Title: Comparing Different Machine-Learning Techniques to Predict Vehicles’ Positions Using the Received Signal Strength of Periodic Messages
Speaker: Mamoudou Sangare, Cnam/Inria.
Time: 16:30, September 19, 2019
Room: amphi V Jean-Prouvé, accès 11, 292 rue St Martin, Paris
Abstract:
One of the main causes of death on roads is car accident. It has been pointed out that the majority of road accidents are due to human errors and these errors could have been avoided if drivers are assisted with accurate positioning system allowing them to be warned on time. Vehicular Adhoc Networks, known as VANETs, are deployed to reduce the risk of road accidents as well as to improve passenger comfort by allowing vehicles to exchange different type of data between the vehicles themselves and the roadside units. The data exchanged between vehicles ranges widely from road safety messages and traffic management infotainment. Recently, safety applications are receiving a great deal of attention from researchers as well as from automobile manufactures. Determining vehicles position using machine learning schemes is the corner stone of my thesis which has as title: Exploring Prediction Strategies in Vehicular Network and Vehicular IoT Paradigm through Machine Learning and Hybrid Intelligence.
Biographie:
Mamoudou Sangaré est né en République de Guinée et a obtenu son diplôme d’ingénieur en informatique en 2010 à l’Université Gamal Abdel Nasser de Conakry-Guinée. Une année plus tard, il obtient une bourse d’étude pour les cours de master en Malaisie et l’obtient en 2014. De retour au pays en 2015, il travail chez Huawei en qualité d’ingénieur de planification et d’optimisation réseaux jusqu’à son départ en Janvier 2018 pour ses travaux de thèse.
