Search

In the rapidly developing field of wireless communication, the control of beams in Reconfigurable Intelligent Surfaces (RISs) has emerged as a promising element beyond 5G wireless communication systems. Due to their distinctive reflecting elements, Reconfigurable Intelligent Surface (RIS) is essential in several operations, including beamforming and beam steering. However, the optimization of these functions necessitates complex solutions. In this study, the authors introduce the Feedback DNN strategy, which combines the Feedback Neural Network and Deep Neural Network techniques specifically designed for channel estimation. This methodology utilizes deep neural networks to provide the RIS and user equipment communication path, enabling improved beamforming and steering capabilities. This study highlights the incorporation of machine learning (ML) within the field of communication engineering, intending to enhance the reliability and effectiveness of wireless communication systems. The contributions encompass a novel methodology for managing RIS beams, sophisticated approaches for channel estimates, optimization of beam operations, and the potential to enhance the performance of wireless systems by utilizing RISs via a Feedback DNN (called DeepRISBeam). The proposed approach is compared against other state-of-the-art ML approaches regarding their training accuracy. At the same time, it evaluated Bit Error Rate performance in high- and low-mobility vehicular communication scenarios.

Due to their minimal environmental impact, green energy sources like wind turbines and solar panels are increasingly utilized in power systems. However, the power they generate is highly variable, leading to unpredictable fluctuations in power supply. Additionally, advanced smart functions in consumer devices and their unpredictable usage patterns contribute to similar fluctuations in power consumption. These fluctuations present a significant challenge to the stability and quality of the power grid, creating a complex issue of power imbalance that becomes harder to manage. Innovative management and control approaches are necessary to address these challenges and thus support the shift to sustainable energy sources. Artificial intelligence (AI) techniques are increasingly proposed as promising solutions, albeit mostly implemented as isolated solutions within centralized power control systems. To effectively manage the complex and often large scale power systems, this paper advocates the use of a Distributed AI (DAI) framework as imperative in enhancing their agility and stability. An illustrative Nano-Grid example (including the potential use of battery sources in extreme scenarios) is adopted to demonstrate the framework’s utility, and a number of power control strategies to safeguard the power system against the variability of both power generators and loads are theoretically formulated and then realized within the proposed framework. Linear Programming, Ant Colony Optimization, Genetic Algorithms, and Particle Swarm Optimization techniques are experimented with, and through simulations, the utility of the DAI framework is demonstrated. The findings underscore the effectiveness and potential benefits of the proposed framework in ensuring the safe and effective operation of power systems with the use of particle swarm optimization amid fluctuating energy scenarios with a small to large number of devices in the nano-grid.

Pneumonia, a severe respiratory infection characterized by a significant morbidity and fatality rate, afflicts many individuals globally. The demand for highly effective antiviral medications has experienced a surge because of the emergence of novel pneumonia viruses, such as the COVID-19 coronavirus. Due to their inherent time and cost constraints, conventional drug development strategies sometimes need to be more manageable. Exploring alternative approaches is crucial to identifying and establishing effective therapy choices. This work introduces a computational methodology for analyzing the chemical space of medications targeting the pneumonia virus, employing Python-based data mining tools. Using computer-aided analysis in drug molecules aims to enhance the efficiency of identifying and evaluating potential new therapeutic candidates using Machine Learning (ML). The research successfully discovered two therapeutic compounds by utilizing the Bayesian Ridge approach, which is the most accurate with the least mean squared error, is less computationally expensive in terms of power, memory, and CPU, and is the fastest of the investigated approaches. It discovered the CHEMBL433378 and CHEMBL93653, with promising docking scores of −4.3 and −4.2, respectively. Additionally, both molecules demonstrated significant inhibitory activity against their respective targets, as seen by their IC50 values of 0.0018 and 0.001. Both compounds meet the criteria for the B. Mann Whitney U Test and Lipinski test.

