In cognitive radio networks (CRNs), secondary users (SUs) transmission requests are fulfilled via the use of portions of the licensed bandwidth dedicated to primary users (PUs). Meanwhile, through spectrum sharing of dynamic spectrum access (DSA), the PUs gain either financial benefits or cooperative communications. Due to the fact that the spectrum bandwidth resources are restricted hence; the dynamic allocation requests have become the focus of attention in recent years. Therefore, the dynamic channel reservation (DCR) in CRNs has a significant influence on improving network performance via the adjustment of the optimal number of reserved channels. Also, the centralized control (central controller) with a software-defined network (SDN) can be employed effectively to manage configuration, simplify the complexities, and develop dynamic coordination between the users in the network. In this paper, two algorithms of DCR are investigated to determine the optimal number of reserved channels based on SU retainability or SU channel availability while taking into consideration PU's channel availability minimum limit in both cases. Performance metrics in both cases indicate the enhancement in system quality of service (QoS). Moreover, the results show a significant reduction in SU cost function and network unserviceable probability (), while meeting the QoS requirements of PU through a minor inconsiderable impact on its channel availability and throughput compared to other previous models. In this paper, a proposed DCR algorithm is designed for selecting one of the two modes of operation depending on the incoming traffic requests to attain better performance characteristics. INDEX TERMS Cognitive radio networks, Dynamic channel reservation, Software defined network, Retainability, SU cost function.

No abstract

No abstract

COVID-19 has been considered as a global pandemic. Recently, researchers are using deep learning networks for medical diseases’ diagnosis. Some of these researches focuses on optimizing deep learning neural networks for enhancing the network accuracy. Optimizing the Convolutional Neural Network includes testing various networks which are obtained through manually configuring their hyperparameters, then the configuration with the highest accuracy is implemented. Each time a different database is used, a different combination of the hyperparameters is required. This paper introduces two COVID-19 diagnosing systems using both Residual Network and Xception Network optimized by random search in the purpose of finding optimal models that give better diagnosis rates for COVID-19. The proposed systems showed that hyperparameters tuning for the ResNet and the Xception Net using random search optimization give more accurate results than other techniques with accuracies 99.27536% and 100 % respectively. We can conclude that hyperparameters tuning using random search optimization for either the tuned Residual Network or the tuned Xception Network gives better accuracies than other techniques diagnosing COVID-19.

No abstract