Coronavirus disease (COVID-19), which is caused by SARS-CoV-2, has been announced as a global pandemic by the World Health Organization (WHO), which results in the collapsing of the healthcare systems in several countries around the globe. Machine learning (ML) methods are one of the most utilized approaches in artificial intelligence (AI) to classify COVID-19 images. However, there are many machine-learning methods used to classify COVID-19. The question is: which machine learning method is best over multi-criteria evaluation? Therefore, this research presents benchmarking of COVID-19 machine learning methods, which is recognized as a multi-criteria decision-making (MCDM) problem. In the recent century, the trend of developing different MCDM approaches has been raised based on different perspectives; however, the latest one, namely, the fuzzy decision by opinion score method that was produced in 2020, has efficiently been able to solve some existing issues that other methods could not manage to solve. because of the multiple criteria decision-making problem and because some criteria have a conflict problem. The methodology of this research was divided into two main stages. The first stage related to identifying the decision matrix used eight different ML methods on chest X-ray (CXR) images and extracted a new decision matrix so as to assess the ML methods. The second stage related to FDOSM was utilized to solve the multiple criteria decision-making problems. The results of this research are as follows: (1) The individual benchmarking results of three decision makers are nearly identical; however, among all the used ML methods, neural networks (NN) achieved the best results. (2) The results of the benchmarking group are comparable, and the neural network machine learning method is the best among the used methods. (3) The final rank is more logical and closest to the decision-makers' opinion. (4) Significant differences among groups' scores are shown by our validation results, which indicate the authenticity of our results. Finally, this research presents many benefits, especially for hospitals and medical clinics, with a view to speeding up the diagnosis of patients suffering from COVID-19 using the best machine learning method.

Mobile edge computing was conceived to address the increasing computing demand generated by users at the communication network edge. It is expected to play a significant role in next-generation (5G, 6G, and beyond) communication systems as new applications such as augmented/extended reality, teleoperations, telemedicine, and gaming become prolific. As the networks become denser, more and more edge servers are expected to be deployed, and the question of task offloading becomes more complicated. In this study, we present a framework for task offloading in the presence of multiple edge servers that employ round-robin task scheduling. Most studies in the literature attempt to optimize the offloading process under the assumption that each user generates just a single task, or they generate one task every time slot in a discrete-time system where all the tasks are handled within a slot. Furthermore, first-come-first-served queueing models are typically used in studies where queueing is considered at all. The work presented is novel in that we assume continuous and stochastic task arrivals generated by multiple users and round-robin task scheduling at the edge servers. This setting is considerably more realistic with respect to the existing works, and we demonstrate through extensive simulations that round-robin task scheduling significantly reduces task delay. We also present a comparison of a number of server selection mechanisms.