Next-generation mobile networks, such as Fifth-Generation (5G), and Sixth-Generation (6G) are envisioned to undergo an unprecedented transformation from connected things to connected intelligence with more stringent characteristics, i.e., low end-to-end latency, high bandwidth, reliable connectivity, etc. Such networks will significantly increase network traffic in the distribution networks, causing the need for real-time automated decision-making, such as automated network resource allocation. The network resources be allocated dynamically based on the Quality of Service (QoS) requirements. However, the primary concern is that the distribution networks may get congested soon after allocating network resources. Thus, a QoS-aware prediction framework can be used proactively to predict the future trend of network traffic in each QoS class. In this paper, we propose a framework for predicting the heterogeneous multivariate QoS-aware network traffic to make the best use of network resources dynamically. Specifically, we use a Recurrent Neural Network (RNN) to integrate a Bidirectional Long Short-Term Memory (BLSTM) neural network. The results show that the fusion of RNN-BLSTM can predict the QoS-aware network traffic for over 13 hours with an average accuracy of 97.68%. Moreover, the proposed model is trained and tested over limited data, collected and identified through Deep Packet Inspection (DPI) over an operational network. In addition, we compared the RNN-BLSTM with other prediction algorithms (i.e., LSTM, ARIMA, SVM) in terms of precision, execution time, and energy consumption. Lastly, the proposed framework is used to assign the network resources to each QoS class based on the QoS requirements of that class and its pre-defined priority.

Intrusion Detection Systems (IDSs) have played a crucial role in identifying cyber threats for a very long time. Still, their significance has increased significantly with the advent of 5G/6G technologies, particularly Device-to-Device (D2D) communication. Multiple cyberattacks, such as Man in the Middle (MITM) attacks, Structured Query Language (SQL) injection attacks, Dictionary attacks, Distributed Denial of Service (DDoS) attacks, and others by using specific attack tools such as HULK, RUDY, and GoldenEye, that can cause rapid battery drain, rendering D2D network devices more prone to hardware failure or even to the dissolution of the D2D communication network affecting the operation and the performance of the mobile network. Using a Deep Hierarchical Machine Learning Model/Deep Hierarchical Neural Network (DHMLM/DHNN) technique, we develop an Intrusion Detection System (IDS) for D2D communication that, due to its hierarchical structure, is distinct from other comparable approaches. (i.e., Recurrent Neural Networks (RNN), Deep Neural Networks (DNN), Long short-term memory (LSTM)), has several advantages, including i) reduced training time (training time can be reduced by 56%.); ii) the ability to identify multiple types of attacks; iii) the ability to identify Zero-day/Unknown attacks (i.e., attacks that it has not seen before); iv) a more straightforward model design due to the low number of connections and neurons compared to other approaches (excluding RNN and LSTM), and; v) overall outstanding performance in terms of accuracy (i.e., 99.07%). The custom/unified data set used to train and evaluate the model was partially manually emulated and partially sampled from a large set (>95%) from the commonly used CIC-DDoS-2019 data set. The after-comparison final proposed model’s 99.07% accuracy on this unified data set demonstrates the efficacy of our method. The model was also tested and demonstrated an astounding 99.63% accuracy for zero-day/unknown attacks.

This paper focuses on D2D communication for 5G/6G in dynamic environments where the D2D network topology changes through time due to D2D Devices’ mobility. Specifically, we consider a scenario within the coverage area of a Base Station (BS) serving a number of User Devices (UEs), with variations in speed and direction causing changes in the D2D network topology, either via direct connections or via D2D single-hop or D2D Multi-hop paths. Based on this scenario, we formulate a problem aiming to maximise the total Spectral Efficiency (SE) whilst minimising the total Power Consumption (PC), by selecting the best transmission mode that the D2D devices will operate. In order to address the aforementioned problem, the Distributed Artificial Intelligence Solution (DAIS) plan proposed in our earlier work and designed for static environments is extended to consider the mobility (i.e., speed, direction and indirectly link distance change) of the D2D Device, targeting the dynamic creation of stable and efficient clusters and good backhauling links towards the gateway. The enhanced DAIS performance is comparatively evaluated in terms of SE and PC against selected variations in UE speed and direction, changes in the link Transmission Power (TP), and an increase in the number of Devices in the D2D network. Overall, the results obtained demonstrated superior performance of enhanced DAIS over all the other related investigated approaches (i.e., Distributed Sum Rate (DSR), Single Hop Relay Approach (SHRA), Distributed Random (DR)), in terms of Spectral Efficiency (SE) and Power Consumption (PC). Also, the ability of enhanced DAIS to react and adapt quickly and efficiently to D2D network topology changes, with reduced signalling overhead and control delay in responding to changes, shows that it is a well-poised approach to be used in a Dynamic D2D Environment.

