Ortega-Anderez, D ORCID: https://orcid.org/0000-0003-3571-847X, Lotfi, A ORCID: https://orcid.org/0000-0002-5139-6565, Langensiepen, C ORCID: https://orcid.org/0000-0002-0165-9048 and Appiah, K ORCID: https://orcid.org/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
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: | Number Type 10.1007/s12652-018-1110-y DOI |
Divisions: | Schools > School of Science and Technology |
Record created by: | Jill Tomkinson |
Date Added: | 05 Nov 2018 15:53 |
Last Modified: | 05 Nov 2018 15:53 |
URI: | https://irep.ntu.ac.uk/id/eprint/34845 |
Actions (login required)
Edit View |
Statistics
Views
Views per month over past year
Downloads
Downloads per month over past year