CoChat
Sign Up
Cited by 186Context-Aware Activity Recognition SystemsPhysical Activity and HealthHuman Mobility and Location-Based Analysis

Hip and Wrist Accelerometer Algorithms for Free-Living Behavior Classification

Open access
ELLIS, KATHERINE, KERR, JACQUELINE, GODBOLE, SUNEETA, STAUDENMAYER, JOHN, LANCKRIET, GERT·2016·Medicine & Science in Sports & Exercise
DOI 10.1249/mss.0000000000000840PMC PMC4833514
Open this paper in CoChat — free account

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.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1249/mss.0000000000000840

Cites

35 of 35 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • A strong random forest model with tried-and-tested time series features has often been neglected in baseline model comparisons.

    “a strong random forest model with tried-and-tested time series features, which has often been neglected in baseline model comparisons8,48–50.”

    From Self-supervised learning for human activity recognition using 700,000 person-days of wearable data (2024) · cites this paper as [50]

    The Methods (Behavior classification algorithm; page unavailable) describe extracting time- and frequency-domain features from accelerometer data and feeding them into a random forest. The Discussion reports that the resulting classifier improved on traditional cutpoint methods. Our copy does not say that such a model has often been neglected in baseline comparisons. (LLM, conf=0.84)

    Experimental — accuracy not yet measured

  • Walking is challenging to classify in free-living conditions (sensitivity = 0.71, specificity = 0.96).

    “However, our data and that from Ellis et al 30 . shows that walking is challenging to classify in free-living conditions (sensitivity = 0.71, specificity = 0.96), probably due to it being part of many everyday activities.”

    From Statistical machine learning of sleep and physical activity phenotypes from sensor data in 96,220 UK Biobank participants (2018) · cites this paper as [30]

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

1 of the 36 references couldn’t be matched to a known paper.

Research works printed but not linked: 2

  1. [9]Ellis K Godbole S Chen J Marshall S Lanckriet G Kerr J Physical activity recognition in free-living from body-worn sensors Proceedings of the 4th International SenseCam & Pervasive Imaging Conference 2013 Nov San Diego 2013 88 89
  2. [17]Kerr J Patterson R Ellis K Godbole S Johnson E Lanckriet G Staudenmayer S Objective Assessment of Walking and Sitting: Classifiers for Public Health Med Sci Sports Exerc In press PMC4837464 27089222

Cited by

Sorted by citations

Related

Authors
ELLIS, K., KERR, J., GODBOLE, S., STAUDENMAYER, J., & LANCKRIET, G.
Affiliations
University of Massachusetts Amherst (US)
ORCID
Venue
Medicine & Science in Sports & Exercise
Publisher
Ovid Technologies (Wolters Kluwer Health)
Published
2016-05
Volume
48
Issue
5
Pages
933-940
ISSN
0195-9131 (ISSN-L)
DOI
10.1249/mss.0000000000000840
PMC
PMC4833514
OpenAlex
W2327453846
Cited by
186
References
36
Citations by year
2026: 7 · 2025: 18 · 2024: 18 · 2023: 10 · 2022: 14 · 2021: 23 · 2020: 20 · 2019: 25 · 2018: 22 · 2017: 20 · 2016: 8 · 2015: 1
FWCI
14.65
Type
journal article
Language
en
Open access
Locations
  • Medicine & Science in Sports & Exercise (publishedVersion)
  • PubMed (publishedVersion)
  • PubMed Central (acceptedVersion)
Funders
National Cancer Institute (R01CA164993)
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
  • Health Sciences › Medicine › Physiology › Physical Activity and Health
  • Social Sciences › Transportation › Human Mobility and Location-Based Analysis
Keywords
hip-worn accelerometers, wrist-worn accelerometers, physical activity classification, free-living activity monitoring, random forest, hidden Markov models, accelerometer cut-points, walking and running detection, wearable cameras, ActiGraph GT3X+
MeSH terms
Machine Learning, Activities of Daily Living, Adult, Aged, Algorithms, Female, Hip, Humans, Markov Chains, Middle Aged, Obesity, Sensitivity and Specificity, Wrist, Exercise, Monitoring, Ambulatory, Overweight, Accelerometry

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review