Skip to Main content Skip to Navigation
Poster communications

Opportunistic Human Activity Recognition: a study on Opportunity dataset

Luis Gioanni 1 Christel Dartigues-Pallez 2 Stéphane Lavirotte 1 Jean-Yves Tigli 1
1 Laboratoire d'Informatique, Signaux, et Systèmes de Sophia-Antipolis (I3S) / Equipe RAINBOW
Laboratoire I3S - SPARKS - Scalable and Pervasive softwARe and Knowledge Systems
2 Laboratoire d'Informatique, Signaux, et Systèmes de Sophia-Antipolis (I3S) / Projet MinD
Laboratoire I3S - SPARKS - Scalable and Pervasive softwARe and Knowledge Systems
Abstract : A lot of research has been done for human activity recognition. But most of it uses a static and immutable set of sensors known beforehand. This approach does not work when applied to a ubiquitous or mobile system, since we cannot know which sensors will be available in the users’ surroundings. This is why we consider here an opportunistic approach, where each sensor individually trained are able to bring its own knowledge. Inspired by the Opportunity project, we propose to evaluate both the effectiveness of using a Random Forest (RF) classifier to train the sensors and the robustness of fusing the results using a weighted majority vote. We found that RF gave better and more robust results than the other classifiers formally tested by Opportunity.
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-01374534
Contributor : Stéphane Lavirotte <>
Submitted on : Friday, September 30, 2016 - 3:34:06 PM
Last modification on : Thursday, March 5, 2020 - 12:20:47 PM

Identifiers

  • HAL Id : hal-01374534, version 1

Collections

Citation

Luis Gioanni, Christel Dartigues-Pallez, Stéphane Lavirotte, Jean-Yves Tigli. Opportunistic Human Activity Recognition: a study on Opportunity dataset. 13th Annual International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services, Nov 2016, Hiroshima, Japan. Proceeding of the 13th Annual International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services. ⟨hal-01374534⟩

Share

Metrics

Record views

298