Markus Hagenbuchner1, Dylan P Cliff2, Stewart G Trost3, Nguyen Van Tuc4, Gregory E Peoples5. 1. Faculty of Engineering and Information Science, University of Wollongong, Australia. Electronic address: markus@uow.edu.au. 2. Faculty of Social Sciences, Early Start Research Institute, University of Wollongong, Australia. Electronic address: dylanc@uow.edu.au. 3. Institute of Health and Biomedical Innovation, Queensland University of Technology, Australia. Electronic address: s.trost@qut.edu.au. 4. Faculty of Engineering and Information Science, University of Wollongong, Australia. Electronic address: vtn966@uow.edu.au. 5. School of Medicine, University of Wollongong, Australia. Electronic address: greg_peoples@uow.edu.au.
Abstract
OBJECTIVES: Recent research has shown that machine learning techniques can accurately predict activity classes from accelerometer data in adolescents and adults. The purpose of this study is to develop and test machine learning models for predicting activity type in preschool-aged children. DESIGN: Participants completed 12 standardised activity trials (TV, reading, tablet game, quiet play, art, treasure hunt, cleaning up, active game, obstacle course, bicycle riding) over two laboratory visits. METHODS: Eleven children aged 3-6 years (mean age=4.8±0.87; 55% girls) completed the activity trials while wearing an ActiGraph GT3X+ accelerometer on the right hip. Activities were categorised into five activity classes: sedentary activities, light activities, moderate to vigorous activities, walking, and running. A standard feed-forward Artificial Neural Network and a Deep Learning Ensemble Network were trained on features in the accelerometer data used in previous investigations (10th, 25th, 50th, 75th and 90th percentiles and the lag-one autocorrelation). RESULTS: Overall recognition accuracy for the standard feed forward Artificial Neural Network was 69.7%. Recognition accuracy for sedentary activities, light activities and games, moderate-to-vigorous activities, walking, and running was 82%, 79%, 64%, 36% and 46%, respectively. In comparison, overall recognition accuracy for the Deep Learning Ensemble Network was 82.6%. For sedentary activities, light activities and games, moderate-to-vigorous activities, walking, and running recognition accuracy was 84%, 91%, 79%, 73% and 73%, respectively. CONCLUSIONS: Ensemble machine learning approaches such as Deep Learning Ensemble Network can accurately predict activity type from accelerometer data in preschool children.
OBJECTIVES: Recent research has shown that machine learning techniques can accurately predict activity classes from accelerometer data in adolescents and adults. The purpose of this study is to develop and test machine learning models for predicting activity type in preschool-aged children. DESIGN:Participants completed 12 standardised activity trials (TV, reading, tablet game, quiet play, art, treasure hunt, cleaning up, active game, obstacle course, bicycle riding) over two laboratory visits. METHODS: Eleven children aged 3-6 years (mean age=4.8±0.87; 55% girls) completed the activity trials while wearing an ActiGraph GT3X+ accelerometer on the right hip. Activities were categorised into five activity classes: sedentary activities, light activities, moderate to vigorous activities, walking, and running. A standard feed-forward Artificial Neural Network and a Deep Learning Ensemble Network were trained on features in the accelerometer data used in previous investigations (10th, 25th, 50th, 75th and 90th percentiles and the lag-one autocorrelation). RESULTS: Overall recognition accuracy for the standard feed forward Artificial Neural Network was 69.7%. Recognition accuracy for sedentary activities, light activities and games, moderate-to-vigorous activities, walking, and running was 82%, 79%, 64%, 36% and 46%, respectively. In comparison, overall recognition accuracy for the Deep Learning Ensemble Network was 82.6%. For sedentary activities, light activities and games, moderate-to-vigorous activities, walking, and running recognition accuracy was 84%, 91%, 79%, 73% and 73%, respectively. CONCLUSIONS: Ensemble machine learning approaches such as Deep Learning Ensemble Network can accurately predict activity type from accelerometer data in preschool children.
Authors: Andrea Mannini; Mary Rosenberger; William L Haskell; Angelo M Sabatini; Stephen S Intille Journal: Med Sci Sports Exerc Date: 2017-04 Impact factor: 5.411
Authors: Christiana M T VAN Loo; Anthony D Okely; Marijka J Batterham; Trina Hinkley; Ulf Ekelund; Søren Brage; John J Reilly; Stewart G Trost; Rachel A Jones; Xanne Janssen; Dylan P Cliff Journal: Med Sci Sports Exerc Date: 2017-04 Impact factor: 5.411
Authors: K Hannam; K C Deere; A Hartley; E M Clark; J Coulson; A Ireland; C Moss; M H Edwards; E Dennison; T Gaysin; R Cooper; A Wong; J S McPhee; C Cooper; D Kuh; J H Tobias Journal: Osteoporos Int Date: 2016-10-31 Impact factor: 4.507
Authors: Matthew Ahmadi; Margaret O'Neil; Maria Fragala-Pinkham; Nancy Lennon; Stewart Trost Journal: J Neuroeng Rehabil Date: 2018-11-15 Impact factor: 4.262
Authors: Soyang Kwon; Patricia Zavos; Katherine Nickele; Albert Sugianto; Mark V Albert Journal: Int J Environ Res Public Health Date: 2019-07-21 Impact factor: 3.390
Authors: Christiana Maria Theodora VAN Loo; Anthony D Okely; Marijka J Batterham; Trina Hinkley; Ulf Ekelund; Søren Brage; John J Reilly; Stewart G Trost; Rachel A Jones; Xanne Janssen; Dylan P Cliff Journal: Med Sci Sports Exerc Date: 2018-03 Impact factor: 5.411
Authors: Rabiu Muazu Musa; Anwar P P Abdul Majeed; Zahari Taha; Siow Wee Chang; Ahmad Fakhri Ab Nasir; Mohamad Razali Abdullah Journal: PLoS One Date: 2019-01-03 Impact factor: 3.240