A comparison of feature extraction methods for the classification of dynamic activities from accelerometer data

Preece, SJ ORCID: https://orcid.org/0000-0002-2434-732X, Goulermas, JY, Kenney, LPJ ORCID: https://orcid.org/0000-0003-2164-3892 and Howard, D ORCID: https://orcid.org/0000-0003-1738-0698 2009, 'A comparison of feature extraction methods for the classification of dynamic activities from accelerometer data' , IEEE Transactions on Biomedical Engineering, 56 , pp. 871-879.

PDF - Accepted Version
Download (516kB) | Preview
[img] PDF - Published Version
Restricted to Repository staff only

Download (369kB) | Request a copy


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 non-stationary 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% inter-subject classification accuracy.

Item Type: Article
Themes: Subjects / Themes > R Medicine > RZ Other systems of medicine
Health and Wellbeing
Schools: Schools > School of Computing, Science and Engineering > Salford Innovation Research Centre
Schools > School of Health and Society > Centre for Health Sciences Research
Journal or Publication Title: IEEE Transactions on Biomedical Engineering
Publisher: Institute of Electrical and Electronics Engineers
Refereed: Yes
ISSN: 0018-9294
Depositing User: SJ Preece
Date Deposited: 21 Dec 2010 10:48
Last Modified: 15 Feb 2022 15:48
URI: https://usir.salford.ac.uk/id/eprint/12578

Actions (login required)

Edit record (repository staff only) Edit record (repository staff only)


Downloads per month over past year