Individual versus Group Calibration of Machine Learning Models for Physical Activity Assessment Using Body-Worn Accelerometers.

Journal: Medicine and science in sports and exercise
Published Date: Dec 1, 2021

Abstract

PURPOSE: We sought to determine if individually calibrated machine learning models yielded higher accuracy than a group calibration approach for physical activity intensity assessment.

Authors

  • Alexander H K Montoye
  • Bradford S Westgate
    Mathematics and Computer Science Department, Alma College, Alma, MI.
  • Kimberly A Clevenger
    National Cancer Institute, National Institutes of Health, Bethesda, MD.
  • Karin A Pfeiffer
    Department of Kinesiology, Michigan State University, East Lansing, MI.
  • Joseph D Vondrasek
    Integrative Physiology and Health Science Department, Alma College, Alma, MI.
  • Morgan R Fonley
    Mathematics and Computer Science Department, Alma College, Alma, MI.
  • Joshua M Bock
  • Leonard A Kaminsky

Keywords

External Resources

Popular Topics
Recent Journals