A multi-level refinement approach towards the classification of quotidian activities using accelerometer data

Ortega-Anderez, D. ORCID: 0000-0003-3571-847X, Lotfi, A. ORCID: 0000-0002-5139-6565, Langensiepen, C. ORCID: 0000-0002-0165-9048 and Appiah, K. ORCID: 0000-0002-9480-0679, 2018. A multi-level refinement approach towards the classification of quotidian activities using accelerometer data. Journal of Ambient Intelligence and Humanized Computing. ISSN 1868-5137

[img]
Preview
Text
12425_Lotfi.pdf - Post-print

Download (651kB) | Preview

Abstract

Wearable inertial measurement units incorporating accelerometers and gyroscopes are increasingly used for activity analysis and recognition. In this paper an activity classification algorithm is presented which includes a novel multi-step refinement with the aim of improving the classification accuracy of traditional approaches. To do so, after the classification takes place, information is extracted from the confusion matrix to focus the computational efforts on those activities with worse classification performance. It is argued that activities differ diversely from each other, therefore a specific set of features may be informative to classify a specific set of activities, but such informativeness should not necessarily be extended to a different activity set. This approach has shown promising results, achieving important classification accuracy improvements of up to 4% with the use of low-dimensional feature vectors.

Item Type: Journal article
Publication Title: Journal of Ambient Intelligence and Humanized Computing
Creators: Ortega-Anderez, D., Lotfi, A., Langensiepen, C. and Appiah, K.
Publisher: Springer
Date: 30 October 2018
ISSN: 1868-5137
Identifiers:
NumberType
10.1007/s12652-018-1110-yDOI
Divisions: Schools > School of Science and Technology
Depositing User: Jill Tomkinson
Date Added: 05 Nov 2018 15:53
Last Modified: 05 Nov 2018 15:53
URI: http://irep.ntu.ac.uk/id/eprint/34845

Actions (login required)

Edit View Edit View

Views

Views per month over past year

Downloads

Downloads per month over past year