Séminaire de TA Viet Cuong, doctorant de l'Institut MICA et de PRIMA Grenoble - Date : jeudi 6 août 2015, 15h00 - Lieu : salle "seminar", 9ème étage, Institut MICA, Hanoi University of Science and Technology

Intervenant :
M. TA Viet Cuong, doctorant en co-tutelle Institut MICA et équipe PRIMA/LIG/Inria Grenoble

Date : jeudi 6 août 2015, 15h00
Lieu : salle "seminar room", 9ème étage, bâtiment B1, Institut MICA, Hanoi University of Science and Technology
Langue : le séminaire sera présenté en anglais

Résumé/Abstract:
WIFI localization is one of main direction for indoor localization. It bases on statistical approach to extract positional information from the unreliable wifi radio signal of the indoor localization. However, it has several weaknesses, such as highly time consuming process of site-surveying and unstable accuracy. This study addresses these problems by using an autonomous robot for building the data map. More specifically, the data is collected at INRIA, by an autonomous robot without the human intervention. From the data, three machine learning models, K-Nearest Neighbours, Random Forest and Support Vector Machine, are used to learn the data and compare results. The average distant error are 2m for N-fold testing and 6m with a further valdation testing. Other factors, which can affect the accuracy of the Wifi Localization, such as the model and the position of the phone are tested within the same environment.