Differentialy-Private Stochastic Gradient Descent (DP-SGD) is the benchmark for protecting sensitive data while training deep neural networks. However, it relies on fixed or heuristic schedules for key parameters such as noise multiplier and clipping threshold, often leading to suboptimal privacy-utility trade-offs. We propose a novel, curvature-aware training framework that dynamically adapts DP-SGD parameters based on the geometry of the loss surface. Leveraging public data, we estimate the local curvature via dominant Hessian eigenvalues and use this signal to compute an expected excess risk (EER) metric. This EER guides real-time adjustments of the DP-SGD mechanism. Our method operates in highly non-convex settings, beyond the limitations of prior EER-based strategies that assume convexity or PL conditions. Experimental results on MNIST, CIFAR-10, and SVHN demonstrate that our approach consistently improves model accuracy and convergence speed under tight privacy constraints, existing baselines.

In the Metaverse, real-time digital twin (DT) updates enable immersive, interactive environments by reflecting real world states. Metaverse can engage its users to share data in order to ensure the completeness of the DT. However, the limitations and heterogeneity in IoT devices' computation and transmission resources are critical challenges to synchronizing the vast volume of real-world objects with their digital replicas. In this work, we propose a novel adaptive Vision Transformer (ViT)- based semantic communication (SemCom) system to extract semantic information from raw data collected by IoT devices. The system dynamically adjusts the model size and computational complexity according to the resource constraints of individual IoT devices, enables broader participation of heterogeneous devices, enhances feature extraction capabilities, and ensures completeness and efficient DT representation. We formulate our problem as an utility-maximization optimization to manage ViT complexity under resource constraints, allowing the Metaverse Services Provider (MSP) to select high-performing IoT devices. To guide the optimization, we profile ViT models with varying architectural complexities and conduct an empirical analysis to capture the relationship between model scale and performance. To address the scalability and privacy limitations of the optimization, we propose a decentralized solution where each IoT device independently optimizes its own utility under local constraints. The MSP, in turn, selects among these devices to ensure quality and maximize its overall utility. We show that our distributed solution achieves near-optimal performance and significantly outperforms other approaches in terms of MSP utility, semantic data quality, and overall IoT utility. © 2026 IEEE.

An in-vehicle network (IVN) is the internal communication network that connects all sensors and control units in an autonomous vehicle. Sensors and control units use the IVN to send perception-related messages and control commands for the normal and safe operation of the vehicle. However, the IVN, by design, is vulnerable to network attacks due to a lack of adequate security mechanisms. This paper presents a Dynamic Windowing Intrusion Detection System (DWIDS) that adapts its detection window in real-time based on observed anomalies, enabling accurate and responsive attack detection. Unlike prior methods that focus on static configurations or single-attack detection, DWIDS supports multi-label classification and real-time tuning of detection parameters. The system is evaluated using two public benchmark datasets (CHD and IVN-IDS challenge) which feature diverse and imbalanced attack types. Experimental results demonstrate high performance across key metrics (e.g., >98% precision, >97% recall and F1-score), including for rare attacks. The findings confirm DWIDS’s practicality and robustness for deployment in real-world autonomous vehicle environments.

Large Language Models (LLMs) inference-time privacy focuses mainly on protecting sensitive information within the prompt. However, enabling end users to repudiate the submission of exact prompts, to avoid potential legal consequences, remains an unexplored research direction. To address this gap, we propose Repudiation for Good (R4G), a privacy-preserving approach that enables users to deny submitting exact prompts while allowing cloud-based LLM providers to receive sufficient semantic information but preventing them from proving with certainty which specific prompt was submitted. R4G is a paradigm shift in LLM inference-time privacy. Rather than encrypting exact prompts, which eventually reveal their precise content upon decryption, R4G transforms prompts into an intentionally ambiguous semantic representation through LLM embedding. This transformation creates a many-to-one mapping where multiple lexically distinct prompts collapse into a similar embedding space. The key insight is that while traditional privacy approaches aim to hide information temporarily (through encryption) or completely (through anonymization), our approach provides a probabilistic association between the prompt and its embedding, creating a deniability space, where users can legitimately deny submitting exact prompts that might carry legal, social, or professional consequences. We conducted experiments to assess the efficacy of R4G by measuring the semantic similarity between the original and approximated prompts. The results show that R4G achieved an average cosine similarity score of approximately 50%, effectively striking a balance between utility and privacy.

Despite its advantages for privacy-preserving data-driven modeling, federated learning is vulnerable to privacy breaches, as demonstrated by recent attacks on its privacy properties. It has been proven that sharing the weights alone is insufficient to protect the underlying data. In this work, we provide a solution for sharing the aggregated weights with a central server while safeguarding the privacy of individual client weights. Our solution introduces a decentralized committee election mechanism, eliminating the need for a trusted party. The election phase is based on verifiable random functions (VRFs), whereas the aggregation phase is based on Elliptic curve cryptography and multi-party secret-sharing schemes. Our experimental results show that our solution outperforms the proposed solutions in terms of communication and computation costs. Overall, our approach offers a robust solution for privacy-preserving federated learning without compromising its accuracy and without relying on a third party.

Graph neural networks (GNNs) have recently garnered significant attention for use in network intrusion detection systems (NIDS), owing to their ability to model network traffic as graphs and capture complex dependencies between flows. However, existing GNN-based methods face critical limitations: their reliance on labeled data, often scarce or noisy in practice, and their inability to address multi-scale threats, such as localized node anomalies (e.g., port scanning), coordinated subnet-work attacks (e.g., botnets), and global network-wide campaigns (e.g., DDoS attacks). To bridge this gap, we propose Multi-Scale Graph Contrastive Representation Learning (MGCRL), a semi-supervised framework that hierarchically integrates three perspectives to model network intrusions. At the node level, MGCRL constructs semantic subnetworks around individual traffic flows to capture fine-grained behavioral deviations. For subnetwork-level threats, it employs substructure-aware pooling to identify coordinated anomalies, such as clusters of devices exhibiting synchronized malicious activity. Finally, at the global level, MGCRL derives representations that reflect the holistic state of the network, enabling detection of large-scale threats, such as distributed malware propagation. MGCRL couples a shared GNN encoder with a multi-level contrastive loss to align multi-scale representations while largely eliminating label dependence. It learns discriminative features from unlabeled traffic, sharpens decision boundaries with minimal supervision, and exposes anomalies that surface in a hierarchical network context by contrasting related and unrelated nodes at each scale. Extensive experiments on three benchmark datasets for multi-class classification show that MGCRL consistently outperforms SOTA methods, particularly under severe label scarcity and class imbalance.

This paper presents FFS-ORAN-IDS, a federated few-shot intrusion-detection framework that secures streaming traffic in Open Radio Access Networks (O-RAN) while respecting their stringent latency and resource constraints. The framework addresses the twin challenges of scarce attack labels and heterogeneous data, where naïve pseudo-label injection without sufficient confidence propagates errors, large-scale labeling of streaming traffic is impractical, and inherent uncertainty often requires costly human intervention. FFS-ORAN-IDS combines three coordinated x-functional blocks: a confidence-adaptive curriculum that releases pseudo-labels only when local TabTransformers are reliable, a diversity filter that retains the most informative uncertain packets, and a token-budgeted large-language-model (LLM) oracle that verifies the remaining hard samples. A mixed-integer optimization jointly governs curriculum pacing, sampling size, and Oracle LLM calls so that each federated round minimizes detection loss, propagation error, and LLM token cost under per-round resource caps. We train FFS-ORAN-IDS in two stages: an initial few-shot phase that fits the TabTransformer on the scarce ground-truth packets, followed by iterative rounds that refine the model with oracle-verified pseudo-labels. Experimental evaluation on the CIC-IDS 2018 benchmark shows that the proposed framework improves detection accuracy by 6%, reduces label-error propagation by 20%, and lowers energy consumption by 40% in the most label-constrained scenarios.

Unmanned aerial vehicles (UAVs) are proven useful for enabling wireless power transfer (WPT), resource offloading, and data collection from ground IoT devices in post-disaster scenarios where conventional communication infrastructure is compromised. As 6G networks emerge, offering ultra-reliable low-latency communication and enhanced energy efficiency, UAVs are poised to play a critical role in extending 6G features to challenging environments. The key challenges in this context include limited UAV flight duration, energy constraints, limited resources, and the reliability of data collection, all of which impact the effectiveness of UAV operations. Motivated by the need for efficient resource allocation and reliable data collection, we propose a solution using UAV swarms combined with reconfigurable intelligent surfaces (RIS) to optimize energy harvesting for IoT devices and enhance communication quality. We formulate the problem of resource optimization, UAVs-RIS trajectory planning, and RIS configuration as a mixed integer nonlinear programming optimization problem and solve it in a dynamic condition by transforming it into a Markov decision process and utilizing a deep reinforcement learning (DRL) approach based on proximal policy optimization (PPO) algorithm to solve it. Simulation results demonstrate that our framework outperforms traditional approaches, including the Actor-Critic (AC) algorithm and a greedy solution, achieving superior performance in energy harvesting efficiency, data collection, and communication reliability.

Deploying transformer models in Personalized Federated Learning (PFL) over wireless networks is challenging due to their large size, which leads to high communication overhead, increased latency, and excessive energy consumption. Traditional pruning and sparsification methods, designed mainly for conventional deep learning architectures, are ineffective for transformers and can cause divergence or degrade performance—especially when applied to self-attention layers or through direct federated averaging. To address these challenges, we propose a novel dual approach called PFL-TPS (PFL with Transformer Pruning and Sparsification). Our approach efficiently reduces communication and computation costs while maintaining model performance, making it suitable for resource-constrained wireless networks. Specifically, we apply adaptive pruning with trainable thresholds to the transformer's Feed-Forward Layers (FFLs), and only these trainable thresholds are shared with the server, resulting in minimal uploaded data. For the Self-Attention Layers (SALs), instead of transmitting bandwidth-intensive model parameters, we employ a server-side hypernetwork that generates personalized parameters based on device-specific embedding vectors sent by the devices, significantly reducing communication overhead and maintaining personalization. Extensive experiments show that PFL-TPS reduces energy consumption by up to 50%, decreases training time by 60.44%, and improves model accuracy by 49.87% compared to baselines in wireless networks.

The advent of$\mathbf{6 G}$Internet of Things (IoT) networks demands ultra-reliable, energy-efficient communications to support the massive integration of connected devices. Non-orthogonal multiple access (NOMA) has emerged as a key technology to improve spectral efficiency (SE) by allowing multiple IoT devices (IDs) to share the same frequency resource block through power-domain multiplexing. However, as the number of IDs increases, NOMA faces significant interference challenges, which limit its scalability and degrade system performance. To address these limitations, we propose a clustered NOMA (C-NOMA) framework, which organizes IDs into clusters and applies NOMA within each cluster, reducing interference and improving the effectiveness of successive interference cancellation (SIC). Additionally, we integrate hybrid beamforming (HBF) with C-NOMA, where unmanned aerial vehicles (UAVs) serve as mobile base stations using 2D uniform planar array (UPA) antennas for beam steering. This enables multiple IDs to be served within each cluster with fewer RF chains, further enhancing SE through spatial multiplexing and beam steering. In order to solve the energy efficiency (EE) maximization problem, we reformulate the optimization problem of HBF and power allocation (PA) as a Markov decision process (MDP) and solve it using multi-agent reinforcement learning (MARL). Simulation results show that our proposed Full-RL algorithm achieves up to 37.7 % higher EE compared to the baseline RL-based PA method. This baseline only uses RL for PA and relies on the averaged phase for analog beamforming without further optimization.

