The Internet belongs to everyone. Let’s keep it that way.

Protect Net Neutrality
Loading presentation...

Present Remotely

Send the link below via email or IM


Present to your audience

Start remote presentation

  • Invited audience members will follow you as you navigate and present
  • People invited to a presentation do not need a Prezi account
  • This link expires 10 minutes after you close the presentation
  • A maximum of 30 users can follow your presentation
  • Learn more about this feature in our knowledge base article

Do you really want to delete this prezi?

Neither you, nor the coeditors you shared it with will be able to recover it again.


ReadySteady: App for Accelerometer-based Activity Monitoring and Wellness-Motivation Feedback System for Older Adults

AMIA Annual Symposium 2012 (Clinical Workflow)

Mithra Vankipuram

on 6 November 2012

Comments (0)

Please log in to add your comment.

Report abuse

Transcript of ReadySteady: App for Accelerometer-based Activity Monitoring and Wellness-Motivation Feedback System for Older Adults

ReadySteady App for Accelerometer-based Activity Monitoring and Wellness-Motivation Feedback System for Older Adults Mithra Vankipuram, PhD
Services and Solutions Research
HP Labs

Siobhan McMahon, PhD, MPH, GNR-BC
University of Minnesota

Julie Fleury, RN, PhD, FAAN
Nursing and Healthcare Innovation
Arizona State University Physical Activity in Older Adults Daily physical activity and exercise have broad implications to both the physical and mental wellbeing of older adults Reduces risk of mortality and age-related morbidity Minimizes falls and fall-related fractures Lowers risk of cognitive impairment and dementia 70% of older adults are inadequately active What is needed to improve adherence to exercise regimens? Study behavioral processes key to both adopting and maintaining activities over time
Provide support structures to foster the necessary motivation Wellness Motivation Theory Provides guidelines for the content and appropriate introduction of motivational feedback in interfaces empower the individual What was needed? Mobile application that could measure physical activity behavior and augment aspects of wellness motivation intervention Measure activity intensity, duration and frequency
Provide activity information back to the users
Supplement quantitative information with motivational feedback Promotes new and positive health patterns
Enable individuals to develop their own goals
Assess opportunities for improvement
Provide capability to initiate and monitor change INDIVIDUAL GROWTH ReadySteady Specifications Mobile application that could measure physical activity behavior and augment aspects of wellness motivation intervention
Measurement device and feedback integrated in one unit
Unit is required to be portable
Needs to be operational for at least 12 hours
Provide real-time feedback on activity
Provide feedback on past activity levels
Allow for goal setting
Store data for analysis by clinician Tools with WMT features Fish 'n' Steps Chick Clique UbiFit Flowie Activity indicated by health of fish
Incentives provided for increased activity Allows sharing goals and progress with friends Metaphorical representation of activity for adults Emotive interface designed for older adults THE POWER OF THE GARDEN Children Teens Children and Adults Older Adults Utilized external accelerometer Proven to convey information adequately Simplifies interactions Avoids expectations that may otherwise arise from real-life avatars Gender neutral Activity Measurement Measurement Tool (iPod Touch accelerometer) Rationale: accelerometer integrated with feedback system
Main Considerations:
Measurement accuracy
Battery life
Output data rate = 100 Hz
For battery optimization rate set at 10 Hz (similar to Actigraph)
Data accumulated sampled at (configurable) regular intervals (e.g. 5 second epochs every 15 seconds in 4 epochs/minute) Activity Measurement Measurement Mode (jerk) Rationale: Most human motion (gross) involves jerk
Main Considerations:
Noise, gravity and indirect movement
Simplicity (project timeline and computation complexity)
No calibration should be needed
Samples collected in a window smoothed using averages computed over a sliding window (noise)
Jerk computed for every sample (constant offsets, gravity) Activity Measurement Energy Estimation (rule-based classifier) Rationale: rough classification needed with high specificity on binary check of if user is active or not
Main Considerations:
Time taken to develop models for classifier
Method that works with little experimental data
No activity: < 15
Low intensity activity (<3 METs): 15-100
Medium intensity activity (3-6 METs): 101 - 160
High intensity activity (>6 METs): > 160 ReadySteady Architecture Interface Display Feedback transitions as activity increases Experiment 1 Experiment 2 Study Purpose
Assess sensitivity of activity measurement in a lab setting Activity Measurement verses Treadmill Speed Participants
Four younger adults (ages between 25-35) Methods
iPod touches carried by participants
Treadmill speed increased from 0 mph to 5 mph in by 0.5 mph intervals every 90 seconds
Participants walked or ran depending on their comfort with the speed Study Purpose
Assess sensitivity of activity measurement in real-life setting Participants
Four older adults (ages between 69-75) Methods
iPod touches carried by participants
Activity logs maintained by participants
Some activities recorded included
rocking in a chair
driving a car (vehicle)
strength and balance exercises
housework and yard work
walking and jogging Measurements across various common physical activities Conclusions Acknowledgements Limitations Self reporting bias
Few participants with varied activities
Difficulty in tracking strength and balance exercises Trade-offs in design and development Choice of platform verses battery life
Granularity of measurement verses ease of use
Screen real-estate and ease of use Collaborators
Siobhan McMahon
Julie Fleury

National Institutes of Health /National Institute of Nursing Research Grant # F31NR01235

Presentation available at:
Full transcript