Accepted for/Published in: JMIR Biomedical Engineering
Date Submitted: Apr 3, 2020
Open Peer Review Period: Apr 3, 2020 - Apr 20, 2020
Date Accepted: Jan 9, 2021
(closed for review but you can still tweet)
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Development of Physical Activity Evaluation Systems Using a Voice Recognition Application
ABSTRACT
Background:
The use of Web-based physical activity systems has been proposed as an easy method for collecting physical activity data. Behavior recording using a voice recognition system via the WEB might be effective.
Objective:
The objective of this study was to develop a behavior-recording application (APP) using voice recognition. The results from our developed APP were compared with objective data from a 3-axis accelerometer to assess the strengths and weaknesses of the new measurement system.
Methods:
A total of 20 participants (14 men, 6 women, 19.1 (SD 0.9) years of age) wore a 3-axis accelerometer and inputted behavioral data into their smartphones for a period of 7 days. The measure of intensity was metabolic equivalents (METs).
Results:
The Pearson correlations for the METs between the two methods were all positive and significant when the analysis was for over 10 hours, r = 0.545 (P =.017), and for over 14 hours with voice input, r = 0.750 (P =.008). The Bland-Altman 95% limits of agreement ranged from –0.35 to 0.54 METs (over 10 hours) and -0.26 to 0.47 (over 14 hours) between the two methods. The exercise intensity was higher according to the APP compared with the 3-axis accelerometer, indicating overestimation.
Conclusions:
Voice recognition APP appear to be useful for assessing physical activity with high accuracy. However, voice input compliance is an important factor.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.