The operation of the Internet of Things (IoT) networks and Wireless Sensor Networks (WSN) is often disrupted by a number of problems, such as path disconnections, network segmentation, node faults, and security attacks. A method that gains momentum in resolving some of those issues is the use of mobile nodes or nodes deployed by mobile robots. The use of mobile elements essentially increases the resources and the capacity of the network. In this work, we present a Node Placement Algorithm with two variations, which utilizes mobile nodes for the creation of alternative paths from source to sink. The first variation employs mobile nodes that create locally-significant alternative paths leading to the sink. The second variation employs mobile nodes that create completely individual (disjoint) paths to the sink. We then extend the local variation of the algorithm by also accounting for the energy levels of the nodes as a contributing factor regarding the creation of alternative paths. We offer both a high-level description of the concept and also detailed algorithmic solutions. The evaluation of the solutions was performed in a case study of resolving congestion in the network. Results have shown that the proposed algorithms can significantly contribute to the alleviation of the problem of congestion in IoT and WSNs and can easily be used for other types of network problems.

The Internet of Things (IoT) provides the ability to extend the Internet into devices and everyday objects, in a way that they are uniquely addressable. Sensors, actuators, as well as everyday devices and objects, such as cellphones, cars, and homes, are interconnected and form a network that can be accessed, monitored, and controlled remotely. Security is an important subject in the IoT networks since the devices and the networks can be used as a means of invading the users' privacy. The current work examines the issue of security agent location using indicative intrusion detection techniques for network layer attacks. We analyze the methodology, operation, as well as the complexity of each technique. Through the extensive implementation and experimentation, we are able to conclude that the local security agents have the same performance results with centralized and decentralized approaches, but with negligible overhead. As such, they are useful when internal network communication, or network augmentation with monitoring nodes, is not feasible.

The remarkable evolution of the IoT raised the need for an efficient way to update the device’s firmware. Recently, a new process was released summarizing the steps for firmware updates over the air (FUOTA) on top of the LoRaWAN protocol. The FUOTA process needs to be completed quickly to reduce the systems’ interruption and, at the same time, to update the maximum number of devices with the lowest power consumption. However, as the literature showed, a single gateway cannot optimize the FUOTA procedure and offer the above mentioned goals since various trade-offs arise. In this paper, we conducted extensive experiments via simulation to investigate the impact of multiple gateways during the firmware update process. To achieve that, we extended the FUOTAsim simulation tool to support multiple gateways. The results revealed that several gateways could eliminate the trade-offs that appeared using a single gateway.

Machine learning (ML) techniques learn a system by observing it. Events and occurrences in the network define what is expected of the network’s operation. It is for this reason that ML techniques are used in the computer network security field to detect unauthorized intervention. In the event of suspicious activity, the result of the ML analysis deviates from the definition of expected normal network activity and the suspicious activity becomes apparent. Support vector machines (SVM) are ML techniques that have been used to profile normal network activity and classify it as normal or abnormal. They are trained to configure an optimal hyperplane that classifies unknown input vectors’ values based on their positioning on the plane. We propose to use SVM models to detect malicious behavior within low-power, low-rate and short range networks, such as those used in the Internet of Things (IoT). We evaluated two SVM approaches, the C-SVM and the OC-SVM, where the former requires two classes of vector values (one for the normal and one for the abnormal activity) and the latter observes only normal behavior activity. Both approaches were used as part of an intrusion detection system (IDS) that monitors and detects abnormal activity within the smart node device. Actual network traffic with specific network-layer attacks implemented by us was used to create and evaluate the SVM detection models. It is shown that the C-SVM achieves up to 100% classification accuracy when evaluated with unknown data taken from the same network topology it was trained with and 81% accuracy when operating in an unknown topology. The OC-SVM that is created using benign activity achieves at most 58% accuracy.