Citation
Bobak Mortazavi, Mohammad Pourhomayoun, Hassan Ghasemzadeh, Roozbeh Jafari, Roberts Christian K., Majid Sarrafzadeh. "Context-Aware Data Processing to Enhance Quality of Measurements in Wireless Health Systems: An Application to MET Calculation of Exergaming Actions". IEEE Internet of Things Journal, 2014.

Abstract
Wireless health systems enable remote and continuous monitoring of individuals, with applications in elderly care support, chronic disease management, and preventive care. The underlying sensing platform provides constructs that consider the quality of information driven from the system and ensure the reliability/validity of the outcomes to support the decision making processes. In this paper, we present an approach to integrate contextual information within the data processing flow in order to improve the quality of measurements. We focus on a pilot application that uses wearable motion sensors to calculate metabolic equivalent of task (MET) of exergaming movements. Exergames need to show energy expenditure values, often using accelerometer approximations applied to general activities. We focus on two contextual factors, namely 'activity type' and 'sensor location', and demonstrate how these factors can be used to enhance the measured values. By placing sensors around the body, it becomes clear that sensors placed closest to the highest areas of movement provide the most accurate approximations. Therefore, allocating larger weights to more informative sensors can improve the final measurements. Further, designing regression models for each activity provides better results than any generalized model. Indeed, the averaged R2 value for the movements using simple sensor location improve from a general :71 to as high as :84 for an individual activity type. The different methods present a range of R2 value averages across activity type from :64 for sensor location to :89 for multidimensional regression, with an average game play MET value of 7:93. Finally, in a leave-one-subject-out cross validation a mean absolute error of 2:231 METs is found when predicting the activity levels using the best models.

Electronic downloads

• https://www.src.org/library/publication/p070209/. (Link to paper on SRC website.)
• http://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=6932440
• http://dx.doi.org/10.1109/JIOT.2014.2364407

• HTML

  Bobak Mortazavi, Mohammad Pourhomayoun, Hassan Ghasemzadeh,
  Roozbeh Jafari, Roberts Christian K., Majid Sarrafzadeh.
  <a
  href="http://www.terraswarm.org/pubs/327.html"
  >Context-Aware Data Processing to Enhance Quality of
  Measurements in Wireless Health Systems: An Application to
  MET Calculation of Exergaming Actions</a>,
  <i>IEEE Internet of Things Journal</i>,  2014.

• Plain text

  Bobak Mortazavi, Mohammad Pourhomayoun, Hassan Ghasemzadeh,
  Roozbeh Jafari, Roberts Christian K., Majid Sarrafzadeh.
  "Context-Aware Data Processing to Enhance Quality of
  Measurements in Wireless Health Systems: An Application to
  MET Calculation of Exergaming Actions". <i>IEEE
  Internet of Things Journal</i>,  2014.

• BibTeX

  @article{MortazaviPourhomayounGhasemzadehJafariChristianK14_ContextAwareDataProcessingToEnhanceQualityOfMeasurements,
      author = {Bobak Mortazavi and Mohammad Pourhomayoun and
                Hassan Ghasemzadeh and Roozbeh Jafari and Roberts
                Christian K. and Majid Sarrafzadeh},
      title = {Context-Aware Data Processing to Enhance Quality
                of Measurements in Wireless Health Systems: An
                Application to MET Calculation of Exergaming
                Actions},
      journal = {IEEE Internet of Things Journal},
      year = {2014},
      abstract = {Wireless health systems enable remote and
                continuous monitoring of individuals, with
                applications in elderly care support, chronic
                disease management, and preventive care. The
                underlying sensing platform provides constructs
                that consider the quality of information driven
                from the system and ensure the
                reliability/validity of the outcomes to support
                the decision making processes. In this paper, we
                present an approach to integrate contextual
                information within the data processing flow in
                order to improve the quality of measurements. We
                focus on a pilot application that uses wearable
                motion sensors to calculate metabolic equivalent
                of task (MET) of exergaming movements. Exergames
                need to show energy expenditure values, often
                using accelerometer approximations applied to
                general activities. We focus on two contextual
                factors, namely 'activity type' and 'sensor
                location', and demonstrate how these factors can
                be used to enhance the measured values. By placing
                sensors around the body, it becomes clear that
                sensors placed closest to the highest areas of
                movement provide the most accurate approximations.
                Therefore, allocating larger weights to more
                informative sensors can improve the final
                measurements. Further, designing regression models
                for each activity provides better results than any
                generalized model. Indeed, the averaged R2 value
                for the movements using simple sensor location
                improve from a general :71 to as high as :84 for
                an individual activity type. The different methods
                present a range of R2 value averages across
                activity type from :64 for sensor location to :89
                for multidimensional regression, with an average
                game play MET value of 7:93. Finally, in a
                leave-one-subject-out cross validation a mean
                absolute error of 2:231 METs is found when
                predicting the activity levels using the best
                models. },
      URL = {http://terraswarm.org/pubs/327.html}
  }
  

Posted by Barb Hoversten on 27 Jun 2014.