Spatiotemporal graph neural networks (STGNNs) have proven especially effective in traffic prediction tasks by modeling sensors or regions as nodes, with distances and correlations as edges. Their ability to capture complex spatiotemporal dependencies in road networks drives key applications in public safety, urban planning, and intelligent transportation. However, existing STGNNs often rely on manually designed architectures and typically process multiview graphs separately, requiring specialized expertise, thus limiting flexibility and overlooking intricate spatiotemporal interdependencies. To address these challenges, we propose an Attention-based Dynamic Multiview Spatiotemporal Graph Neural Architecture Search (ADMGNAS) framework, comprising three interconnected components. First, we introduce a unified Attention-based Dynamic Multiview Spatiotemporal Graph (ADMSTG) architecture that integrates spatiotemporal and view-aware attention mechanisms, enabling the effective capture of complex cross-view relationships. Building upon this architecture, we then develop a dedicated Multiview Attention Spatiotemporal (MVAS) search space, which systematically automates the selection of optimal attention operations. Then, a specialized differentiable search algorithm efficiently explores the MVAS space to dynamically identify architecture variations specifically tailored to dynamic multiview spatiotemporal graphs. Extensive experiments on benchmark datasets show that ADMGNAS consistently outperforms SOTA methods, proving its effectiveness and adaptability.

Deploying large language models (LLMs) at the wireless edge is a promising solution to meet the low-latency, high-computation demands of next-generation AI applications. Although the existing literature has introduced approaches to enable distributed LLM inference, these methods largely overlook the distinct computational and communication characteristics of the two-phase LLM inference process—the pre-fill and decode phases. This oversight leads to suboptimal performance and limits scalability in real-world deployments. To address these issues, we propose a novel collaborative inference framework that strategically minimizes inference latency by optimally distributing computational loads across edge devices, the edge server, and the cloud. Our approach introduces a hybrid framework that combines head-wise parallel processing with layer-wise partitioning of LLM models, supported by a dual-phase optimization strategy. In the pre-fill phase, we optimize assigning attention heads to selected edge devices for parallel computation and efficient resource use. We then optimize for minimal latency by selecting participants, determining head assignments per device, and allocating bandwidth while meeting all constraints. In the de-code phase, our framework adaptively decides whether to execute computations locally on the edge server, offload them to the cloud, or redistribute tasks among edge devices, optimizing this decision based on the remaining latency budget and the sequential nature of the decode phase. The simulation results demonstrate that the proposed framework significantly outperforms the baseline methods, achieving a 56% reduction in inference latency, 40% improvement in bandwidth efficiency and 35% improvement in resource utilization.

Smart electric vehicle charging stations (EVCSs) are crucial in advancing sustainable transportation by scheduling charging based on user preferences and grid constraints. However, their reliance on digital communication makes them vulnerable to attacks that can shift the EV aggregator’s load profile to different times, leading to substantial financial losses. They can also alter charging times in ways that degrade battery health and overburden the grid. Although the existing literature has explored various strategies to mitigate these risks, most prior work has focused on simple, handcrafted charge manipulation attacks (CMAs). This makes them often fall short when confronted with artificially intelligent methods to remain undetected. To address these limitations, we propose a novel framework that both generates and defends against highly evasive CMAs. First, we utilize deep reinforcement learning (DRL) to craft advanced, stealthy attacks capable of bypassing intrusion detection systems (IDS). Second, we introduce an IDS built on LSTM variational autoencoders, which captures the nuanced temporal dependencies of smart CMAs, as well as intricate patterns. This enables our IDS to significantly enhance the detection and mitigation of complex threats. We conduct extensive simulations using real-world datasets, which reveal critical security gaps in existing benchmark approaches while highlighting the strong performance of our proposed framework. Notably, our IDS achieves detection accuracies of 0.97, 0.96, and 0.96 across different scenarios, even against highly evasive CMAs.

Existing literature confirms the ability of machine learning to identify fraudulent smart grid power consumers who report false consumption readings to pay less electricity bills. Additionally, federated learning (FL) shows promise as a way to train the detection model without requiring data sharing, thereby safeguarding consumer privacy. However, malicious participants (i.e., clients) in FL training can launch adversarial attacks by training their local models with specially crafted low-consumption data to inject a Trojan into the global model. This Trojan can then be activated during the evaluation phase to evade the detection of false data. To the best of our knowledge, not enough research has been done on this topic in the context of unsupervised learning. The absence of labels in unsupervised learning exacerbates the effectiveness of Trojan attacks and renders it more challenging to design robust defense mechanisms. In this article, we first investigate the vulnerability of one-class classifiers to Trojan attacks. Then, we propose two defense approaches named layerwise close-to-median (LWCM) and Machine Unlearning to counter this attack. In LWCM, by choosing a FL client whose last layer model parameters are near to the median of all clients’ last layer parameters to update the global model, we can identify and exclude malicious updates. The idea is that the last layer parameters of honest clients should be similar, whereas those from malicious clients are different. With the majority of clients being honest, the median values are closer to the parameters of these clients, facilitating the detection of malicious clients. In Machine Unlearning, we utilize gradient ascent-based techniques to adapt models by selectively removing attacker-related data points. This is possible because honest clients generate data resembling that of malicious clients and employ a dual-component loss function to maintain model proficiency in recognizing benign power consumption patterns while eliminating malicious patterns. To show the seriousness of Trojan attacks and the effectiveness of our countermeasures, many experiments have been carried out.

Clustered Federated Multi-task Learning (CFL) has emerged as a promising technique to address statistical challenges, particularly with non-independent and identically distributed (non-IID) data across users. However, existing CFL studies entirely rely on the impractical assumption that devices possess access to accurate ground-truth labels. This assumption becomes specifically problematic in hierarchical wireless networks (HWNs), with vast unlabeled data and dual-level model aggregation, not only leading to slowing down convergence speeds and extending processing times but also resulting in increased resource consumption. To this end, we propose Clustered Federated Semi-Supervised Learning (CFSL), a novel framework tailored for more realistic scenarios in HWNs. We leverage specialized models resulting from device clustering and present two prediction model schemes, the best-performing specialized model and the weighted-averaging ensemble model, to correctly label unlabeled, unseen data. For the best-performing specialized model scheme, a specialized model excelling in label prediction for a specific device is assigned to correctly label the unlabeled data, even when the data originates from other environments, while the weighted-averaging ensemble model combines all specialized models into a unified model, capturing more details from broader data distributions across edge networks. The CFSL also introduces two novel prediction time schemes, split-based and stopping-based, for accurately timing the labeling process, alongside two strategic device selection schemes, greedy and round-robin, upon reaching each cluster’s stopping point. Extensive testing validates CFSL’s superiority over existing models in labeling and testing accuracies and resource efficiency, achieving up to 51% energy savings.

Autonomous Vehicles (AVs) represent a transformative advancement in the transportation industry. These vehicles have sophisticated sensors, advanced algorithms, and powerful computing systems that allow them to navigate and operate without direct human intervention. However, AVs’ systems still get overwhelmed when they encounter a complex dynamic change in the environment resulting from an accident or a roadblock for maintenance. The advanced features of Sixth Generation (6G) technology are set to offer strong support to AVs, enabling real-time data exchange and management of complex driving maneuvers. This paper proposes a Multi-Agent Reinforcement Learning (MARL) framework to improve AVs’ decision-making in dynamic and complex Intelligent Transportation Systems (ITS) utilizing 6G-V2X communication. The primary objective is to enable AVs to avoid roadblocks efficiently by changing lanes while maintaining optimal traffic flow and maximizing the mean harmonic speed. To ensure realistic operations, key constraints such as minimum vehicle speed, roadblock count, and lane change frequency are integrated. We train and test the proposed MARL model with two traffic simulation scenarios using the SUMO and TraCI interface. Through extensive simulations, we demonstrate that the proposed model adapts to various traffic conditions and achieves efficient and robust traffic flow management. Specifically, the proposed approach results in a harmonic mean speed increase of up to 15% and a reduction in lane-change frequency by 10%. The trained model effectively navigates dynamic roadblocks, promoting improved traffic efficiency in AV operations with more than 70% efficiency over other benchmark solutions.

Semantic Communication (SemCom) systems, em-powered by deep learning (DL), represent a paradigm shift in data transmission. These systems prioritize the significance of content over sheer data volume. However, existing SemCom designs face challenges when applied to diverse computational capabilities and network conditions, particularly in time-sensitive applications. A key challenge is the assumption that diverse devices can uniformly benefit from a standard, large DL model in SemCom systems. This assumption becomes increasingly impractical, especially in high-speed, high-reliability applications such as industrial automation or critical healthcare. Therefore, this paper introduces a novel SemCom framework tailored for heterogeneous, resource constrained edge devices and computation-intensive servers. Our approach employs dynamic knowledge distillation (KD) to customize semantic models for each device, balancing computational and communication constraints while ensuring Quality of Service (QoS). We formulate an optimization problem and develop an adaptive algorithm that iteratively refines semantic knowledge in edge devices, resulting in better models tailored to their resource profiles. This algorithm strategically adjusts the granularity of distilled knowledge, enabling devices to maintain high semantic accuracy for precise inference tasks, even under unstable network conditions. Extensive simulations demonstrate that our approach significantly reduces model complexity for edge devices, leading to better semantic extraction and achieving the desired QoS.

Today, wireless networks are becoming responsible for serving intelligent applications, such as extended reality and metaverse, holographic telepresence, autonomous transportation, and collaborative robots. Although current fifth-generation (5G) networks can provide high data rates in terms of Giga-bytes/second, they cannot cope with the high demands of the aforementioned applications, especially in terms of the size of the high-quality live videos and images that need to be communicated in real-time. Therefore, with the help of artificial intelligence (AI)-based future sixth-generation (6G) networks, the semantic communication concept can provide the services demanded by these applications. Unlike Shannon's classical information theory, semantic communication urges the use of the semantics (meaningful contents) of the data in designing more efficient data communication schemes. Hence, in this paper, we model semantic communication as an energy minimization framework in heterogeneous wireless networks with respect to delay and quality-of-service constraints. Then, we propose a sub-optimal solution to the NP-hard combinatorial mixed-integer nonlinear programming problem (MINLP) by utilizing efficient techniques such as discrete optimization variables' relaxation. In addition, AI-based autoencoder and classifier are trained and deployed to perform semantic extraction, reconstruction, and classification services. Finally, we compare our proposed sub-optimal solution with different state-of-the-art methods, and the obtained results demonstrate its superiority.

Digital Twin-Edge Network (DTEN) architecture is emerging as a critical component in the landscape of 6G networks, offering the promise of real-time data processing, system simulation, and edge-cloud computing. The integration of unmanned aerial vehicles (UAVs) and high-altitude platform systems (HAPS) within these architectures further adds to the complexity and capabilities, particularly in time-sensitive scenarios. The study of delay-sensitive queue-aware task offloading of real-time applications in such intricate dynamic energy-constrained networks remains nascent. This paper aims to bridge this gap by exploring optimizing IoT device association, offloading decisions, and resource allocation to maximize energy efficiency (EE) in an Air-to-Ground DTEN (A2G-DTEN). Our primary objective is to maximize the EE of the network while adhering to constraints related to queuing delays, maximum permissible task latency, and computing capabilities of edge servers. We proposed a comprehensive problem formulation and offered solutions leveraging a deep deterministic policy gradient (DDPG) based algorithm with two other baselines. The numerical results show that our proposed DDPG-based algorithm achieves high EE despite the strict task delay constraints.

The increasing popularity of electric vehicles (EVs) necessitates robust defenses against sophisticated cyber threats. A significant challenge arises when EVs intentionally provide false information to gain higher charging priority, potentially causing grid instability. While various approaches have been proposed in existing literature to address this issue, they often overlook the possibility of attackers using advanced techniques like deep reinforcement learning (DRL) or other complex deep learning methods to achieve such attacks. In response to this, this paper introduces a hierarchical adversarial framework using DRL (HADRL), which effectively detects stealthy cyberattacks on EV charging stations, especially those leading to denial of charging. Our approach includes a dual approach, where the first scheme leverages DRL to develop advanced and stealthy attack methods that can bypass basic intrusion detection systems (IDS). Second, we implement a DRL-based scheme within the IDS at EV charging stations, aiming to detect and counter these sophisticated attacks. This scheme is trained with datasets created from the first scheme, resulting in a robust and efficient IDS. We evaluated the effectiveness of our framework against the recent literature approaches, and the results show that our IDS can accurately detect deceptive EVs with a low false alarm rate, even when confronted with attacks not represented in the training dataset.

