Giter Site home page Giter Site logo

device_validity_time's Introduction

Changes in Step Count Accuracy of Wearable Devices with the Continuous Development of New Technology

Authors

  1. Daniel Fuller, Department of Community Health and Epidemiology, University of Saskatchewan.
  2. Ryan Ellis, School of Human Kinetics and Recreation, Memorial University of Newfoundland.
  3. Kevin Mongeon, School of Human Kinetics, University of Ottawa, Canada.

Abstract

Commercial wearable devices have become an important tool in the physical activity routines of many people. An important factor in the usefulness of these devices is their criterion validity to measure various physical activity parameters compared to a gold standard. The purpose of this study is to examine whether criterion validity of commercial wearable devices has changed over time with the release of new devices. A cross-sectional study was conducted using publicly available data from a systematic review examining the criterion validity of commercial wearable devices. The systematic review was conducted in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. We included studies with valid data for the step count mean absolute percent error (MAPE), device market availability, device brand and type, and study year. Regression analyses were used to examine the association between device MAPE and the year the device was available on the market. A total of 944 MAPE values were included in the analysis. Devices were released between 2008 and 2016. Results show that for each year there was an improvement in MAPE of -1.5 percent (CI: -2.5 to -0.5). Sensitivity analysis showed while most brands validity improved over time, Fitbit validity did not change. The results suggest that despite many iterations of new commercial wearables being released there has only been small improvements in criterion of these devices over time.

Data and Code

device_validity_time's People

Contributors

walkabilly avatar

Watchers

 avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.