Personal tools
Laboratoire d'InfoRmatique en Image et Systèmes d'information

Skip to content. | Skip to navigation

Laboratoire d'InfoRmatique en Image et Systèmes d'information
UMR 5205 CNRS / INSA Lyon / Université Claude Bernard Lyon 1 / Université Lumière Lyon 2 / École Centrale de Lyon
You are here: Home > membres

Amine El Ouassouli

photo

PhD student

Team Database Group
 
Institution Institut National des Sciences Appliquées de Lyon
Location Blaise Pascal (INSA)
 
E-mail amine.el-ouassouli at liris.cnrs.fr
Contact details Publications Thesis
 
Subject Detection of spatial-temporal dependencies in an heterogeneous sensor system
Abstract In the last decades, significant advances have been made in sensor technologies, accelerating their integration for various usages. Motions sensors, mobile phones or video cameras are intensively used in both public and private areas and for different fields of applications. The usage of a large batch of sensors producing temporal data make it possible for monitoring tools to obtain a behavior characterization of complex systems. Thereby, for each time interval where no change can be observed, we take a photography of a sensed environment. These photographies form a temporal stream describing in time the monitored system. That fact introduces a challenging problem: how to obtain non-trivial, compact and directly actionable knowledge from real time ram data produced by existing sensors ? Modeling this kind of knowledge and algorithms is the main goal of this PhD work. More precisely, we are interested on extracting temporal dependencies between interval-based streams produced by heterogeneous sensors. These streams take the form of a succession of temporal intervals representing a state (an interval is a portion of time where this state is active). Since heterogeneity is an important aspect of our work, we aim to use different kind of sensors, particularly video analysis, to extract temporal relations over spatial data as an application.
Advisor Vasile-Marian Scuturici

Last update : 2018-01-11 14:14:12