The phenomenon of leaving against medical advice remains a significant issue in public reference institutions in Côte d’Ivoire. Thus, one out of twelve adult patients hospitalized in the Orthopedics – Traumatology department of the Treichville University Hospital often interrupts their treatment in favor of traditional Bone-Setters or other destinations. However, despite recent advances in machine learning, it is still challenging to predict what type of destination these absconding patients will choose. Therefore, this article first aims to sequentially establish two datasets based on medical records: one original and the other after feature selection. Then, based on these datasets, this research involved four supervised machine learning models (Logistic Regression (LR), Decision Tree (DT), Random Forest (RF), and Gradient Boosting (GB)). The results obtained from performance metrics during testing, after five cross-validations, show that Random Forest is the most robust model for both datasets. Finally, a second analysis indicates that the Random Forest built on the original dataset remains the best model overall, with an AUC-ROC of 96%, an accuracy of 86%, a precision of 84%, a recall of 100%, and an F1-Score of 91%. These results suggest that this model offers hope for early and accurate prediction of the destination the absconding patient will opt for, thus positively impacting their care.

Mobile money is a financial service available on mobile phones. The evolution of mobile telephony in Africa, and particularly in Côte d’Ivoire, has led to the growing evolution of mobile money services. These services have revolutionized the lives of citizens who do not have access to or do not have a bank account. Thanks to the mobile money service, any citizen can now transfer, withdraw or save money and even make payments. However, with the digitalization of systems, users of these mobile money services suffer from cyberattacks thanks to the scale of social engineering. To slow down and fight against this evolution of cyberattacks. In this article, we propose a new multi-factor authentication system in the context of mobile money transactions unlike the two-factor authentication system. We have developed an authentication algorithm for transfers using a password, fingerprint or secret word and a secret code. For direct deposit, we have proposed a system that provides a withdrawal code to the issuer that the recipient must provide upon withdrawal. We also proposed an authentication algorithm for password changes based on the current password and a secret code to provide. These contributions will help curb deposits made by mistake, scams and theft of mobile phones with password theft.

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.

The creation of a «Serious Game» can take several approaches, ranging from total creativity to the adaptation of an existing game. A game engine calls on a set of software components as diverse as scripting, the graphics engine, artificial intelligence, the physical effects engine, the audio engine and networking, all of which come into play in the design of a Serious Game. The aim of this research is to find out how game components, otherwise known as game assets, interact with each other in the design of a Serious Game to contribute to learner motivation The research aims to understand how the components or assets of a «Serious Game» interact to motivate the learner. A study was carried out with 50 3rd grade students, aged between 14 and 16, who were experiencing difficulties in mathematics. These students, familiar with digital technology, were immersed in a game designed to reinforce their mathematical skills. The aim was to demonstrate the effectiveness of the «serious game» as a pedagogical tool, and to underline the importance of adapted game assets for maximum immersion and interactivity. Following a questionnaire, the analysis showed a moderate correlation between the various game assets, confirming that graphics, sound, mechanics, narrative, interactivity and accessibility are crucial in the design of an educational game.