Literature DB >> 27372275

Field evaluation of a random forest activity classifier for wrist-worn accelerometer data.

Toby G Pavey1, Nicholas D Gilson2, Sjaan R Gomersall2, Bronwyn Clark3, Stewart G Trost4.   

Abstract

OBJECTIVES: Wrist-worn accelerometers are convenient to wear and associated with greater wear-time compliance. Previous work has generally relied on choreographed activity trials to train and test classification models. However, validity in free-living contexts is starting to emerge. Study aims were: (1) train and test a random forest activity classifier for wrist accelerometer data; and (2) determine if models trained on laboratory data perform well under free-living conditions.
DESIGN: Twenty-one participants (mean age=27.6±6.2) completed seven lab-based activity trials and a 24h free-living trial (N=16).
METHODS: Participants wore a GENEActiv monitor on the non-dominant wrist. Classification models recognising four activity classes (sedentary, stationary+, walking, and running) were trained using time and frequency domain features extracted from 10-s non-overlapping windows. Model performance was evaluated using leave-one-out-cross-validation. Models were implemented using the randomForest package within R. Classifier accuracy during the 24h free living trial was evaluated by calculating agreement with concurrently worn activPAL monitors.
RESULTS: Overall classification accuracy for the random forest algorithm was 92.7%. Recognition accuracy for sedentary, stationary+, walking, and running was 80.1%, 95.7%, 91.7%, and 93.7%, respectively for the laboratory protocol. Agreement with the activPAL data (stepping vs. non-stepping) during the 24h free-living trial was excellent and, on average, exceeded 90%. The ICC for stepping time was 0.92 (95% CI=0.75-0.97). However, sensitivity and positive predictive values were modest. Mean bias was 10.3min/d (95% LOA=-46.0 to 25.4min/d).
CONCLUSIONS: The random forest classifier for wrist accelerometer data yielded accurate group-level predictions under controlled conditions, but was less accurate at identifying stepping verse non-stepping behaviour in free living conditions Future studies should conduct more rigorous field-based evaluations using observation as a criterion measure.
Copyright © 2016 Sports Medicine Australia. Published by Elsevier Ltd. All rights reserved.

Entities:  

Keywords:  Accelerometer; Physical activity; Random forest classifier; Wrist

Mesh:

Year:  2016        PMID: 27372275     DOI: 10.1016/j.jsams.2016.06.003

Source DB:  PubMed          Journal:  J Sci Med Sport        ISSN: 1878-1861            Impact factor:   4.319


  34 in total

1.  Clinico-radiological characteristic-based machine learning in reducing unnecessary prostate biopsies of PI-RADS 3 lesions with dual validation.

Authors:  Yansheng Kan; Qing Zhang; Jiange Hao; Wei Wang; Junlong Zhuang; Jie Gao; Haifeng Huang; Jing Liang; Giancarlo Marra; Giorgio Calleris; Marco Oderda; Xiaozhi Zhao; Paolo Gontero; Hongqian Guo
Journal:  Eur Radiol       Date:  2020-06-10       Impact factor: 5.315

2.  Perspective: Opportunities and Challenges of Technology Tools in Dietary and Activity Assessment: Bridging Stakeholder Viewpoints.

Authors:  Sai Krupa Das; Akari J Miki; Caroline M Blanchard; Edward Sazonov; Cheryl H Gilhooly; Sujit Dey; Colton B Wolk; Chor San H Khoo; James O Hill; Robin P Shook
Journal:  Adv Nutr       Date:  2022-02-01       Impact factor: 11.567

3.  Prospective Associations of Daily Step Counts and Intensity With Cancer and Cardiovascular Disease Incidence and Mortality and All-Cause Mortality.

Authors:  Borja Del Pozo Cruz; Matthew N Ahmadi; I-Min Lee; Emmanuel Stamatakis
Journal:  JAMA Intern Med       Date:  2022-09-12       Impact factor: 44.409

4.  Pre- and post-dam river water temperature alteration prediction using advanced machine learning models.

Authors:  Dinesh Kumar Vishwakarma; Rawshan Ali; Shakeel Ahmad Bhat; Ahmed Elbeltagi; Nand Lal Kushwaha; Rohitashw Kumar; Jitendra Rajput; Salim Heddam; Alban Kuriqi
Journal:  Environ Sci Pollut Res Int       Date:  2022-06-28       Impact factor: 5.190

5.  An Open-Source Monitor-Independent Movement Summary for Accelerometer Data Processing.

Authors:  Dinesh John; Qu Tang; Fahd Albinali; Stephen Intille
Journal:  J Meas Phys Behav       Date:  2019-12

Review 6.  Assessment of Physical Activity in Adults Using Wrist Accelerometers.

Authors:  Fangyu Liu; Amal A Wanigatunga; Jennifer A Schrack
Journal:  Epidemiol Rev       Date:  2022-01-14       Impact factor: 4.280

7.  Balanced: a randomised trial examining the efficacy of two self-monitoring methods for an app-based multi-behaviour intervention to improve physical activity, sitting and sleep in adults.

Authors:  Mitch J Duncan; Corneel Vandelanotte; Stewart G Trost; Amanda L Rebar; Naomi Rogers; Nicola W Burton; Beatrice Murawski; Anna Rayward; Sasha Fenton; Wendy J Brown
Journal:  BMC Public Health       Date:  2016-07-30       Impact factor: 3.295

8.  Noncontact Sleep Study by Multi-Modal Sensor Fusion.

Authors:  Ku-Young Chung; Kwangsub Song; Kangsoo Shin; Jinho Sohn; Seok Hyun Cho; Joon-Hyuk Chang
Journal:  Sensors (Basel)       Date:  2017-07-21       Impact factor: 3.576

9.  Activity Recognition for Persons With Stroke Using Mobile Phone Technology: Toward Improved Performance in a Home Setting.

Authors:  Megan K O'Brien; Nicholas Shawen; Chaithanya K Mummidisetty; Saninder Kaur; Xiao Bo; Christian Poellabauer; Konrad Kording; Arun Jayaraman
Journal:  J Med Internet Res       Date:  2017-05-25       Impact factor: 5.428

10.  The impact of an m-Health financial incentives program on the physical activity and diet of Australian truck drivers.

Authors:  Nicholas D Gilson; Toby G Pavey; Olivia Rl Wright; Corneel Vandelanotte; Mitch J Duncan; Sjaan Gomersall; Stewart G Trost; Wendy J Brown
Journal:  BMC Public Health       Date:  2017-05-18       Impact factor: 3.295

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.