A One-Vs-One classifier ensemble with majority voting for activity recognition

Romera-Paredes, B., Aung, M. S.H. and Bianchi-Berthouze, N. (2013) A One-Vs-One classifier ensemble with majority voting for activity recognition. In: ESANN 2013 proceedings, 21st European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. ESANN 2013 proceedings, 21st European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. BEL, pp. 443-448. ISBN 9782874190810

Full text not available from this repository.

Abstract

A solution for the automated recognition of six full body motion activities is proposed. This problem is posed by the release of the Activity Recognition database [1] and forms the basis for a classification competition at the European Symposium on Artificial Neural Networks 2013. The data-set consists of motion characteristics of thirty subjects captured using a single device delivering accelerometric and gyroscopic data. Included in the released data-set are 561 processed features in both the time and frequency domains. The proposed recognition framework consists of an ensemble of linear support vector machines each trained to discriminate a single motion activity against another single activity. A majority voting rule is used to determine the final outcome. For comparison, a six "winner take all" multiclass support vector machine ensemble and k-Nearest Neighbour models were also implemented. Results show that the system accuracy for the one versus one ensemble is 96.4% for the competition test set. Similarly, the multiclass SVM ensemble and k-Nearest Neighbour returned accuracies of 93.7% and 90.6% respectively. The outcomes of the one versus one method were submitted to the competition resulting in the winning solution.

Item Type: Book Section
Uncontrolled Keywords: artificial intelligence,information systems ,/dk/atira/pure/subjectarea/asjc/1700/1702
Related URLs:
Depositing User: LivePure Connector
Date Deposited: 27 Nov 2019 02:17
Last Modified: 17 Nov 2021 04:59
URI: https://ueaeprints.uea.ac.uk/id/eprint/73161
DOI:

Actions (login required)

View Item View Item