Katherine Ellis1, Jacqueline Kerr, Suneeta Godbole, John Staudenmayer, Gert Lanckriet. 1. 1Department of Electrical and Computer Engineering, University of California, San Diego, CA; 2Department of Family Medicine and Public Health, University of California, San Diego, CA; and 3Department of Mathematics and Statistics, University of Massachusetts, Amherst, MA.
Abstract
PURPOSE: Accelerometers are a valuable tool for objective measurement of physical activity (PA). Wrist-worn devices may improve compliance over standard hip placement, but more research is needed to evaluate their validity for measuring PA in free-living settings. Traditional cut-point methods for accelerometers can be inaccurate and need testing in free living with wrist-worn devices. In this study, we developed and tested the performance of machine learning (ML) algorithms for classifying PA types from both hip and wrist accelerometer data. METHODS: Forty overweight or obese women (mean age = 55.2 ± 15.3 yr; BMI = 32.0 ± 3.7) wore two ActiGraph GT3X+ accelerometers (right hip, nondominant wrist; ActiGraph, Pensacola, FL) for seven free-living days. Wearable cameras captured ground truth activity labels. A classifier consisting of a random forest and hidden Markov model classified the accelerometer data into four activities (sitting, standing, walking/running, and riding in a vehicle). Free-living wrist and hip ML classifiers were compared with each other, with traditional accelerometer cut points, and with an algorithm developed in a laboratory setting. RESULTS: The ML classifier obtained average values of 89.4% and 84.6% balanced accuracy over the four activities using the hip and wrist accelerometer, respectively. In our data set with average values of 28.4 min of walking or running per day, the ML classifier predicted average values of 28.5 and 24.5 min of walking or running using the hip and wrist accelerometer, respectively. Intensity-based cut points and the laboratory algorithm significantly underestimated walking minutes. CONCLUSIONS: Our results demonstrate the superior performance of our PA-type classification algorithm, particularly in comparison with traditional cut points. Although the hip algorithm performed better, additional compliance achieved with wrist devices might justify using a slightly lower performing algorithm.
PURPOSE: Accelerometers are a valuable tool for objective measurement of physical activity (PA). Wrist-worn devices may improve compliance over standard hip placement, but more research is needed to evaluate their validity for measuring PA in free-living settings. Traditional cut-point methods for accelerometers can be inaccurate and need testing in free living with wrist-worn devices. In this study, we developed and tested the performance of machine learning (ML) algorithms for classifying PA types from both hip and wrist accelerometer data. METHODS: Forty overweight or obesewomen (mean age = 55.2 ± 15.3 yr; BMI = 32.0 ± 3.7) wore two ActiGraph GT3X+ accelerometers (right hip, nondominant wrist; ActiGraph, Pensacola, FL) for seven free-living days. Wearable cameras captured ground truth activity labels. A classifier consisting of a random forest and hidden Markov model classified the accelerometer data into four activities (sitting, standing, walking/running, and riding in a vehicle). Free-living wrist and hip ML classifiers were compared with each other, with traditional accelerometer cut points, and with an algorithm developed in a laboratory setting. RESULTS: The ML classifier obtained average values of 89.4% and 84.6% balanced accuracy over the four activities using the hip and wrist accelerometer, respectively. In our data set with average values of 28.4 min of walking or running per day, the ML classifier predicted average values of 28.5 and 24.5 min of walking or running using the hip and wrist accelerometer, respectively. Intensity-based cut points and the laboratory algorithm significantly underestimated walking minutes. CONCLUSIONS: Our results demonstrate the superior performance of our PA-type classification algorithm, particularly in comparison with traditional cut points. Although the hip algorithm performed better, additional compliance achieved with wrist devices might justify using a slightly lower performing algorithm.
Authors: Richard P Troiano; David Berrigan; Kevin W Dodd; Louise C Mâsse; Timothy Tilert; Margaret McDowell Journal: Med Sci Sports Exerc Date: 2008-01 Impact factor: 5.411
Authors: Dale W Esliger; Ann V Rowlands; Tina L Hurst; Michael Catt; Peter Murray; Roger G Eston Journal: Med Sci Sports Exerc Date: 2011-06 Impact factor: 5.411
Authors: Vincent T van Hees; Frida Renström; Antony Wright; Anna Gradmark; Michael Catt; Kong Y Chen; Marie Löf; Les Bluck; Jeremy Pomeroy; Nicholas J Wareham; Ulf Ekelund; Søren Brage; Paul W Franks Journal: PLoS One Date: 2011-07-29 Impact factor: 3.240
Authors: Marta Karas; Jiawei Bai; Marcin Strączkiewicz; Jaroslaw Harezlak; Nancy W Glynn; Tamara Harris; Vadim Zipunnikov; Ciprian Crainiceanu; Jacek K Urbanek Journal: Stat Biosci Date: 2019-01-12
Authors: K W DeGregory; P Kuiper; T DeSilvio; J D Pleuss; R Miller; J W Roginski; C B Fisher; D Harness; S Viswanath; S B Heymsfield; I Dungan; D M Thomas Journal: Obes Rev Date: 2018-02-09 Impact factor: 9.213