Machine Learning Models for Classifying Physical Activity in Free-Living Preschool Children

• Published in: Sensors (Basel, Switzerland) Vol. 20; no. 16; p. 4364
• Main Authors: Ahmadi, Matthew N., Pavey, Toby G., Trost, Stewart G.
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 05.08.2020; MDPI
• Subjects: accelerometer; Accelerometers; Accelerometry; Accuracy; Aged; Artificial intelligence; assessment; Behavior; Cameras; Child, Preschool; Classification; Data processing; Exercise; Humans; Laboratories; Light; Machine Learning; measurement; Monitoring, Ambulatory; Obesity; Overweight; Pattern recognition; physical activity; Preschool children; Public health; supervised learning; Wrist; United States > US; assessment; early childhood; supervised learning; accelerometer; classification; measurement; physical activity
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s20164364

Machine learning (ML) activity classification models trained on laboratory-based activity trials exhibit low accuracy under free-living conditions. Training new models on free-living accelerometer data, reducing the number of prediction windows comprised of multiple activity types by using shorter w...