Abstract: In this paper, we first describe the general principle of dynamic modelling, the effectiveness of which in analyzing the traffic of multiservice networks is one of the main objects of this study. By showing how this technique can be applied to obtain the elementary Markovian system: of the queue M/M/1/∞; we partly answer the big problem on the management of the QoS in the case of an isolated node then of a network. We then focus on the principles of traffic control of multiservice networks, drawing inspiration from existing work in the literature and from policies for managing congestion phenomena defined in recommendations I.371 of the ITU-T and ATM-Forum UNI specification V3.1. As a possible solution to this problem, we have evoked the hypothesis of the reaction to congestion by dynamic traffic compression, in the event of the appearance of a phenomenon of congestion exceeding any prediction. The progress of this hypothesis will have the merit of resurfacing and increasing the interest of resorting to compression as a solution to the problem of congestion, in particular for wireless networks; since radio resources are scarce and shared.

Abstract: This work focuses on the design and implementation of a computer system capable of tracking the position of a vehicle in real time and recording its different positions during a journey. Thanks to such a system, the owner of the vehicle will be kept informed of the various past locations of his vehicle but also of other additional information which will be provided to him by the system, for example the total distance traveled by the vehicle, etc. To succeed in designing such a system, we used two technologies: GPS and GSM (GPRS). GPS is a technology that, thanks to a constellation of satellites orbiting the earth, allows us to obtain the geographical location of a place (or geographical coordinates including latitude, longitude and altitude). GSM, on the other hand, refers to the cellular network which serves as a transmission medium for conveying the geographical coordinates freshly collected. Concretely, the vehicle will be equipped with an embedded system consisting of an Arduino card, a GPS chip and a GSM/GPRS expansion card. This on-board system will send the geographical coordinates to a computer server in which is installed a database intended to store this data. Thanks to a web application linked to this database, the owner will be able to track his vehicle.

The dark and worrying health picture characterized by the revelations made by international organizations concerning pneumonia challenged us as researchers. It is in this perspective that we decided to make our contribution to this problem by presenting a system for pneumonia detection in chest x-ray images. To achieve this goal, we used an approach based on deep learning to properly identify pathological or non-pathological radiographs by setting up a convolutional neural network called Xception. Two optimization algorithms were selected, namely Adam and SGD. The setting of hyperparameters of our convolutional neural network led us to a promising result compared to the size of our dataset. In conclusion, the obtained results in our experiments showed that the SGD optimization algorithm reached the best result of 92% accuracy on new data with a learning rate of 0.001 for 20 epochs.