Literature DB >> 26673129

Performance of Activity Classification Algorithms in Free-Living Older Adults.

Jeffer Eidi Sasaki1, Amanda M Hickey, John W Staudenmayer, Dinesh John, Jane A Kent, Patty S Freedson.   

Abstract

PURPOSE: The objective of this study is to compare activity type classification rates of machine learning algorithms trained on laboratory versus free-living accelerometer data in older adults.
METHODS: Thirty-five older adults (21 females and 14 males, 70.8 ± 4.9 yr) performed selected activities in the laboratory while wearing three ActiGraph GT3X+ activity monitors (in the dominant hip, wrist, and ankle; ActiGraph, LLC, Pensacola, FL). Monitors were initialized to collect raw acceleration data at a sampling rate of 80 Hz. Fifteen of the participants also wore GT3X+ in free-living settings and were directly observed for 2-3 h. Time- and frequency-domain features from acceleration signals of each monitor were used to train random forest (RF) and support vector machine (SVM) models to classify five activity types: sedentary, standing, household, locomotion, and recreational activities. All algorithms were trained on laboratory data (RFLab and SVMLab) and free-living data (RFFL and SVMFL) using 20-s signal sampling windows. Classification accuracy rates of both types of algorithms were tested on free-living data using a leave-one-out technique.
RESULTS: Overall classification accuracy rates for the algorithms developed from laboratory data were between 49% (wrist) and 55% (ankle) for the SVMLab algorithms and 49% (wrist) to 54% (ankle) for the RFLab algorithms. The classification accuracy rates for SVMFL and RFFL algorithms ranged from 58% (wrist) to 69% (ankle) and from 61% (wrist) to 67% (ankle), respectively.
CONCLUSIONS: Our algorithms developed on free-living accelerometer data were more accurate in classifying the activity type in free-living older adults than those on our algorithms developed on laboratory accelerometer data. Future studies should consider using free-living accelerometer data to train machine learning algorithms in older adults.

Entities:  

Mesh:

Year:  2016        PMID: 26673129      PMCID: PMC4833628          DOI: 10.1249/MSS.0000000000000844

Source DB:  PubMed          Journal:  Med Sci Sports Exerc        ISSN: 0195-9131            Impact factor:   5.411


  17 in total

1.  Motion pattern and posture: correctly assessed by calibrated accelerometers.

Authors:  F Foerster; J Fahrenberg
Journal:  Behav Res Methods Instrum Comput       Date:  2000-08

2.  Understanding interobserver agreement: the kappa statistic.

Authors:  Anthony J Viera; Joanne M Garrett
Journal:  Fam Med       Date:  2005-05       Impact factor: 1.756

3.  Detection of daily activities and sports with wearable sensors in controlled and uncontrolled conditions.

Authors:  M Ermes; J Pärkka; J Mantyjarvi; I Korhonen
Journal:  IEEE Trans Inf Technol Biomed       Date:  2008-01

Review 4.  Activity identification using body-mounted sensors--a review of classification techniques.

Authors:  Stephen J Preece; John Y Goulermas; Laurence P J Kenney; Dave Howard; Kenneth Meijer; Robin Crompton
Journal:  Physiol Meas       Date:  2009-04-02       Impact factor: 2.833

5.  Detection of type, duration, and intensity of physical activity using an accelerometer.

Authors:  Alberto G Bonomi; Annelies H C Goris; Bin Yin; Klaas R Westerterp
Journal:  Med Sci Sports Exerc       Date:  2009-09       Impact factor: 5.411

6.  Assessment of posture and motion by multichannel piezoresistive accelerometer recordings.

Authors:  J Fahrenberg; F Foerster; M Smeja; W Müller
Journal:  Psychophysiology       Date:  1997-09       Impact factor: 4.016

7.  The measurement of observer agreement for categorical data.

Authors:  J R Landis; G G Koch
Journal:  Biometrics       Date:  1977-03       Impact factor: 2.571

8.  A short physical performance battery assessing lower extremity function: association with self-reported disability and prediction of mortality and nursing home admission.