Clustered Federated Multi-task Learning (CFL) has gained considerable attention as an effective strategy for over-coming statistical challenges, particularly when dealing with non-independent and identically distributed (non-IID) data across multiple users. However, much of the existing research on CFL operates under the unrealistic premise that devices have access to accurate ground-truth labels. This assumption becomes especially problematic in, especially hierarchical wireless networks (HWNs), where edge networks contain a large amount of unlabeled data, resulting in slower convergence rates and increased processing times-particularly when dealing with two layers of model aggregation. To address these issues, we introduce a novel frame-work-Clustered Federated Semi-Supervised Learning (CFSL), designed for more realistic HWN scenarios. Our approach leverages a best-performing specialized model algorithm, wherein each device is assigned a specialized model that is highly adept at generating accurate pseudo-labels for unlabeled data, even when the data stems from diverse environments. We validate the efficacy of CFSL through extensive experiments, comparing it with existing methods highlighted in recent literature. Our numerical results demonstrate that CFSL significantly improves upon key metrics such as testing accuracy, labeling accuracy, and labeling latency under varying proportions of labeled and unlabeled data while also accommodating the non-IID nature of the data and the unique characteristics of wireless edge networks.

As smart grids (SG) increasingly rely on advanced technologies like sensors and communication systems for efficient energy generation, distribution, and consumption, they become enticing targets for sophisticated cyber-attacks. These evolving threats demand robust security measures to maintain the stability and resilience of modern energy systems. While extensive research has been conducted, a comprehensive exploration of proactive cyber defense strategies utilizing Deep Learning (DL) in SG remains scarce in the literature. This survey bridges this gap, studying the latest DL techniques for proactive cyber defense. The survey begins with an overview of related works and our distinct contributions, followed by an examination of SG infrastructure. Next, we classify various cyber defense techniques into reactive and proactive categories. A significant focus is placed on DL-enabled proactive defenses, where we provide a comprehensive taxonomy of DL approaches, highlighting their roles and relevance in the proactive security of SG. Subsequently, we analyze the most significant DL-based methods currently in use. Further, we explore Moving Target Defense, a proactive defense strategy, and its interactions with DL methodologies. We then provide an overview of benchmark datasets used in this domain to substantiate the discourse. This is followed by a critical discussion on their practical implications and broader impact on cybersecurity in Smart Grids. The survey finally lists the challenges associated with deploying DL-based security systems within SG, followed by an outlook on future developments in this key field.

Abstract Food plays an important role in our lives that goes beyond mere sustenance. Food affects behavior, mood, and social life. It has recently become an important focus of multimedia and social media applications. The rapid increase of available image data and the fast evolution of artificial intelligence, paired with a raised awareness of people’s nutritional habits, have recently led to an emerging field attracting significant attention, called food computing, aimed at performing automatic food analysis. Food computing benefits from technologies based on modern machine learning techniques, including deep learning, deep convolutional neural networks, and transfer learning. These technologies are broadly used to address emerging problems and challenges in food-related topics, such as food recognition, classification, detection, estimation of calories and food quality, dietary assessment, food recommendation, etc. However, the specific characteristics of food image data, like visual heterogeneity, make the food classification task particularly challenging. To give an overview of the state of the art in the field, we surveyed the most recent machine learning and deep learning technologies used for food classification with a particular focus on data aspects. We collected and reviewed more than 100 papers related to the usage of machine learning and deep learning for food computing tasks. We analyze their performance on publicly available state-of-art food data sets and their potential for usage in multimedia food-related applications for various needs (communication, leisure, tourism, blogging, reverse engineering, etc.). In this paper, we perform an extensive review and categorization of available data sets: to this end, we developed and released an open web resource in which the most recent existing food data sets are collected and mapped to the corresponding geographical regions. Although artificial intelligence methods can be considered mature enough to be used in basic food classification tasks, our analysis of the state-of-the-art reveals that challenges related to the application of this technology need to be addressed. These challenges include, among others: poor representation of regional gastronomy, incorporation of adaptive learning schemes, and reverse engineering for automatic food creation and replication.

Honeypot technologies provide an effective defense strategy for the Industrial Internet of Things (IIoT), particularly in enhancing the Advanced Metering Infrastructure’s (AMI) security by bolstering the network intrusion detection system. For this security paradigm to be fully realized, it necessitates the active participation of small-scale power suppliers (SPSs) in implementing honeypots and engaging in collaborative data sharing with traditional power retailers (TPRs). To motivate this interaction, TPRs incentivize data sharing with tangible rewards. However, without access to an SPS’s confidential data, it is daunting for TPRs to validate shared data, thereby risking SPSs’ privacy and increasing sharing costs due to voluminous honeypot logs. These challenges can be resolved by utilizing Federated Learning (FL), a distributed machine learning (ML) technique that allows for model training without data relocation. However, the conventional FL algorithm lacks the requisite functionality for both the security defense model and the rewards system of the AMI network. This work presents two solutions: first, an enhanced and cost-efficient FedAvg algorithm incorporating a novel data quality measure, and second, FedPot, the development of an effective security model with a fair incentives mechanism under an FL architecture. Accordingly, SPSs are limited to sharing the ML model they learn after efficiently measuring their local data quality, whereas TPRs can verify the participants’ uploaded models and fairly compensate each participant for their contributions through rewards. Moreover, the proposed scheme addresses the problem of harmful participants who share subpar models while claiming high-quality data through a two-step verification approach. Simulation results, drawn from realistic mircorgrid network log datasets, demonstrate that the proposed solutions outperform state-of-the-art techniques by enhancing the security model and guaranteeing fair reward distributions.

The vulnerability of smart contracts has been demonstrated by an increasing number of multi-million exploitation incidents in public blockchains. Several works propose applying runtime verification to protect smart contracts post-deployment. However, none discuss the induced onchain overhead that may preclude its deployment, leaving smart contracts unprotected. A prominent solution to the onchain overhead is outsourcing the analysis off-chain. In this work, we analytically study the potential efficiency of off-chain smart contract runtime verification. We present a generic queueing network model of the off-chain runtime verification and the block generation process. The queuing model approach allows us to efficiently and flexibly capture the non-deterministic behavior of blockchain, estimating the number of transactions in the pool and their corresponding waiting times. We analyze the onchain overhead and evaluate off-chain RV, providing numerical indicators of transaction processing latency and throughput.

Heterogeneous wireless networks (HetNets), where networks are deployed with ultra-dense small cells (SCs), is one of the main enabling technologies for future wireless networks. In such networks, signals are vulnerable to severe blockage, interference, and intermittent connectivity. This can be largely overcome using the emerging Reconfigurable Intelligent Surface (RIS) technology that can enhance HetNets performance by controlling the propagation environment. However, jointly optimizing the parameters of base stations’ (BSs’) active beamforming and RISs’ passive beamforming is a major challenge in RIS-empowered HetNets. In this paper, we investigate the issue of rate control in RIS-empowered multi-cell multiple-input single-output (MISO) HetNets via joint users’ equipment (UEs) rate fairness and SCs rate load balancing. We assume RIS-assisted SC BSs at mmWave underlying a RIS-assisted macrocell (MC) BS at sub-6GHz serving dual-connectivity UEs that can concurrently connect to the MC BS and a single SC BS. Then, we formulate an optimization problem whose objective is to jointly optimize the active transmit beamforming vectors of the MC and SCs BSs on the one hand and the passive beamforming vectors of the MC and SCs RISs on the other hand. Due to the high non-convexity and complexity of the formulated problem, we propose a novel distributed Deep Deterministic Policy Gradient (DDPG)-based multi-task deep reinforcement learning (MTDRL) scheme to solve the problem and learn network dynamics. Through deliberate definitions of MTDRL agent’s tasks and their corresponding main elements, we demonstrate via simulations that our proposed scheme guarantees a fair distribution of rates within UEs and SCs. In addition, we quantify the robustness of our proposed MTDRL scheme compared with some benchmarks in terms of convergence speed and utility values.

Adopting honeypot defenses is a promising technology for protecting the industrial Internet of Things (IIoT), particularly the Advanced Metering Infrastructure (AMI). The effectiveness of AMI defense is entirely reliant on the deployment of honeypots by small-scale power suppliers (SPSs) and then sharing the defense data with traditional power retailers (TPRs) to build anomaly detectors. TPR encourages the SPSs to share their collected honeypot logs by designing proper rewards. However, TPRs cannot confirm the validity of the shared defense data unless they have access to SPSs' private data, compromising their privacy since SPSs may be reluctant to disclose their private collected data. In addition, the honeypot logs are large, which increases the sharing costs. Federated Learning (FL), as a promising privacy-preserving machine learning technique, can solve these problems. Yet, the conventional FL algorithm cannot optimally fit the security defense model and the associated returned rewards in the AMI network. Thus, using two proposed solutions, including a modified FedAvg algorithm, this paper proposes a privacy-preserving and cost-effective FL framework for efficient security model development and fair rewards, in which SPSs can share only the learned ML model while TPR can validate the quality of the uploaded models and compensate all participants with appropriate rewards that reflect their contributions. The proposed framework also considers malicious participants who claim high-quality data while sharing bad models. We run extensive simulations on realistic log datasets, and the results show that the proposed solutions outperform existing approaches.

The ever-expanding landscape of advanced applications and services, as well as the associated emerging attacks in the zero-touch network and service management (ZSM) paradigm, necessitates novel approaches to manage complex network infrastructures while addressing the security requirements of beyond 5G networks. To address this issue, we present a cutting-edge, novel semi-supervised federated learning approach that incorporates a Deep Reinforcement Learning (DRL) agent for real-time defense system updates. Specifically, we propose the DRL-FedUSS framework, which stands for DRL-based Federated Uncertainty-guided Semi-Supervised learning. DRL-FedUSS is designed explicitly for Label-at-Client scenarios to accelerate the training convergence when clients hold a scarcity of labeled and an abundance of unlabeled network traffic samples. The DRL-FedUSS framework integrates a DRL agent that intelligently selects the most informative samples with a real-time adaptive threshold for data annotation, considering uncertainty, time, budget constraints, and, most importantly, the convergence rate and confidence level constraints. Our extensive simulations on realistic non-independent and identically distributed (non-IID) datasets prove that the DRL-FedUSS framework outperforms baseline approaches, achieving superior intrusion detection accuracy, reducing the associated cost, and accelerating the convergence rate with minimal network traffic labeled data.

Clustered federated multi task learning (CFL) is introduced as an effective and efficient approach for addressing statistical challenges such as non-independent and identically distributed (non-IID) data among workers. Workers in CFL are clustered in groups based on similarity (i.e., cosine similarity) in their data distributions, in which each cluster is equipped with an efficient specialized model. However, this approach can be costly and time-consuming when implemented in hierarchical wireless networks (HWNs) due to uploading several models at every round to enable the cloud server to capture the incongruent data distribution from different edge networks. This brings about the need for novel solutions to address these challenges. To this end, this paper introduces a framework with two cloud-based model aggregation approaches, round-based and split-based, so as to minimize latency and resource consumption while attaining satisfying personalized accuracy. In the round-based scheme, the cloud aggregates the models from the edge servers after a predetermined number of rounds. As for the split-based scheme, the models are collected by the cloud only when edge servers perform the split. Extensive experiments are conducted to evaluate and compare the proposed heuristics against approaches presented in the recent literature. The numerical results and findings demonstrate that the proposed heuristics significantly conserve resources by reducing energy consumption by 60% and saving time, all while accelerating the convergence rate for cluster workers across various edge networks.

