Chicoutimi, Canada
Chicoutimi, Canada

Time filter

Source Type

Bouchard K.,LIARA Laboratory | Fortin-Simard D.,LIARA Laboratory | Gaboury S.,LIARA Laboratory | Bouchard B.,LIARA Laboratory | Bouzouane A.,LIARA Laboratory
International Journal of Wireless Information Networks | Year: 2014

The smart home as emerged in recent years as a new trend of research aiming to propose an alternative to postpone the institutionalization of cognitively-impaired people. These habitats are intended to provide security, guidance and direct support services to its resident. To fulfill this important mission, an algorithm first has to identify the ongoing activities of its user by tracking, in real time, the position of the main daily living objects. Many researchers addressed this issue by proposing systems based ultrasonic wave sensors, video cameras, and radio-frequency identification (RFID). However, the RFID technology, constitutes the most viable technology for smart homes. Recently, several RFID localization algorithms have been developed, mainly for commercial and industrial uses, but they are not precise enough to be used in an assistive context. Furthermore, the majority of them focuses on systems exploiting active RFID tags, which need batteries and are much more expensive. We present, in this paper, a new algorithmic approach for passive RFID localization in smart homes based on elliptical trilateration and fuzzy logic. This new algorithm has been implemented in a real smart home infrastructure. It has been rigorously tested and outperformed the comparable approaches. © 2013 Springer Science+Business Media New York.


Bouchard K.,LIARA Laboratory | Bouzouane A.,LIARA Laboratory | Bouchard B.,LIARA Laboratory
Proceedings of the 2013 IEEE Symposium on Computational Intelligence and Data Mining, CIDM 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013 | Year: 2013

Human Activity Recognition (HAR) is a challenging problem that could enable an outstanding number of applications in pervasive computing. Many approaches have been developed to overcome this issue, but they all suffer from major drawbacks. While some use invasive sensors such as video-cameras and wearable technology, other exploit complex models to only recognize coarse-grained activities. In this paper, we propose to exploit the largely neglected spatial aspects in the smart home to recognize the activity of daily living (ADLs) of a resident in a noninvasive fashion. To do so, we designed an extension to well-known data mining algorithms that we exploit to automatically learn the models of the resident ADLs. The models are built from the retrieval of spatial patterns corresponding to the topological relationships of the smart home entities. We demonstrate the advantages of our new semi-supervised system through comprehensive experiments inside a smart home and compare the results with expert defined models of activity. © 2013 IEEE.

Loading LIARA Laboratory collaborators
Loading LIARA Laboratory collaborators