No abstract

Networks are exposed to an increasing number of cyberattacks due to their vulnerabilities. So, cybersecurity strives to make networks as safe as possible, by introducing defense systems to detect any suspicious activities. However, firewalls and classical intrusion detection systems (IDSs) suffer from continuous updating of their defined databases to detect threats. The new directions of the IDSs aim to leverage the machine learning models to design more robust systems with higher detection rates and lower false alarm rates. This research presents a novel network IDS, which plays an important role in network security and faces the current cyberattacks on networks using the UNSW-NB15 dataset benchmark. Our proposed system is a dynamically scalable multiclass machine learning-based network IDS. It consists of several stages based on supervised machine learning. It starts with the Synthetic Minority Oversampling Technique (SMOTE) method to solve the imbalanced classes problem in the dataset and then selects the important features for each class existing in the dataset by the Gini Impurity criterion using the Extremely Randomized Trees Classifier (Extra Trees Classifier). After that, a pretrained extreme learning machine (ELM) model is responsible for detecting the attacks separately, “One-Versus-All” as a binary classifier for each of them. Finally, the ELM classifier outputs become the inputs to a fully connected layer in order to learn from all their combinations, followed by a logistic regression layer to make soft decisions for all classes. Results show that our proposed system performs better than related works in terms of accuracy, false alarm rate, Receiver Operating Characteristic (ROC), and Precision-Recall Curves (PRCs).

Shadowed Rician model is considered to be the most appropriate that is used to characterize the impairments seen in wireless channels, which suffer Line-Of-Sight (LOS) shadowing and small-scale fading. In this model, the Probability Density Function (PDF) of the Signal to Noise Ratio (SNR) per symbol needs numerical solutions to be evaluated. More than that, for some values of the fading parameters, the numerical solution converging too slowly, and so needs too much time to be evaluated. This is considered as a problem in real time applications where delay is a critical issue. In this paper, the authors present and prove approximations for Shadowed Rician model according to the values of the fading parameters, which are the Rice factor and the Shadowing standard deviation. With the proposed approximation, the required PDF could be written in intervals which make it easier to calculate at parameters values that causes slow converging.

In this paper, we reformulate the gridless direction of arrival (DoA) estimation problem in a novel reweighted covariance fitting (CF) method. The proposed method promotes joint sparsity among different snapshots by means of nonconvex Schatten-p quasi-norm penalty. Furthermore, for more tractable and scalable optimization problem, we apply the unified surrogate for Schatten-p quasi-norm with two-factor matrix norms. Then, a locally convergent iterative reweighted minimization method is derived and solved efficiently via a semidefinite program using the optimization toolbox. Finally, numerical simulations are carried out in the background of unknown nonuniform noise and under the consideration of coprime array (CPA) structure. The results illustrate the superiority of the proposed method in terms of resolution, robustness against nonuniform noise, and correlations of sources, in addition to its applicability in a limited number of snapshots.

Expanding network capacity and guaranteeing the Quality of Service (QoS) are significant goals in fifth-Generation (5G) for high densities of mobile terminals. Femtocell-based 5G is an essential radio access technology that meets the exponentially increasing demand. Femtocells have emerged as an efficient solution for improving the capacity and coverage of wireless cellular networks, especially, for indoor wireless users. However because of the limited wireless radio resources, resource allocation is a key issue in femtocell networks. Motivated by this challenge in this study, we propose an efficient resource allocation approach that satisfies the QoS requirements for High-Priority (HP) users while serving Best-Effort (BE) users effectively as possible. The user differentiation strategy ensures the QoS guarantee uponthe priority level of each user. We consider major metrics for performance evaluation which are: the rate of rejected users, throughput satisfaction rate, spectrum spatial reuse and fairness. Dedicated simulations prove that our proposal outperforms one of the most effective techniques in the literature.