Currently, in the face of the health crisis caused by the Coronavirus COVID-19 which has spread throughout the worldwide. The fight against this pandemic has become an unavoidable reality for many countries. It is now a matter involving many areas of research in the use of new information technologies, particularly those related to artificial intelligence. In this paper, we present a novel contribution to help in the fight against this pandemic. It concerns the detection of people wearing masks because they cannot work or move around as usual without protection against COVID-19. However, there are only a few research studies about face mask detection. In this work, we investigated using different deep Convolutional Neural Networks (CNN) to extract deep features from images of faces. The extracted features are further processed using various machine learning classifiers such as Support Vector Machine (SVM) and K-Nearest Neighbors (K-NN). Were used and examined all different metrics such as accuracy and precision, to compare all model performances. The best classification rate was getting is 97.1%, which was achieved by combining SVM and the MobileNetV2 model. Despite the small dataset used (1376 images), we have obtained very satisfactory results for the detection of masks on the faces.

No abstract

This article is part of the field of Multi-Criteria Decision Aid (MCDA), where several criteria must be considered in decision making. All criteria are generally as varied as possible and express different dimensions, and aspects of the decision problem posed. For more than four decades, several MCDA methods have emerged and have been applied perfectly to solve a large number of multi-criteria decision problems. Several studies have tried to compare these methods directly with one another. Since each method has its disadvantages and advantages, a direct comparison between the two methods is normally far from common sense and becomes subjective. In this article, we propose a rational and objective approach that will be used to compare the methods between them. This approach consists of using the famous correlation measure to evaluate the quality of the results obtained by different MCDA approaches. To prove the effectiveness of the proposed approach, experimental examples, as well as a study of real cases, will be studied. Indeed, a set of indicators, known as The Europe 2020 indicators, are defined by the European Commission (EC) to control the smart, sustainable and inclusive growth performance of the European Union countries (EU). In this proposed real study, a subset of indicators is used to compare the performance of environmental preservation and protection of the EU states. For this, the two-renowned methods MCDA ELECTRE II and TOPSIS are used to classify from the best to the worst CE countries with regard to environmental preservation. The results of the experiment that the proposed ranking quality measure is significant. For the case study shows that the ELECTRE II method results in a better ranking than that obtained by the TOPSIS method.

No abstract

No abstract