phillip A Bishop,et al.  Wheelchair-mounted accelerometers for measurement of physical activity , 2012, Disability and rehabilitation. Assistive technology.

[20]  Glen M. Davis,et al.  Comparison of methods to assess energy expenditure and physical activity in people with spinal cord injury , 2012, The journal of spinal cord medicine.

[21]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[22]  Matthew Chalmers,et al.  Personal tracking as lived informatics , 2014, CHI.

[23]  Bernt Schiele,et al.  A tutorial on human activity recognition using body-worn inertial sensors , 2014, CSUR.