Marouan Baklouti

the work developed consisted on constructing a new linear-regression model for the estimation of the path-loss exponent and the parameters of the shadowing from the propagation-loss data collected by the mobiles with respect to their serving base stations. After validation of the model, a cartography interface was constructed to visualize the propagation-loss prediction in Tunis.

Within the department ’Images and Deep Learning ’, the work developed consisted of the construction and the implementation of a particle filter, also known by sequential Monte Carlo filter , to the noisy images captured by the Sentinel Satellite 2-A. The idea of the filter implementation is to estimate the posterior density of the pixels assuming that all the pixels form a Markov chain.