The majority of streaming Internet of Things (IoT) applications use machine learning models to identify and classify streaming inputs before forwarding them for further processing. These streaming IoT systems, however, are vulnerable to poisoning and adversarial attacks. An adversary deliberately modifies the input by adding a small perturbation during the communication to fool the class label into producing an arbitrary or specific output. The increasing number of well-developed, imperceptible attacks necessitates more sophisticated countermeasures. To this end, this paper underlines this problem and proposes a new scheme based on committee-based machine learning models: some have experience with only benign inputs, and others with benign and adversarial inputs. Then, the probabilities of the outputs of these pairs' models are utilized. The KL-divergence after that is applied to identify, detect, and mitigate such streaming attacks. Specifically, we use the uncertainty measures between the output of mitigation and non-mitigation ML models as a proxy to identify adversely attacked inputs. We use traffic sign classification in autonomous vehicle technology as a streaming IoT application. Our experiments demonstrate that the proposed approach can detect and mitigate adversarial attacks with high confidence for the white-box attack.

Datasets are essential for training machine learning algorithms and ensuring accurate classifications. However, obtaining such datasets, especially those relating to IEC61850 GOOSE messages in smart grids, poses a significant challenge for researchers. Privacy regulations and potential misuse of industrial data have compounded this problem, necessitating alternative methods for generating datasets. In this paper, we detail the design and implementation of a simulation testbed that uses MATLAB/Simulink, OpenPLC and the lib61850 library. This testbed simulates a smart grid system and generates IEC61850 GOOSE messages for dataset creation. We assess the testbed performance using a simplified smart grid model with multiple protection relays, also known as Intelligent Electronic Devices (IEDs), enabling us to measure the response time of the protection system under various fault conditions. The testbed is flexible, allowing for design alterations and expansions, which aids researchers in generating diverse datasets to represent various smart grid networks. This flexibility will increase the availability of valuable datasets and enable the broader application of machine-learning techniques in this domain.

Advanced Information Communication Technology (ICT) is used in smart grid systems to introduce intelligence and efficiency, potentially outperforming conventional power systems. A fundamental component of a smart grid system is the Smart Meters (SMs), which are integrated with billing utilities, such as national control centers (NCC), and advanced metering infrastructure (AMI). However, like most emerging technologies, some security vulnerabilities and attacks were found. In this paper, we address such vulnerabilities, specifically associated with SMs, that occur when energy consumption is reported to the billing system, specifically through the IEC-60870-5-104(IEC-104) protocol. Since existing datasets do not include sufficient data related to such vulnerabilities, especially in SM with IEC-104 protocol communication, we developed a testbed with a virtual environment and generated a dataset with and without attack vectors. We then proposed a novel anomaly detection algorithm based on LSTM autoencoder, which combines the functional benefits of LSTM and the deep learning of autoencoders. The model's performance is evaluated against two popular attacks, MITM and Replay, and our result shows that the replay attack is harder to find since the attack is executed without data alteration.

Internet of Drones (IoD)-aided wireless networks are proving their efficiency in various commercial and military applications, such as object recognition, surveillance, and data acquisition. However, the broadcast communication nature of IoD networks raises significant communication security issues. This paper investigates drone-to-ground communication subject to eavesdroppers in urban environments. We aim to provide secure communication utilizing physical layer security by increasing network secrecy rates. In addition, we aim to reduce the energy consumption within the IoD network by optimizing drones’ transmitting and jamming power and employing energy harvesting techniques to charge drones wirelessly. Our optimization problem is formulated as a Markov decision process (MDP), and a deep reinforcement learning (DRL) algorithm is proposed to solve the problem.

Protecting the privacy of personal information, including emotions, is essential, and organizations must comply with relevant regulations to ensure privacy. Unfortunately, some organizations do not respect these regulations, or they lack transparency, leaving human privacy at risk. These privacy violations often occur when unauthorized organizations misuse machine learning (ML) technology, such as facial expression recognition (FER) systems. Therefore, researchers and practitioners must take action and use ML technology for social good to protect human privacy. One emerging research area that can help address privacy violations is the use of adversarial ML for social good. Evasion attacks, which are used to fool ML systems, can be repurposed to prevent misused ML technology, such as ML-based FER, from recognizing true emotions. By leveraging adversarial ML for social good, we can prevent organizations from violating human privacy by misusing ML technology, particularly FER systems, and protect individuals' personal and emotional privacy. In this work, we propose an approach called Chaining of Adversarial ML Attacks (CAA) to create a robust attack that fools misused technology and prevents it from detecting true emotions. To validate our proposed approach, we conduct extensive experiments using various evaluation metrics and baselines. Our results show that CAA significantly contributes to emotional privacy preservation, with the fool rate of emotions increasing proportionally to the chaining length. In our experiments, the fool rate increases by 48% in each subsequent chaining stage of the chaining targeted attacks (CTA) while keeping the perturbations imperceptible ($\epsilon = 0.0001$).

In the 5G/B5G network paradigms, intelligent medical devices known as the Internet of Medical Things (IoMT) have been used in the healthcare industry to monitor remote users’ health status, such as elderly monitoring, injuries, stress, and patients with chronic diseases. Since IoMT devices have limited resources, mobile edge computing (MEC) has been deployed in 5G networks to enable them to offload their tasks to the nearest computational servers for processing. However, when IoMTs are far from network coverage or the computational servers at the terrestrial MEC are overloaded/emergencies occur, these devices cannot access computing services, potentially risking the lives of patients. In this context, unmanned aerial vehicles (UAVs) are considered a prominent aerial connectivity solution for healthcare systems. In this article, we propose a multiagent federated reinforcement learning (MAFRL)-based resource allocation framework for a multi-UAV-enabled healthcare system. We formulate the computation offloading and resource allocation problems as a Markov decision process game in federated learning with multiple participants. Then, we propose an MAFRL algorithm to solve the formulated problem, minimize latency and energy consumption, and ensure the quality of service. Finally, extensive simulation results on a real-world heartbeat data set prove that the proposed MAFRL algorithm significantly minimizes the cost, preserves privacy, and improves accuracy compared to the baseline learning algorithms.

Runtime-verification of smart contracts ensures the absence of exploitations within a transaction during execution. It is a crucial security aspect that is often omitted due to its high onchain overhead. The lack of runtime-verification in public blockchains allowed attackers to compromise vulnerable contracts and cause significant monetary losses. Although several runtime protection solutions have been proposed, they do not discuss the onchain overhead limitation, which may hinder their deployment and undermine their effectiveness. To address this problem, we propose an efficient Smart contract Runtime Protection framework, called SRP, that minimizes the onchain burden of runtime-verification by integrating an off-chain mechanism with onchain contract execution. The proposed hybrid architecture is designed to protect already-deployed smart contracts from attacks in real-time while maintaining the throughput of the underlying blockchain. We first present SRP from a design perspective proposing a protocol customized for off-chain runtime-verification interoperability. Then, we evaluate our approach empirically and demonstrate the applicability of SRP using a proof-of-concept implementation on a local instance of the Ethereum network. Our empirical and experimental results indicate the feasibility and efficiency of our approach, where SRP outperforms the onchain-only mechanism in terms of service time and throughput, for increasing workloads.

Clustered federated Multitask learning is introduced as an efficient technique when data is unbalanced and distributed amongst clients in a non-independent and identically distributed manner. While a similarity metric can provide client groups with specialized models according to their data distribution, this process can be time-consuming because the server needs to capture all data distribution first from all clients to perform the correct clustering. Due to resource and time constraints at the network edge, only a fraction of devices is selected every round, necessitating the need for an efficient scheduling technique to address these issues. Thus, this paper introduces a two-phased client selection and scheduling approach to improve the convergence speed while capturing all data distributions. This approach ensures correct clustering and fairness between clients by leveraging bandwidth reuse for participants spent a longer time training their models and exploiting the heterogeneity in the devices to schedule the participants according to their delay. The server then performs the clustering depending on predetermined thresholds and stopping criteria. When a specified cluster approximates a stopping point, the server employs a greedy selection for that cluster by picking the devices with lower delay and better resources. The convergence analysis is provided, showing the relationship between the proposed scheduling approach and the convergence rate of the specialized models to obtain convergence bounds under non-i.i.d. data distribution. We carry out extensive simulations, and the results demonstrate that the proposed algorithms reduce training time and improve the convergence speed by up to 50% while equipping every user with a customized model tailored to its data distribution.

Deep neural networks have shown vulnerability to well-designed inputs called adversarial examples. Researchers in industry and academia have proposed many adversarial example defense techniques. However, they offer partial but not full robustness. Thus, complementing them with another layer of protection is a must, especially for mission-critical applications. This article proposes a novel online selection and relabeling algorithm (OSRA) that opportunistically utilizes a limited number of crowdsourced workers to maximize the machine learning (ML) system's robustness. The OSRA strives to use crowdsourced workers effectively by selecting the most suspicious inputs and moving them to the crowdsourced workers to be validated and corrected. As a result, the impact of adversarial examples gets reduced, and accordingly, the ML system becomes more robust. We also proposed a heuristic threshold selection method that contributes to enhancing the prediction system's reliability. We empirically validated our proposed algorithm and found that it can efficiently and optimally utilize the allocated budget for crowdsourcing. It is also effectively integrated with a state-of-the-art black box defense technique, resulting in a more robust system. Simulation results show that the OSRA can outperform a random selection algorithm by 60% and achieve comparable performance to an optimal offline selection benchmark. They also show that OSRA's performance has a positive correlation with system robustness.

Federated edge learning (FEEL) is a rapidly growing distributed learning technique for next-generation wireless edge systems. Smart systems across various application domains face challenges, such as data heterogeneity, limited wireless resources, and device heterogeneity, which necessitate intelligent participant selection schemes that accelerate convergence rates. Consequently, this article presents joint participant selection and bandwidth allocation schemes to address these challenges. First, we formulate an optimization problem that considers communication and computation latencies, as well as imbalanced data distribution, while meeting round deadlines and bandwidth constraints. To address the combinatorial problems of participant selection, we employ a relaxation method followed by a proposed priority selection algorithm to select near-optimal participants. The proposed algorithm initially prioritizes participants with larger datasets, effective channel states, and better CPU speeds. To address data heterogeneity, we propose a randomized deadline-controlling algorithm that diversifies updates by allowing the edge server to include different participants with fewer data samples in training rounds. The proposed algorithms offer near-optimal performance compared to the brute-force method. Experiments demonstrate that our proposed scheme accelerates the convergence rate by up to 55% under extensive non-IID settings compared to benchmarks. Furthermore, the deadline-controlling algorithm improves performance at high levels of data heterogeneity, resulting in faster FEEL systems.

Reconfigurable Intelligent Surface (RIS) has recently emerged as an enabling technology to enhance reliability and overcome blockage in future heterogeneous wireless networks (HetNets). Adjusting amplitudes and phases of the RIS elements to achieve such goals is a major challenge. In this paper, we study the problem of network rate control to achieve users (UEs) fairness and smallcells (SCs) load balancing in multi-cell RIS-assisted multiple-input single-output (MISO) HetNets. We consider dual-connectivity UEs that can simultaneously connect to mmWave-operating SCs and sub-6GHz-operating RIS-assisted macrocell (MC), where RISs are mainly deployed to enhance sub-6GHz signal reception and mitigate interference. Then, we formulate an optimization problem whose objective is to jointly control the active beamforming vectors of SCs and MC on the one hand and the passive beamforming vectors of RISs on the other hand to maximize UEs fairness and network load balancing. Due to the high complexity of the formulated problem, we propose a novel multi-task deep reinforcement learning (MTDRL) model based on the Deep Deterministic Policy Gradient (DDPG) algorithm to solve the problem and learn system dynamics. Through proper definitions of network tasks and their main elements, we show via simulations that our proposed MTDRL-based model ensures fair distribution of rates within UEs and SCs and that it outperforms key benchmarks.

