Data exploiting from simulators of road traffic is a well-established field. This paper addresses the development of a tool for data representing for Simulation of Urban MObility (SUMO) software; aiming at first, to (a) optimize of required simulation scenarios inputs (i.e. configuration files), and parse generated data of simulation scenarios such as CO2 emission, noise emission. Secondly, to (b) make generated data more consumable, such as map of emissions activities along the area of study. The evaluation was done with a real-world scenario of Casablanca city, to highlight the performance of the proposed solution.

Data exploiting from simulators of road traffic is a well-established field. This paper addresses the development of a tool for data representing for Simulation of Urban MObility (SUMO) software; aiming at first, to (a) optimize of required simulation scenarios inputs (i.e. configuration files), and parse generated data of simulation scenarios such as CO2 emission, noise emission. Secondly, to (b) make generated data more consumable, such as map of emissions activities along the area of study. The evaluation was done with a real-world scenario of Casablanca city, to highlight the performance of the proposed solution.

Diabetic retinopathy (DR) is considered one of the worldwide diseases of blindness, especially in the elderly. The main reason for this disease is the complication of diabetes in the retinal blood vessels. Usually, the warning signs are not observed. Screening is an important key to diagnosing the early stages of diabetic retinopathy. This work represents an intelligent system of DR classification based on deep learning (DL) tools, especially convolutional neural networks (CNN). Proposed system can assist ophthalmologists to make a preliminary decision, it allows a DR classification considering normal eyes, mild DR, Moderate DR, Severe DR and Proliferative DR. Obtained results, in terms of classification accuracy, for DR classification using the color retinal background images based on VGG-16 and ResNet50 models are in order 70% and 25% respectively.