Judgments made on a subject by certain people can take various forms. In the case of the covid-19 crisis, certain opinions on the vaccine for this pandemic have generated a lot of comments of various kinds. Unfortunately, some of them have some side effects that vary from person to person. This phenomen on creates then feelings of caution in the population not yet vaccinated. The objective of this article is to propose a model allowing us to analyze and understand the characteristics of the categories of people who made these comments. This model identifies individuals based on the classes of comments issued. It is based on a hybrid approach combining the multinomial logistic model and a genetic model. An application is made on the data of the comments of the Covid-19 in Côte d’Ivoire.

In the growing context of online exam surveillance to ensure academic integrity, biometric authentication through facial recognition has become a common practice. However, the efficacy of this method is being questioned due to the potential vulnerability associated with the use of printed images to bypass the monitoring system. This vulnerability raises significant concerns regarding the security and authenticity of online assessments, thereby necessitating a deeper exploration of more reliable and secure facial liveness detection methods. In this study, we proposed a real-time approach for detecting facial liveliness within an anti-fraud device during online exams, leveraging facial recognition technology. Our focus was on employing a convolutional neural network algorithm to extract distinctive facial features. Convolutional neural networks, known for their adeptness in pattern detection and recognition, were at the core of our investigation. We delved into analyzing facial liveliness through two distinct approaches. Firstly, we meticulously examined facial texture, studying a dataset comprising both genuine faces and reproductions on various media such as fabric or masks. Concurrently, we implemented a method centered on detecting eye blinking. Regarding the implementation with the neural network algorithm, the results unveiled a precision rate of 57% for skin texture analysis, highlighting the inherent challenges of this method. Conversely, the eye blinking approach exhibited significantly better performance, with a precision of 96%, emphasizing its strong potential in detecting facial liveliness.

This paper presents a novel approach to improving urban road traffic control using artificial intelligence (AI) for dynamic traffic light management. We begin by describing the current context of urban traffic management and the challenges facing traffic light infrastructures. We then explain how AI can be integrated into this context for more effective regulation. We have chosen to use a basic model based on convolutional neural networks (CNN) to model road traffic in real time. This model collects real-time data from traffic cameras and other sensors, pre-processes it and then analyses it to make intelligent decisions about traffic light control. By using historical data and adapting to changing conditions, our model has been able to reduce waiting times at intersections, minimise congestion and improve traffic flow. This research paves the way for more intelligent and adaptive traffic management in urban environments. The practical implications of our approach include more efficient urban mobility, reduced greenhouse gas emissions and improved road safety. Future prospects lie in the continued optimisation of the AI model and its integration with other intelligent transport systems, contributing to more sustainable and liveable cities.