In 6G networks, unmanned aerial vehicles (UAVs) can serve as aerial flying base stations (AFBS) with aerial mobile edge computing (AMEC) server capabilities. AFBS is an increasingly popular solution for delivering time-sensitive applications, extending network coverage, and assisting ground base stations in the healthcare systems for remote areas with limited infrastructure. Furthermore, the UAVs are deployed in the healthcare system to support the Internet of medical things (IoMT) devices in data collection, medical equipment distribution, and providing smart services. However, ensuring the privacy and security of patients' data with the limited UAV resources is a major challenge. In this paper, we present a federated deep reinforcement learning framework for resource allocation in UAV-enabled healthcare systems, where IoMT devices send their trained model parameters without transmitting sensitive raw data to the AMEC server. In the proposed framework, the IoMT device is associated with AFBS based on the quality of the data and its demand in order to maximize learning efficiency and accuracy. This work aims to minimize the computation costs of the IoMT devices while considering UAV resources and the fairness of UAV coverage. Simulation results prove that our proposed algorithm outperforms other baseline algorithms in learning accuracy and computational cost.

Federated learning (FL) has evolved to leverage a distributed dataset from numerous IoT devices to improve the performance of a Machine Learning (ML) model while preserving the privacy of device data. Client devices train a global model jointly and share local model updates with a central entity or a server. However, FL is vulnerable to a variety of adversarial attacks that target its security and privacy and lead to compromising the main FL task. In particular, devices can contribute unreliable local model updates due to poisoning attack, or unintentionally due to their limited resources. Therefore, identifying trustworthy and reliable devices to participate in FL task is a key security challenge. In this paper, we propose a reputation management mechanism based on Deep Reinforcement Learning (DRL) in order to optimize the selection and evaluation of reliable devices and improve the accuracy of the FL model. The experimental results show that the proposed DRL-based reputation management scheme can enhance the FL accuracy by 20% while requiring fewer training iterations when compared to conventional reputation-based methods.

In recent years, Federated Edge Learning has gained interest from both industry and academia for deployment at the wireless network edge. However, some resource-restricted edge devices (EDs) bear more computation and communication loads due to the heterogeneity of data and resources. Several approaches have been proposed in the literature to reduce energy costs by scheduling only a few EDs to complete training tasks based on their energy budgets. Nevertheless, from a practical perspective, the incongruent data distribution cannot be captured, resulting in a biased model for EDs that are frequently selected. Furthermore, the frequently scheduled devices deplete their energy quickly, making them inaccessible. Thus, this paper proposes a novel scheduling policy based on the historical participation of each ED that ensures an unbiased model while balancing learning tasks so that all EDs consume equivalent energy at the end of the training. We formulate an optimization problem based on Jain's fairness index, followed by tractable algorithms to solve this problem. Extensive experiments have been conducted, and the results show that the proposed algorithm balances the energy consumption among EDs and accelerates the convergence rate while achieving satisfactory performance.

Federated Learning (FL) is one of the hot research topics, and it utilizes Machine Learning (ML) in a distributed manner without directly accessing private data on clients. How-ever, FL faces many challenges, including the difficulty to obtain high accuracy, high communication cost between clients and the server, and security attacks related to adversarial ML. To tackle these three challenges, we propose an FL algorithm inspired by evolutionary techniques. The proposed algorithm groups clients randomly in many clusters, each with a model selected randomly to explore the performance of different models. The clusters are then trained in a repetitive process where the worst performing cluster is removed in each iteration until one cluster remains. In each iteration, some clients are expelled from clusters either due to using poisoned data or low performance. The surviving clients are exploited in the next iteration. The remaining cluster with surviving clients is then used for training the best FL model (i.e., remaining FL model). Communication cost is reduced since fewer clients are used in the final training of the FL model. To evaluate the performance of the proposed algorithm, we conduct a number of experiments using FEMNIST dataset and compare the result against the random FL algorithm. The experimental results show that the proposed algorithm outperforms the baseline algorithm in terms of accuracy, communication cost, and security.

Abstract The licensed band is crowded and suffers from immense mobile data traffic growth, which exceeded 58 exabytes per month in 5 years. Meanwhile, a significant portion of the unlicensed band is underutilized and not coordinated efficiently. Experiments in some urban areas of the world have shown that only 5% of the unlicensed 5 GHz band is being used. 5G NR‐U technology supports 5G networks in the unlicensed band to alleviate the traffic congestion and boosts 5G networks capacity. Different heterogeneous network access technologies already use the unlicensed band. Consequently, 5G NR‐U networks will operate in the proximity of the other coexisting networks, such as WiFi networks in the 5 GHz and 6 GHz bands. In such environments, assessing the shared spectrum becomes challenging and necessitates adequate protocols to identify idle slots for successful transmissions. Cooperative Spectrum Sensing (CSS) improves the spectrum assessment process, as the decision about the spectrum state is rendered based on the local decisions of multiple sensing nodes. CSS is exploited by integrating it with Blockchain technology to design a decentralized cooperative spectrum management system called: Blockchain‐Based Cooperative Spectrum Management (BCSM). The system is attributed to ameliorating 5G NR‐U awareness about the neighboring WiFi networks traffic in the unlicensed band. An algorithm is designed for performing distributed cooperative spectrum assessment between the 5G NR‐U base stations to profile the WiFi networks traffic in their proximity. To ensure fairness based on the effort expended in assessing the spectrum, a priority‐based algorithm is designed for spectrum access scheduling. A proof‐of‐concept is implemented using private Ethereum Blockchain and NS3 simulator. Finally, the system's accuracy is evaluated empirically along with theoretical security analysis.

Federated learning (FL) has emerged to leverage datasets from multiple devices to improve the performance of a machine learning (ML) model while providing privacy preservation for devices. The training data is collected at the devices, also known as FL workers, which collaboratively train a global learning model and share their local model updates with a central entity or server without sharing their data. However, FL can be susceptible to various adversarial attacks that target its security and privacy. In particular, the workers can upload unreliable local model updates, leading to corruption of the main FL task. Workers may intentionally contribute unreliable local updates by launching poisoning attacks or unintentionally by updating low-quality models caused by high device mobility, limited device resources, or unstable network connection. Consequently, identifying reliable and trustworthy workers becomes critical for FL security. In this article, the concept of reputation is adopted as a metric to evaluate workers’ reliability and trustworthiness. In addition, deep reinforcement learning (DRL)-based reputation mechanism is proposed for optimal selection and evaluation of reliable FL workers. Due to the dynamic nature of worker behavior in the FL environment, the DRL-based algorithm deep deterministic policy gradient (DDPG) is employed to improve the FL model accuracy and stability. We compare the performance of our proposed method with a conventional reputation method and deep$Q$-networks (DQNs)-based reputation method. Our simulation results demonstrate that our proposed method can improve FL accuracy by more than 30% under various scenarios and achieves better convergence than the other methods.

Federated learning (FL) is a promising paradigm for future sixth-generation wireless systems to underpin network edge intelligence for smart cities applications. However, most of the data collected by the Internet of Things devices in such applications is unlabeled, necessitating the use of semi-supervised learning. Existing studies have introduced solutions to run semi-supervised FL; however, they overlooked the inherent critical impacts of the wireless characteristics at the network edge. We fill this gap by proposing novel solutions to run semi-supervised FL over wireless network edge, considering the limited computation and communication resources and deadline constraints and realizing that unlabeled data can be automatically labeled during the training rounds to improve the performance of the global model. The problem is first formulated as an optimization problem followed by a two-phase solution. In the first phase, we propose a bisection-based algorithm to find the transmit power and local processing speed that optimally fit the new injected labeled data. In the second phase, we propose three algorithms to control the local updates and injected samples that meet the deadline constraint. We analyze the performance of each algorithm concerning the tradeoffs between learning performance, training time, and total energy consumption. Targeting two applications in smart cities, human activity recognition and object detection, we conduct extensive simulations using realistic federated data sets under nonindependent and identically distributed settings. Numerical results show that the proposed algorithms effectively utilize unlabeled samples while accounting for the characteristics of wireless edge networks in smart cities.

Vehicular Ad Hoc Networks (VANETs) have the potential to enable the next-generation Intelligent Transportation Systems (ITS). In ITS, data contributed by vehicles can build a spatio-temporal view of traffic statistics, which can improve road safety and reduce slow traffic and jams. To preserve drivers’ privacy, vehicles should use multiple pseudonyms instead of only one identity. However, vehicles may exploit this abundance of pseudonyms and launch Sybil attacks by pretending to be multiple vehicles. Then, these Sybil (or fake) vehicles report false data, e.g., to create fake congestion or pollute traffic management data. In this article, we propose a Sybil attack detection scheme using proofs of work and location. The idea is that each road side unit (RSU) issues a signed time-stamped tag as a proof for the vehicle’s anonymous location. Proofs sent from multiple consecutive RSUs are used to create a trajectory which is used as vehicle anonymous identity. Also, contributions from one RSU are not enough to create trajectories, rather the contributions of several RSUs are needed. By this way, attackers need to compromise an infeasible number of RSUs to create fake trajectories. Moreover, upon receiving the proof of location from an RSU, the vehicle should solve a computational puzzle by running proof of work (PoW) algorithm. Then, it should provide a valid solution (proof of work) to the next RSU before it can obtain a proof of location. Using the PoW can prevent the vehicles from creating multiple trajectories in case of low-dense RSUs. To report an event, the vehicle has to send the latest trajectory to an event manager. Then, the event manager uses a matching technique to identify the trajectories sent from Sybil vehicles. The scheme depends on the fact that the Sybil trajectories are bounded physically to one vehicle, and therefore, their trajectories should overlap. Extensive experiments and simulations demonstrate that our scheme achieves high detection rate of Sybil attacks with low false negative and acceptable communication and computation overhead.

Clustered Federated Multitask Learning (CFL) was introduced as an efficient scheme to obtain reliable specialized models when data is imbalanced and distributed in a non-i.i.d. (non-independent and identically distributed) fashion amongst clients. While a similarity measure metric, like the cosine similarity, can be used to endow groups of the client with a specialized model, this process can be arduous as the server should involve all clients in each of the federated learning rounds. Therefore, it is imperative that a subset of clients is selected periodically due to the limited bandwidth and latency constraints at the network edge. To this end, this paper proposes a new client selection algorithm that aims to accelerate the convergence rate for obtaining specialized machine learning models that achieve high test accuracies for all client groups. Specifically, we introduce a client selection approach that leverages the devices' heterogeneity to schedule the clients based on their round latency and exploits the bandwidth reuse for clients that consume more time to update the model. Then, the server performs model averaging and clusters the clients based on predefined thresholds. When a specific cluster reaches a stationary point, the proposed algorithm uses a greedy scheduling algorithm for that group by selecting the clients with less latency to update the model. Extensive experiments show that the proposed approach lowers the training time and accelerates the convergence rate by up to 50% while imbuing each client with a specialized model that is fit for its local data distribution.

In this paper, a Deep Q-Network (DQN) based multi-agent multi-user power allocation algorithm is proposed for hybrid networks composed of radio frequency (RF) and visible light communication (VLC) access points (APs). The users are capable of multihoming, which can bridge RF and VLC links for accommodating their bandwidth requirements. By leveraging a non-cooperative multi-agent DQN algorithm, where each AP is an agent, an online power allocation strategy is developed to optimize the transmit power for providing users’ required data rate. Our simulation results demonstrate that DQN’s median convergence time training is 90% shorter than the Q-Learning (QL) based algorithm. The DQN-based algorithm converges to the desired user rate in half duration on average while converging with the rate of 96.1% compared to the QL-based algorithm’s convergence rate of 72.3%. Additionally, thanks to its continuous state-space definition, the DQN-based power allocation algorithm provides average user data rates closer to the target rates than the QL-based algorithm when it converges.

Recognizing the patient's emotions using deep learning techniques has attracted significant attention recently due to technological advancements. Automatically identifying the emotions can help build smart healthcare centers that can detect depression and stress among the patients in order to start the medication early. Using advanced technology to identify emotions is one of the most exciting topics as it defines the relationships between humans and machines. Machines learned how to predict emotions by adopting various methods. In this survey, we present recent research in the field of using neural networks to recognize emotions. We focus on studying emotions' recognition from speech, facial expressions, and audio-visual input and show the different techniques of deploying these algorithms in the real world. These three emotion recognition techniques can be used as a surveillance system in healthcare centers to monitor patients. We conclude the survey with a presentation of the challenges and the related future work to provide an insight into the applications of using emotion recognition.

