Machine learning algorithms can classify outdoor terrain types during running using accelerometry data.

Journal: Gait & posture
Published Date:

Abstract

BACKGROUND: Running is a popular physical activity that benefits health; however, running surface characteristics may influence loading impact and injury risk. Machine learning algorithms could automatically identify running surface from wearable motion sensors to quantify running exposures, and perhaps loading and injury risk for a runner.

Authors

  • P C Dixon
    Department of Environmental Health, Harvard T.H. Chan School of Public Health, United States; Liberty Mutual Research Institute for Safety, United States.
  • K H Schütte
    Human Movement Biomechanics Research Group, Department of Movement Sciences, KU Leuven, Leuven, Belgium.
  • B Vanwanseele
    Human Movement Biomechanics Research Group, Department of Movement Sciences, KU Leuven, Leuven, Belgium.
  • J V Jacobs
    Liberty Mutual Research Institute for Safety, United States.
  • J T Dennerlein
    Department of Environmental Health, Harvard T.H. Chan School of Public Health, United States; Bouvé College of Health Sciences, Northeastern University, United States.
  • J M Schiffman
    Liberty Mutual Research Institute for Safety, United States.
  • P-A Fournier
    Carré Technologies, Inc., Montreal, Canada.
  • B Hu
    Department of Environmental Health, Harvard T.H. Chan School of Public Health, United States; Liberty Mutual Research Institute for Safety, United States. Electronic address: boyihu@hsph.harvard.edu.