Séminaire ACMES/ARMEDIA de Hela Sfar – jeudi 28/02 à 15h15 en BL005 : Dynamic Streaming Sensor Data Segmentation for Smart Environments Applications

Hela Sfar, doctorante, 3ème année qui effectue sa thèse dans le cadre du projet FUI COCAPS fera une présentation Jeudi 28 Février à 14h salle BL005 sur la segmentation dynamique de données de capteurs.

Quand : Jeudi 28 février de 15h15 à 16h00
Où : en BL005, à Télécom SudParis, Evry
Titre : Dynamic Streaming Sensor Data Segmentation for Smart Environments Applications

With the increasing availability of unobtrusive, and inexpensive sensors in smart environments, online sensor data segmentation becomes an important topic in reconstructing and understanding sensor data. Usually, in the literature, the segmentation is either performed by following a fixed or a dynamic time-window length. As stated in several works, static time-window length has several drawbacks while adjusting dynamically the window length is more appropriate. However, each of the previous methods for dynamic data segmentation targets only a particular type of application. Hence, there is a need for a general method independent of applications providing a high degree of usability. This talk presents a novel method that dynamically adapts the time-window size by combining statistical learning and knowledge representation. The proposal is designed to be applied in a wide range of applications (activity recognition, decision making, etc.).