Internet of Things (IoT) is an innovative paradigm envisioned to provide massive applications that are now part of our daily lives. Millions of smart devices are deployed within complex networks to provide vibrant functionalities, including communications, monitoring, and controlling of critical infrastructures. However, this massive growth of IoT devices and the corresponding huge data traffic generated at the edge of the network created additional burdens on the state-of-the-art centralized cloud computing paradigm due to the bandwidth and resource scarcity. Hence, edge computing (EC) is emerging as an innovative strategy that brings data processing and storage near to the end users, leading to what is called the EC-assisted IoT. Although this paradigm provides unique features and enhanced Quality of Service (QoS), it also introduces huge risks in data security and privacy aspects. This article conducts a comprehensive survey on security and privacy issues in the context of EC-assisted IoT. In particular, we first present an overview of EC-assisted IoT, including definitions, applications, architecture, advantages, and challenges. Second, we define security and privacy in the context of EC-assisted IoT. Then, we extensively discuss the major classifications of attacks in EC-assisted IoT and provide possible solutions and countermeasures along with the related research efforts. After that, we further classify some security and privacy issues as discussed in the literature based on security services and based on security objectives and functions. Finally, several open challenges and future research directions for secure EC-assisted IoT paradigm are also extensively provided.

Ridesharing allows multiple persons to share one vehicle for their trips instead of using multiple vehicles. Ridesharing can reduce the number of vehicles in the street, which consequently can reduce air pollution, traffic congestion, and transportation cost. However, ridesharing organization requires passengers to report sensitive location information about their trips to a trip organizing server (TOS) which creates a serious privacy issue. The existing ridesharing organization schemes are neither flexible nor scalable in the sense that they require a driver and a rider to have exactly the same trip to share a ride, and they are inefficient if applied to large geographic areas. In this paper, we propose two efficient privacy-preserving ridesharing organization schemes for Non-transferable Ridesharing Service (NRS) and Transferable Ridesharing Service (TRS). In NRS, a rider shares a ride from his/her trip's start to the destination with only one driver, whereas, in TRS, a rider can transfer between multiple drivers while en route until he reaches his destination. In the proposed schemes, the ridesharing area is divided into a number of small geographic areas, called cells, and each cell has a unique identifier. Each driver/rider should encrypt his/her trip's data with modified kNN encryption scheme, and send an encrypted ridesharing offer/request to the TOS. In NRS scheme, Bloom filters are used to represent the trip information compactly before encryption. Then, the TOS can measure the similarity of the encrypted trips to organize shared rides without revealing either the users' identities or the locations. In TRS scheme, drivers report their encrypted routes, and then the TOS builds a directed graph that is passed to a modified version of Dijkstra's shortest path algorithm to search for an optimal path for rides that can achieve a set of preferences prescribed by the riders. Although TRS can be used to organize non-transferable trips, performance evaluation shows that NRS requires less communication overhead than TRS. Our formal privacy proof and analysis demonstrate that the proposed schemes can preserve users privacy and our experimental results using routes extracted from real maps show that the proposed schemes can be used efficiently for large cities.

Privacy concerns are considered one of the main challenges in smart cities as sharing sensitive data induces threatening problems in people's lives. Federated learning has emerged as an effective technique to avoid privacy infringement as well as increase the utilization of the data. However, there is a scarcity in the amount of labeled data and an abundance of unlabeled data collected in smart cities; hence there is a necessity to utilize semi-supervised learning. In this paper, we present the primary design aspects for enabling federated learning at the edge networks taking into account the problem of unlabeled data. We propose a semi-supervised federated edge learning method called FedSem that exploits unlabeled data in real-time. FedSem algorithm is divided into two phases. The first phase trains a global model using only the labeled data. In the second phase, Fedsem injects unlabeled data into the learning process using the pseudo labeling technique and the model developed in the first phase to improve the learning performance. We carried out several experiments using the traffic signs dataset as a case study. Our results show that FedSem can achieve accuracy by up to 8% by utilizing the unlabeled data in the learning process.

Received Signal Strength (RSS) fingerprint-based localization has attracted a lot of research effort and cultivated many commercial applications of location-based services due to its low cost and ease of implementation. Many studies are exploring the use of deep learning (DL) algorithms for localization. DL's ability to extract features and to classify autonomously makes it an attractive solution for fingerprint-based localization. These solutions require frequent retraining of DL models with vast amounts of measurements. Although crowdsourcing is an excellent way to gather immense amounts of data, it jeopardizes the privacy of participants, as it requires to collect labeled data at a centralized server. Recently, federated learning has emerged as a practical concept in solving the privacy preservation issue of crowdsourcing participants by performing model training at the edge devices in a decentralized manner; the participants do not expose their data anymore to a centralized server. This paper presents a novel method utilizing federated learning to improve the accuracy of RSS fingerprint-based localization while preserving the privacy of the crowdsourcing participants. Employing federated learning allows ensuring preserving the privacy of user data while enabling an adequate localization performance with experimental data captured in real-world settings. The proposed method improved localization accuracy by 1.8 meters when used as a booster for centralized learning and achieved satisfactory localization accuracy when used standalone.

This work proposes an intelligent receiver for wireless Orbital Angular Momentum (OAM) systems. The proposed receiver consists of an optical filter followed by a neural network. The filter is designed to partially match a range of OAM modes such that the intensity of its output represents the projection of the received signal over the different modes (including fractional modes). The output of the filter is then passed as an input to a pre-trained shallow neural network to decide on the transmitted symbol. Simulations show that the proposed receiver outperforms both the conventional matched filters based receiver and the Fourier-based receiver.

Recently, Autonomous Vehicles (AVs) have gained extensive attention from both academia and industry. AVs are a complex system composed of many subsystems, making them a typical target for attackers. Therefore, the firmware of the different subsystems needs to be updated to the latest version by the manufacturer to fix bugs and introduce new features, e.g., using security patches. In this paper, we propose a distributed firmware update scheme for the AVs' subsystems, leveraging blockchain and smart contract technology. A consortium blockchain made of different AVs manufacturers is used to ensure the authenticity and integrity of firmware updates. Instead of depending on centralized third parties to distribute the new updates, we enable AVs, namely distributors, to participate in the distribution process and we take advantage of their mobility to guarantee high availability and fast delivery of the updates. To incentivize AVs to distribute the updates, a reward system is established that maintains a credit reputation for each distributor account in the blockchain. A zero-knowledge proof protocol is used to exchange the update in return for a proof of distribution in a trustless environment. Moreover, we use attribute-based encryption (ABE) scheme to ensure that only authorized AVs will be able to download and use a new update. Our analysis indicates that the additional cryptography primitives and exchanged transactions do not affect the operation of the AVs network. Also, our security analysis demonstrates that our scheme is efficient and secure against different attacks.

This work proposes a means to increase the effective modulation bandwidth of a visible light communication (VLC) system using phosphor-coated white light emitting diodes (LEDs) under wide-angle operation. The proposed remedy involves employing a response-flattening filter at the receiver's end of such a VLC system. Off-the-shelf component models are used to simulate the VLC system of interest in order to guarantee realistic results. A trade-off between satisfying a relatively large modulation bandwidth and wide-angle operation of the system is observed. The response- flattening filter proves to be an adequate remedy to mitigate such a trade-off. Analytical expressions and numerical results are used to verify the validity of our proposal.

Non-orthogonal multiple access (NOMA) is considered to be one of the promising multiple access techniques for 5G networks. This paper studies a decode-and-forward cooperative underlay cognitive radio NOMA network. Closed-form expressions for the outage probability of two NOMA secondary destination users (D1and D2) are evaluated. Furthermore, optimal power allocation factors for different distances of D1are found to satisfy the outage probability (OP) fairness for both users. Moreover, the OP for NOMA compared to that of conventional multiple access. Finally, the obtained analytical expressions are corroborated by Monte Carlo simulation.

The broadcast nature of wireless networks makes them vulnerable to eavesdropping attacks; therefore, physical layer security (PLS) becomes essential to protect the signal at the physical layer. In this paper, we investigate PLS aspects in terms of the secrecy capacity (SC) in hybrid radio frequency (RF)/visible light communication (VLC) networks. First, we design RF-and VLC-based beamforming vectors to maximize the achievable SC. Moreover, using these vectors, we solve the power minimization problem satisfying the required SC. The results provide useful insights into how the eavesdropper's location affects the power consumption profile. Finally, the results reveal that the performance of the VLC network in terms of the consumed power per bits/s/Hz is more efficient than the RF one.

In this paper, we investigate the performance of spectrally and energy efficient orthogonal frequency-division multiplexing (SEE-OFDM) based visible light communications (VLC) systems. We propose to apply non-orthogonal multiple access (NOMA) for the downlink in SEE- OFDM based VLC network. Moreover, we provide a novel approach in decoding the composite NOMA signal. Next, based on the considered channel conditions, we analyze the impact of power-allocating coefficients on the bit-error rate (BER) performance. Finally, satisfying the target BER, we estimate the data rate regions achievable by the receivers under the derived system parameters and then compare the results with the ones obtainable for orthogonal multiple access.

Wireless power transfer and energy harvesting have attracted a significant research attention in terms of their application in cooperative relaying systems. Most of existing works in this field focus on the half-duplex (HD) relaying mechanism over certain fading channels, however, in contrast, this paper considers a dual-hop full-duplex (FD) relaying system over a generalized independent but not identically distributed α-μ fading channel, where the relay node is energy-constrained and entirely depends on the energy signal from the source node. Three special cases of the α-μ model are investigated, namely, Rayleigh, Nakagami- m and Weibull fading. As the system performance, we investigate the outage probability (OP) for which we derive exact unified closed-form expressions. The provided Monte Carlo simulations validate the accuracy of our analysis. Moreover, the results obtained for the FD scenario are compared to the ones related to the HD. The results demonstrate that the decode-and-forward relaying outperforms the amplify-and-forward relaying for both HD and FD scenarios. It is also shown that the FD scenario performs better than the HD relaying systems. Finally, we analyzed the impact of the fading parameters α and μ on the achievable OP.

In this paper, a two-hop decode-and-forward wireless powered relaying cognitive radio network with interference alignment over Rayleigh fading channels is investigated. The energy-constrained secondary relay node harvests energy from both the information and interference signals. Then, the harvested energy is used by the relay to forward the information signal from the source to the destination node. By applying beamforming matrices to primary and secondary networks, the performance metrics, such as outage probability, capacity, and bit error rate are studied under perfect and imperfect channel state information scenarios for both power-splitting relaying (PSR) and time-switching relaying (TSR) protocols. In addition, the optimal network performance is achieved by calculating the optimal energy harvesting time-switching and power-splitting coefficients. Finally, closed-form expressions for the outage probability of primary and secondary users are derived. Monte Carlo simulation results corroborate the analytical ones and show that the PSR technique outperforms TSR in the considered system model.

In this paper, a two-hop decode-and-forward cognitive radio system with deployed interference alignment is considered. The relay node is energy- constrained and scavenges the energy from the interference signals. In the literature, there are two main energy harvesting protocols, namely, time-switching relaying and power-splitting relaying. We first demonstrate how to design the beamforming matrices for the considered primary and secondary networks. Then, the system capacity under perfect and imperfect channel state information scenarios, considering different portions of time-switching and power-splitting protocols, is estimated.

In this paper, we consider a two-hop amplify-and- forward (AF) relaying system, where the relay node is energy-constrained and harvests energy from the source node. In the literature, there are three main energy-harvesting (EH) protocols, namely, time-switching relaying (TSR), power-splitting (PS) relaying (PSR) and ideal relaying receiver (IRR). Unlike the existing studies, in this paper, we consider α-μ fading channels. In this respect, we derive accurate unified analytical expressions for the ergodic capacity for the aforementioned protocols over independent but not identically distributed (i.n.i.d) α-μ fading channels. Three special cases of the α-μ model, namely, Rayleigh, Nakagami-m and Weibull fading channels were investigated. Our analysis is verified through numerical and simulation results. It is shown that finding the optimal value of the PS factor for the PSR protocol and the EH time fraction for the TSR protocol is a crucial step in achieving the best network performance.

