Open AccessFree-living Evaluation of Laboratory-based Activity Classifiers in Preschoolers
Author(s) -
Matthew Ahmadi,
D Brookes,
Alok Kumar Chowdhury,
Toby Pavey,
Stewart G. Trost
Publication year - 2019
Publication title -
medicine and science in sports and exercise
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.703
H-Index - 224
eISSN - 1530-0315
pISSN - 0195-9131
DOI - 10.1249/mss.0000000000002221
Subject(s) - random forest , support vector machine , wrist , artificial intelligence , accelerometer , machine learning , activities of daily living , computer science , activity recognition , actigraphy , confusion matrix , confusion , physical medicine and rehabilitation , physical therapy , medicine , psychology , endocrinology , circadian rhythm , radiology , operating system , psychoanalysis
Machine learning classification models for accelerometer data are potentially more accurate methods to measure physical activity in young children than traditional cut point methods. However, existing algorithms have been trained on laboratory-based activity trials, and their performance has not been investigated under free-living conditions.