With the rapid growth of internet of medical things (IoMT) devices, edge computing providers must proactively address cybersecurity threats. This study leverages artificial intelligence (AI) for detecting malicious activities by utilising the synthetic minority oversampling technique (SMOTE) to balance class distributions in the imbalanced dataset. It employs a weighted hybrid feature selection method combining chi-squared and light gradient boosting machine (LightGBM). The proposed solution introduces a new ensemble model using bagging with multiple base classifiers like random forest, extra trees, XGBoost, and others. Using benchmark simulated data from the Washington University St. Louis Enhanced Healthcare Monitoring System (WUSTL-EHMS), the results demonstrate that the bagging of XGBoost achieves a high accuracy of 99.04%, showcasing its effectiveness in detecting cyber threats compared to other baseline models.

Unmanned aerial vehicles (UAVs) have recently received considerable attention to improve network coverage. One promising application is to use UAVs in Wireless communications field. UAVs offer a promising solution to extend coverage and to provide high-quality network connectivity in wireless communication. For this reason, this field has received more attention from researchers in recent years. However, there are several issues that have been raised and they are not yet resolved. To address these problems, the applicability of game theory approaches has recently been explored by researchers. In this paper, we have developed a new framework for the use of the UAV to cover access to network services for such a geographical area with a parameterization based on availability, access price and quality of service. A complete analytical study of the game's results, based on equilibrium price, equilibrium quality of service and equilibrium availability, is derived. More precisely, we showed the existence and uniqueness of the Nash equilibrium under some conditions. Furthermore, we are implementing the best response algorithm as a dynamic learning method that allows drones to quickly find the Nash Equilibrium situation in a distributed fashion. Finally, numerical analysis offers encouraging insights into how to choose game parameters to effectively control the game and confirm our proposal.

Normally, the full use of the network can not be done when we opened a single connection, this can be noticed especially when the quality of the network is not good. The paper aims to maximize the transmission capacity of the mobile applications while guaranteeing the stability of the hole system in presence of an incomplete informations. We formulate a Bayesian game to the network resource allocation problem under the selfish behaviour of mobile applications with multiple connections to a several available network interfaces simultaneously. The maximum data transfer rate for a network interface is private information and is considered as the type of the player(mobile application). The mobile application choses the number of concurrent connections to maximize its own profit. Based on the number of concurrent connections, the mobile applications decide the strategies to maximize their payoffs defined as the difference between the transmission capacity and the connection maintenance cost. After showing the existence and uniqueness of equilibrium in terms of number of concurrent connections, we analyze the impact of interactions between applications on the data transfer rate. We also validated our theoretical study with numerical results, which show that the non-cooperative game has an Bayesian Nash equilibrium (BNE) point which depends on all parameters of the system.

In this paper, we have studied the impact of customer confusion on the decision-making strategies of Internet service providers (ISP) in the network and telecommunications market. This confusion may come from several factors, e.g. incomplete information on the offer, non-transparent advertising, the ability of the analysis, etc.; but that sure varies over time since yesterday’s customer is no longer today’s. In this work, we have developed a simple oligopolistic model, using non-cooperative game theory, to formalize the interactions between service providers and end-users by considering that the rationality of customers varies over time. We assessed the impact of the dynamics of consumer confusion on the competition and profitability of service providers who are considered rational and competitive with one another to maximize their respective gains in the face of a confused fraction of consumers while others are not confused. We have shown the existence and uniqueness of the Nash equilibrium. We used the best response dynamic algorithm for learning Nash equilibrium. On the one hand, we have shown that when the number of confused customers is large, the ISP is interested in that and they offer moderately high prices with low quality of service. On the other hand, over time, rationality increases, forcing the ISPs to change their strategies by offering better services so that their demand increases. We also add that when customer behavior changes quickly, the ISPs follow clearer strategies with customer satisfactory services.

In the last years, mobile devices need more and more transmission capacity, despite the development of the number and the performance of network interfaces, these latter cannot be fully utilized by the most applications. In this paper, we propose a solution to the network resource allocation problem under the selfish behavior of mobile applications with multiple connections to a several available network interfaces simultaneously. Where those applications are not only in interaction with others phones applications, but also with applications in the same phone, in particular, those applications which require more data rate speed (voice over internet protocol, the live video streaming, online gaming,). A transmission mobile applications game is proposed to resolve the conflict of interest in the network, under different types of interactions (cooperation/competition). After showing the existence and uniqueness of equilibrium in terms of number of concurrent connections, we analyze the impact of interactions between applications on the data transfer rate. We also validated our theoretical study with numerical results, which show that the non-cooperative game has an equilibrium point which depends on all parameters of the system; and we show that the cooperative situation between applications is much more beneficial in terms of the performance of mobiles and the data transfer rate.