Visible light communication (VLC) is an effective alternative technology to overcome the limitations related to the radio frequency (RF) spectrum. In the modern day of communication systems, the energy harvesting (EH) technique is considered as a promising technology to design more energy efficient communication systems. Integrating VLC with the EH technology in wireless networks guaranties the reliability of these networks. In this paper, we consider a dual-hop VLC/RF wireless communication, composed of two Light Emitting Diodes (LEDs) and two receivers, assisted by a decode-and-forward (DF) relaying system operating with EH in order to boost the coverage of VLC systems. Using successive interference cancellation, we derive achievable rates of both users. Afterwards, we determine the achievable rate-region for this communication system where we show that this region can take four shapes depending on the communication scenario. Then, we formulate the achievable rate-region maximization problem, and we develop solution to find the optimal design for the EH time switching protocol. Further, we show that EH enhances the performance of the communication system in a certain regime of its initial power. We finally present selected numerical result to verify the analytic results.

Visible light communication (VLC) has emerged as a promising candidate to complement and enhance the performance of the existing radio frequency (RF) networks in indoor environments. Due to the broadcast nature of both RF and VLC channels, improving the transmission confidentiality is a requirement in practical wireless networks. Physical-layer security has emerged to provide a first line of defense against eavesdropping attacks. In this paper, we study the physical layer security problem of a hybrid RF/VLC system. First, we formulate the minimization problem of the consumed electrical power in the hybrid RF/VLC network while satisfying the user's required secrecy rate. Then, we propose a zero forcing beamforming strategy and a minimum power allocation algorithm. Simulations results show that the proposed power allocation and beamforming algorithms outperform the benchmark algorithms in terms of the average consumed electrical power in various indoor scenarios.

This paper studies a two-hop decode-and-forward underlay cognitive radio system with interference alignment technique. An energy-constrained relay node harvests the energy from the interference signals through a power-splitting (PS) relaying protocol. Firstly, the beamforming matrices design for the primary and secondary networks is demonstrated. Then, a bit error rate (BER) performance of the system under perfect and imperfect channel state information (CSI) scenarios for PS protocol is calculated. Finally, the impact of the CSI mismatch parameters on the BER performance is simulated.

In this work, the performance of an underwater visible light communication system utilizing a vertical communication channel is evaluated. The inhomogeneity of underwater environment is taken into consideration. A mathematical model for the received power is derived and bit error rates (BER) are computed for different underwater environments. The validity of the model is verified by numerical results. Moreover, our results show that there exists an optimum transmitter-receiver separation, where BER is minimum, under a specific transmission orientation angle.

The growing energy consumption of communication systems raises economical and environmental concerns. Indoor visible light communication (VLC) systems are energy friendly as they exploit the illumination power of LED luminaries for data transmission. However, the VLC systems suffer from service disruptions due to the limited coverage of light. To alleviate this problem, hybrid RF#x002F;VLC architecture has been recently proposed for indoor networks where the RF networks can be exploited to resolve the limited VLC coverage. In this paper, we consider a network composed of multiple VLC access points and an RF access points. We develop resource allocation algorithms to maximize the system's power efficiency defined as the total system throughput per unit power. Simulations show that deploying VLC access points improves the power efficiency of the system and increases the minimum guaranteed rate per user. Simulations also show that higher power efficiency can be obtained using the same number of operating VLC access points by redistributing them more uniformly across the room.

The IEEE 802.15.7 standard for visible light communication (VLC) includes the use of run-length-limited codes to mitigate modulation-induced flickering and the further use of coding to improve bit error rate performance. In this paper, we introduce algorithms to design codes using finite-state machines, which provide simultaneously a coding gain while also mitigating flicker. The codes have the additional advantage of being optimally soft-decision decodable using the Viterbi algorithm. To compare the flicker mitigation performance of different codes, we further introduce a mathematical measure of flicker based on the power spectrum of the transmitted signals. We discuss tradeoffs between flicker mitigation, code rate, and coding gain, design several codes, and compare their error rate and flicker mitigation performance to some codes in the VLC standard.

Visible light communications (VLC) technology has recently emerged as a complementary technology to the indoor radio frequency (RF) networks. While the backhauling of the indoor RF networks has been supported by fiber optics, the backhauling of the VLC network is still an open research problem. Power line communications (PLC) has been considered as a possible solution for the VLC networks due to its ubiquity. However, given the noisy behaviour of the channels, the use of PLC backhauling requires further study to investigate the maximum rate which can be supported for VLC networks. In this paper, we continue our work on a single-user hybrid PLC/VLC/RF system [1] to study the effect of PLC backhauling in multi-user hybrid VLC/RF networks. To this end, we adopt an orthogonal frequency division multiplexing (OFDM)- based PLC backhaul system where we find the optimal power and subcarrier allocation algorithm that maximizes the multi-user rate utility function for the cascaded PLC and VLC links in parallel with the RF network. Moreover, we study numerically the impact of various parameters on the system performance including the PLC transmission power, the RF and VLC maximum allowable rates, and the numbers of mobile terminals and access points.

Based on the concept of reconfigurable antennas (RAs), SSK-RA has been recently proposed as a novel transmission scheme to improve the performance of space shift keying (SSK). In this context, it has been shown that RAs' reconfigurable properties can be used as additional degrees of freedom to enhance the throughput, implementation complexity, and error performance of SSK. In this paper, we extend SSK-RA to cognitive radio (CR) systems in an effort to improve the secondary system's performance in a spectrum sharing scenario. Taking advantage of the interplay between RAs and the propagation channels for both the secondary and interference links, we propose a RA-based scheme with pointing-direction reconfiguration aiming at improving the secondary system's performance while verifying an outage interference constraint to the primary user (PU). In this paper, we analyse the performance of the proposed scheme in Rician fading channels and provide simulation examples confirming these analytical results. The proposed schemes are shown to offer better bit error rate (BER) performance and lower implementation complexity when compared to conventional antenna-based spectrum sharing systems.

In this work, the outage performance analysis of a dual-hop transmission system composed of asymmetric radio frequency (RF) channels cascaded with free-space optical (FSO) links is presented. The RF links are modeled by the Rayleigh fading distribution and the FSO links are modeled by Malaga (M) turbulence distribution. The FSO links account for pointing errors and both types of detection techniques (i.e. heterodyne detection as well as intensity modulation/direct detection (IM/DD)). Transmit diversity is applied at the source, selection combining is applied at the destination, and the relay is equipped with single RF receive antenna and single aperture for relaying the information over FSO links. With this model, a new exact closed-form expression is derived for the outage probability of the end-to- end signal-to-noise ratio of such communication systems in terms of the Meijer's G function under fixed amplify-and-forward relay scheme. All new analytical results are verified via computer-based Monte-Carlo simulations and are illustrated by some selected numerical results.

In this work, bit error rate (BER) measurements of visible light communications (VLC) systems are introduced as an effective possible replacement of reflectivity measurements in a conventional optical plasmonic sensing procedure. In particular, we investigate a procedure where we exploit the phenomenon of the variations of BER values of the VLC systems with the sensed concentration of contaminations in the sensing medium. We consider a system composed of a VLC white LED source that transmits data through the sensing medium, which is then detected by a receiver and the BER values are computed. Our analysis proves that the information extracted from the BER measurements is sufficient to learn about the sensing medium and hence can replace conventional measurement techniques used in optical sensing. Thus, a simpler procedure of optical sensing is proposed due to the low cost of the proposed system and its flexibility in sensing medium in different environment scenarios. In this work, the proposed idea is verified for optical SPR sensors for their high impact state-of-art performance over other conventional optical sensors. Moreover, the VLC-based system is shown to have no negative effect on the performance of the designed optical SPR sensor in a way that undermines its operation.

Developing energy efficient wireless communication networks has become crucial due to the associated environmental and financial benefits. Visible light communication (VLC) has emerged as a promising candidate for achieving energy efficient wireless communications. Integrating VLC with radio frequency (RF)-based wireless networks has improved the achievable data rates of mobile users. In this paper, we investigate the energy efficiency benefits of integrating VLC with RF-based networks in a heterogeneous wireless environment. We formulate and solve the problem of power and bandwidth allocation for energy efficiency maximization of a heterogeneous network composed of a VLC system and an RF communication system. Then, we investigate the impact of the system parameters on the energy efficiency of the mixed RF/VLC heterogeneous network. Numerical results are conducted to corroborate the superiority in performance of the proposed hybrid system. The impact of hybrid system parameters on the overall energy efficiency is also quantified.

Based on the concept of reconfigurable antennas (RAs), space-shift keying (SSK)-RA has been recently proposed as a novel transmission scheme to improve the performance of SSK. In this context, it has been shown that RAs' reconfigurable properties can be used as additional degrees of freedom to enhance the throughput, implementation complexity, and error performance of SSK. In this paper, we study the implementation of SSK-RA within underlay cognitive radio systems in an effort to improve the performance of the secondary user while verifying the constraints set by the primary user (PU). Taking advantage of the interplay between RAs and the propagation channels for both the secondary and interference links, we propose an RA-based scheme with beam-direction reconfiguration aiming at improving the secondary system's performance while verifying an outage interference constraint to the PU. In this paper, we analyze the performance of the proposed scheme in Rician fading channels and provide simulation examples confirming these analytical results. The proposed schemes are shown to offer enhanced bit error rate performance and lower implementation complexity when compared with conventional antenna-based spectrum sharing systems.

The increased demands for indoor wireless data services with the limited available radio frequency (RF) spectrum are motivating researchers to investigate alternative technologies to augment the existing RF networks. Utilizing the visible light spectrum by exploiting visible light communication (VLC) has shown strong potential to augment RF networks in indoor scenarios. The ubiquity of the power-line network makes it an attractive choice as a communication medium between the data sources and the VLC transmitters through power line communication (PLC). Hence, integrating VLC and PLC systems can be a strong complementary hybrid wireline/wireless technology for indoor data networks. In this paper, we investigate the power allocation problem for a communication scenario in which data is transferred through a cascaded PLC/VLC channel in parallel to an RF wireless channel. We develop an algorithm for allocating the transmission powers among the communication nodes to maximize the achievable rate. Our results show that the proposed system provides appreciable rate gains compared to conventional RF communication systems for the same amount of total transmission power.

In future smart grids, energy storage systems (ESSs) are expected to play a key role in reducing peak hour electricity generation cost and the associated level of carbon emissions. Considering their high acquisition, operation, and maintenance costs, ESSs are likely to serve a large number of users. Hence, optimal sizing of energy ESSs plays a critical role as over-provisioning ESS size leads to under-utilizing costly assets and under-provisioning it taxes operation lifetime. This paper proposes a stochastic framework for analyzing the optimal size of energy storage systems. In this framework the demand of each customer is modeled stochastically and the aggregate demand is accommodated by a combination of power drawn from the grid and the storage unit when the demand exceeds grid capacity. In this framework an analytical method is developed, which provides tractable solution to the ESS sizing problem of interest. The results indicate that significant savings in terms of ESS size can be achieved.

This paper focuses on the resilience of routing protocols against malicious insiders willing to disrupt communications. Previous study showed that introducing randomness and data replication enhances the resilience of routing protocols. It makes them unpredictable for an attacker and provides route diversification. We propose a theoretical framework of the resilience based on biased random walks on a torus lattice. The objective is to evaluate analytically the influence of bias and data replication introduced to random walks. The bias allows to decrease the route length, thus reducing the probability of a data packet to meet a malicious insider along the route; however, it also decreases the degree of randomness (entropy). When combined with data replication, the reliability is improved thanks to route diversity despite an additional overhead in terms of energy consumption. The main goal is to provide a good tradeoff between shortest path and route diversity for a reasonable cost.