Authors:  J M Guralnik; E M Simonsick; L Ferrucci; R J Glynn; L F Berkman; D G Blazer; P A Scherr; R B Wallace
Journal:  J Gerontol       Date:  1994-03

9.  Methods to estimate aspects of physical activity and sedentary behavior from high-frequency wrist accelerometer measurements.

Authors:  John Staudenmayer; Shai He; Amanda Hickey; Jeffer Sasaki; Patty Freedson
Journal:  J Appl Physiol (1985)       Date:  2015-06-25

10.  An artificial neural network to estimate physical activity energy expenditure and identify physical activity type from an accelerometer.

Authors:  John Staudenmayer; David Pober; Scott Crouter; David Bassett; Patty Freedson
Journal:  J Appl Physiol (1985)       Date:  2009-07-30
View more
  32 in total

1.  Ordinal Statistical Models of Physical Activity Levels from Accelerometer Data.

Authors:  Shafayet S Hossain; Drew M Lazar; Munni Begum
Journal:  Int J Exerc Sci       Date:  2021-04-01

2.  Classifiers for Accelerometer-Measured Behaviors in Older Women.

Authors:  Dori Rosenberg; Suneeta Godbole; Katherine Ellis; Chongzhi Di; Andrea Lacroix; Loki Natarajan; Jacqueline Kerr
Journal:  Med Sci Sports Exerc       Date:  2017-03       Impact factor: 5.411

3.  Application of Convolutional Neural Network Algorithms for Advancing Sedentary and Activity Bout Classification.

Authors:  Supun Nakandala; Marta M Jankowska; Fatima Tuz-Zahra; John Bellettiere; Jordan A Carlson; Andrea Z LaCroix; Sheri J Hartman; Dori E Rosenberg; Jingjing Zou; Arun Kumar; Loki Natarajan
Journal:  J Meas Phys Behav       Date:  2021-02-25

4.  Posture and Physical Activity Detection: Impact of Number of Sensors and Feature Type.

Authors:  Q U Tang; Dinesh John; Binod Thapa-Chhetry; Diego Jose Arguello; Stephen Intille
Journal:  Med Sci Sports Exerc       Date:  2020-08

5.  [Influences of Autonomic Function, Salivary Cortisol and Physical Activity on Cognitive Functions in Institutionalized Older Adults with Mild Cognitive Impairment: Based on Neurovisceral Integration Model].

Authors:  Minhee Suh
Journal:  J Korean Acad Nurs       Date:  2021-06       Impact factor: 0.984

6.  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

7.  Free-Living Standing Activity as Assessed by Seismic Accelerometers and Cognitive Function in Community-Dwelling Older Adults: The MIND Trial.

Authors:  Shannon Halloway; Klodian Dhana; Pankaja Desai; Puja Agarwal; Thomas Holland; Neelum T Aggarwal; Jordi Evers; Frank M Sacks; Vincent J Carey; Lisa L Barnes
Journal:  J Gerontol A Biol Sci Med Sci       Date:  2021-10-13       Impact factor: 6.053

Review 8.  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

Review 9.  A Review of Activity Trackers for Senior Citizens: Research Perspectives, Commercial Landscape and the Role of the Insurance Industry.

Authors:  Salvatore Tedesco; John Barton; Brendan O'Flynn
Journal:  Sensors (Basel)       Date:  2017-06-03       Impact factor: 3.576

10.  Performance of thigh-mounted triaxial accelerometer algorithms in objective quantification of sedentary behaviour and physical activity in older adults.

Authors:  Jorgen A Wullems; Sabine M P Verschueren; Hans Degens; Christopher I Morse; Gladys L Onambélé
Journal:  PLoS One       Date:  2017-11-20       Impact factor: 3.240

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.