CoChat
Sign Up
Cited by 551Context-Aware Activity Recognition SystemsPhysical Activity and HealthGait Recognition and Analysis

A Comparison of Feature Extraction Methods for the Classification of Dynamic Activities From Accelerometer Data

Open access
Preece, Stephen J., Goulermas, John Yannis, Kenney, Laurence P. J., Howard, David·2009·IEEE Transactions on Biomedical Engineering
DOI 10.1109/tbme.2008.2006190
Open this paper in CoChat — free accountOpen PDF

Abstract

Driven by the demands on healthcare resulting from the shift toward more sedentary lifestyles, considerable effort has been devoted to the monitoring and classification of human activity. In previous studies, various classification schemes and feature extraction methods have been used to identify different activities from a range of different datasets. In this paper, we present a comparison of 14 methods to extract classification features from accelerometer signals. These are based on the wavelet transform and other well-known time- and frequency-domain signal characteristics. To allow an objective comparison between the different features, we used two datasets of activities collected from 20 subjects. The first set comprised three commonly used activities, namely, level walking, stair ascent, and stair descent, and the second a total of eight activities. Furthermore, we compared the classification accuracy for each feature set across different combinations of three different accelerometer placements. The classification analysis has been performed with robust subject-based cross-validation methods using a nearest-neighbor classifier. The findings show that, although the wavelet transform approach can be used to characterize nonstationary signals, it does not perform as accurately as frequency-based features when classifying dynamic activities performed by healthy subjects. Overall, the best feature sets achieved over 95% intersubject classification accuracy.

Integrity signals

Registry

Crossref · 10.1109/tbme.2008.2006190

Cites

43 of 43 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Claims the paper makes

We couldn’t retrieve this paper’s full text, so its claims and self-check weren’t run. The registry and citation checks still apply.

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?

  • The activity-based misalignment measure in prior work focuses on classification of interesting classes and the NULL class, with all misalignment types related to wrong classification of the NULL class.

    “To analyze and evaluate the continuous activity recognition on time series data, the activity-based misalignment measure is proposed in [32], where the HAR model focuses on the classification of the interesting classes and the NULL class, all the misalignment types are related to the wrong classification of the NULL class.”

    From Human Activity Recognition Based on Motion Sensor Using U-Net (2019) · cites this paper as [32]

Cites

Flagged first, then by citations

Cited by

Sorted by citations

Related

Authors
Preece, S. J., Goulermas, J. Y., Kenney, L. P. J., & Howard, D.
Affiliations
  • University of Salford (GB)
  • University of Liverpool (GB)
ORCID
Venue
IEEE Transactions on Biomedical Engineering
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Published
2009-03
Volume
56
Issue
3
Pages
871-879
ISSN
  • 0018-9294 (ISSN-L)
  • 1558-2531
DOI
10.1109/tbme.2008.2006190
OpenAlex
W2132691216
Cited by
551
References
43
Citations by year
2026: 8 · 2025: 11 · 2024: 20 · 2023: 24 · 2022: 26 · 2021: 46 · 2020: 49 · 2019: 42 · 2018: 59 · 2017: 54 · 2016: 39 · 2015: 42 · 2014: 40 · 2013: 31 · 2012: 24
FWCI
17.25
Type
journal article
Language
en
Open access
Licence
Locations
  • IEEE Transactions on Biomedical Engineering (publishedVersion)
  • PubMed (publishedVersion)
  • University of Salford Institutional Repository (University of Salford) (submittedVersion, cc-by)
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
  • Health Sciences › Medicine › Physiology › Physical Activity and Health
  • Physical Sciences › Engineering › Biomedical Engineering › Gait Recognition and Analysis
Keywords
activity recognition, accelerometer signals, feature extraction, wavelet transform, frequency-domain features, time-domain features, dynamic activities, walking, stair climbing, stair descent, accelerometer placement, wearable sensors, sedentary lifestyle, human activity monitoring
MeSH terms
Adult, Algorithms, Ankle, Female, Humans, Locomotion, Male, Models, Theoretical, Movement, Signal Processing, Computer-Assisted, Thigh, Reproducibility of Results, Monitoring, Ambulatory

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