Reconfigurable antennas (RA) offer an emerging technology that allows wireless devices to alter their antenna states determined by different radiation patterns to maximize received signal strength. In this paper, we consider multiuser orthogonal frequency-division multiple access cognitive heterogeneous networks (HetNets) and we study the potential benefits of employing RA in terms of improving the overall network capacity. In cognitive HetNets, a secondary network is allowed to share the spectrum with the primary network under the condition that the interference level experienced by the primary network is below a predetermined threshold. To satisfy this interference constraint, a secondary user (SU) employs a power control mechanism, which typically limits its transmission power and thus reduces substantially its performance. Moreover, the large number of users expected for next-generation networks brings dense interference to the secondary network and, as such, even efficient interference mitigation and resource allocation techniques can fail in maintaining an acceptable performance level for the network. In this work, we consider utilizing RA technology at SUs to act as an additional resource in terms of selecting antenna radiation patterns that improve received signal strength among SUs. This also limits the mutual interference between the secondary and primary networks. We propose a game theoretical framework for jointly selecting the subcarriers as well as the RA antenna state at each SU that maximizes the overall capacity of the network while meeting the interference target in the primary network. Using potential games that guarantee the existence of a Nash equilibrium, our results show that, by selecting the best RA state and subcarriers for each SU, the capacity of the secondary network increases substantially compared to a scenario with conventional omni-directional antennas.

Abstract This paper focuses on the development of multiuser access schemes for spectrum sharing systems whereby secondary users are allowed to share the spectrum with primary users under the condition that the interference observed at the primary receiver is below a predetermined threshold. In particular, two scheduling schemes are proposed for selecting a user among those that satisfy the interference constraint and achieve an acceptable signal‐to‐noise ratio level. The first scheme focuses on optimizing the average spectral efficiency by selecting the user that reports the best channel quality. In order to alleviate the relatively high feedback required by the first scheme, a second scheme based on the concept of switched diversity is proposed, where the base station (BS) scans the secondary users in a sequential manner until a user whose channel quality is above an acceptable predetermined threshold is found. We develop expressions for the statistics of the signal‐to‐interference and noise ratio as well as the average spectral efficiency, average feedback load, and the delay at the secondary BS. We then present numerical results for the effect of the number of users and the interference constraint on the optimal switching threshold and the system performance and show that our analysis results are in perfect agreement with the numerical results. Copyright © 2014 John Wiley & Sons, Ltd.

In this paper, it is demonstrated for the first time that the problem of continuous downhole monitoring in the oil and gas industry is effectively addressed by the use of visible light communication (VLC). As a reliable, flexible and low-cost technique, VLC can fulfill a critical need of operators to maintain production efficiency and optimize gas well performance. The proposed VLC system makes use of a light emitting diode (LED) transmitter and a high sensitivity single photon detecting receiver referred to as single-photon avalanche diode (SPAD). The latter is instrumental in achieving long range communications, and the fact that ambient light is not present in a gas pipe is exploited. Specifically, the lack of ambient light enables high signal to noise ratio (SNR) at the receiver which operates in a photon counting mode. In this study, the bit error ratio (BER) performance of the system is simulated for a 4 kilometres long metal pipe. It is shown that the proposed system has superior power efficiency over conventional methods, which is important as it is assumed that the transmitter is battery operated. In addition, the theoretical BER performance is calculated and compared to the simulation results.

Reconfigurable antennas (RA) have been viewed as a hardware-efficient alternative solution to multiple-input multiple-output systems whereby network users can vary the antenna radiation patterns using a single antenna element to maximize the received signal strength. In this paper, we study the potential benefits of employing RA in multiuser orthogonal frequency division multiple access cognitive heterogeneous networks (Het-Nets) in terms of the overall network capacity. In cognitive HetNets, a secondary (unlicensed) network is allowed to share the spectrum with the primary (licensed) network under the condition that the interference level at the primary network is below a predetermined value. To account for this interference constraint, the secondary user (SU) can limit their transmission power and thus reducing substantially its performance. Moreover, the large number of users expected for next generation network brings dense interference to the secondary network and thus even efficient interference mitigation and resource allocation techniques can fail in maintaining the required performance level. Therefore, in this paper, we consider utilizing an RA at the SUs that acts as an additional resource which can be optimized by selecting the best state that maximizes the signal strength among the SUs and limits the mutual interference between the secondary and primary network. In particular, we propose a game theoretical framework for selecting the subcarriers based on best allocation techniques as well as the random antenna state selection that maximizes the overall capacity of the network while obeying the interference level in the primary network. We use potential games which guarantee the Nash equilibrium existence. Our results show that by selecting the optimal RA state and the subcarriers for each user, the capacity of the secondary network increases substitutionally with limited hardware complexity.

In underlay cognitive networks, the unlicensed (secondary) user is allowed to share the spectrum with the licensed (primary) user under the constraint that the interference at the primary user should be below a specific threshold. This constraint forces the cognitive network to apply power control techniques, which typically result in limited transmission power and hence limited coverage area. As a solution to reach the intended far destinations, relaying techniques can be used to improve the performance of underlay cognitive networks in terms of signal-to-noise ratio (SNR). Recently, single best relay selection schemes have been proposed that maintain a desired SNR for the cognitive network while satisfying the interference level at the primary network. However, these schemes suffer from high outage probability especially at low SNR, where the probability of finding a single relay that satisfies both constraints is reduced. Therefore, in this paper, we propose a multiple relay selection scheme, where at each channel realization, we allow for multiple relay selection in case the best relay, among those that satisfy the interference constraint, does not satisfy the desired SNR. In particular, we select the least number of relays whose sum of their individual SNR's achieves the desired level. This scheme leads to a reduced outage probability especially for low SNR. We derive a closed form expression for the cumulative density function (CDF) of the selected relay(s) SNR for a certain number of relays. Simulation results confirm the analytical results and show that the proposed relay(s) selection algorithm in an underlay cognitive environment improves the outage probability and symbol error rate (SER) in low SNR regions.

The operations of smart metering heavily rely on the communication network for efficient data gathering, thus eliminating manual meter reading. Smart electronic devices are deployed in open, unattended and possibly hostile environment such as consumer's home and office areas, making them particularly vulnerable to physical attacks. Resilience is needed to mitigate such inherent vulnerabilities and risks related to security and reliability. In this article, a general overview of the resilience including definition, metric and resilient techniques relevant for smart metering is presented. A quantitative metric, visual and meaningful, based on the graphical representation is adopted to compare routing protocols in the sense of resilience against active insider attacks. Five well-known routing protocols from the main categories have been studied through simulations and their resilience is evaluated according to the given metric. Resilient techniques introduced to these protocols have enhanced significantly the resilience against attacks providing route diversification.

In this paper, the performance of a visible light communication (VLC) network exploiting power control is considered. The achievable rate region of two VLC communication pairs is characterized. The system employs optical orthogonal frequency division multiplexing (O-OFDM) with power control performed at the transmitters. The optical signal clipping effect is taken into consideration which results from the physical limitations at the transmitters. Also, the system is constrained by the desired illumination power for each transmitter. We prove that the achievable rate region is defined as the union of two regions where the boundary of each of these regions can be obtained by a single variable optimization problem. Our numerical results show the effects of the system parameters including direct current (DC) bias, the desired illumination power, clipping noise and the relative positions of the receivers relative to the LED transmitters on the achievable rate region of the two users. We show the enhancement in the performance resulted from using power control compared to orthogonal resource allocation techniques.

In this work, we present the performance analysis of a dual-hop transmission system composed of asymmetric radio frequency (RF) and free-space optical (FSO) links in underlay cognitive networks. For the RF link, we consider an underlay cognitive network where the secondary users share the spectrum with licensed primary users, where indoor femtocells act as a practical example for such networks. More specifically, we assume that the RF link is subject to an interference constraint. The FSO link accounts for pointing errors and both types of detection techniques (i.e. intensity modulation/direct detection (IM/DD) as well as heterodyne detection). On the other hand, RF link is modeled by the Rayleigh fading distribution that applies power control to maintain the interference at the primary network below a specific threshold whereas the FSO link is modeled by a unified Gamma-Gamma fading distribution. With this model, we derive new exact closed-form expressions for the cumulative distribution function, the probability density function, the moment generating function, and the moments of the end-to-end signal-to-interference plus noise ratio of these systems in terms of the Meijer's G functions. We then capitalize on these results to offer new exact closed-form expressions for the outage probability, the higher-order amount of fading, and the average error rate for binary and Mary modulation schemes, all in terms of Meijer's G functions. All our new analytical results are verified via computer-based Monte-Carlo simulations and are illustrated by some selected numerical results.

In this paper, we investigate the impact of using outdated channel state information for incremental opportunistic relay selection in a spectrum sharing cognitive network. In our work, we present the outage performance of two schemes where the power allocation is based on the instantaneous outdated channel state information and the statistical knowledge of the interference links, referred to as CSI-based scheme and LF-based scheme, respectively. By investigating the effect of the rank of the selected relay and the correlation coefficients imbalance on outage performance, a comparison reveals that LF-based scheme outperforms its CSI-based counterpart. We validate our analysis with simulation results in a Rayleigh fading environment.

Cognitive heterogeneous networks (HetNets) have been recently introduced as a promising solution to meet the user demand for higher data rate. Due to the physical coexistence of microcells, femtocells and the lack of available spectrum, there is a need for techniques that allows users to share the same spectrum while maintaining required performance level for each user by adopting interference mitigation techniques. In this paper, we focus on resource allocation algorithm for orthogonal frequency-division multiple access (OFDMA) cognitive networks using game theory. In particular, we consider supermodular game theory, where given the problem meets specific requirement, the game has two significant features; it has at least one pure Nash Equilibrium (NE) and its best responses are monotonically increasing. Our objective is that each femtocell user selects a specific number of subcarriers determined by its needs. In comparison where at each iteration of the game, the femtocell user search all the subcarriers to maximize its payoff, our algorithm is based on selecting the subcarriers randomly and checks only those subcarriers that achieve higher payoff. Our results show that our algorithm reaches NE and can provide lower feedback compared to the sweeping-all subcarriers.

In cognitive radio (CR) systems, one of the main implementation issues is spectrum sensing because of the uncertainties in propagation channel, hidden primary user (PU) problem, sensing duration and security issues. This paper considers an orthogonal frequency-division multiplexing (OFDM)-based CR spectrum sharing system that assumes random access of primary network subcarriers by secondary users (SUs) and absence of the PU's spectrum utilization information, i.e., no spectrum sensing is employed to acquire information about the PU's activity or availability of free subcarriers. In the absence of information about the PU's activity, the SUs randomly access (utilize) the subcarriers of the primary network and collide with the PU's subcarriers with a certain probability. In addition, inter-cell collisions among the subcarriers of SUs (belonging to different cells) can occur due to the inherent nature of random access scheme. This paper conducts a stochastic analysis of the number of subcarrier collisions between the SUs' and PU's subcarriers assuming fixed and random number of subcarriers requirements for each user. The performance of the random scheme in terms of capacity and capacity (rate) loss caused by the subcarrier collisions is investigated by assuming an interference power constraint at PUs to protect their operation.

In spectrum sharing systems, a secondary user (SU) is allowed to share the spectrum with a primary (licensed) network under the condition that the interference observed at the receivers of the primary users (PU-Rxs) is below a predetermined level. In this paper, we consider a secondary network comprised of a secondary transmitter (SU-Tx) equipped with multiple antennas and a single-antenna secondary receiver (SU-Rx) sharing the same spectrum with multiple primary users (PUs), each with a distinct spectrum. We develop transmit antenna diversity schemes at the SU-Tx that exploit the multi-spectrum diversity provided by the existence of multiple PUs so as to optimize the signal-to-noise ratio (SNR) at the SU-Rx. In particular, assuming bounded transmit power at the SU-Tx, we develop switched selection schemes that select the primary spectrum and the SU-Tx transmit antenna that maintain the SNR at the SU-Rx above a specific threshold. Assuming Rayleigh fading channels and binary phase-shift keying (BPSK) transmission, we derive the average bit-error-rate (BER) and average feedback load expressions for the proposed schemes. For the sake of comparison, we also derive a BER expression for the optimal selection scheme that selects the best antenna/spectrum pair that maximizes the SNR at the SU-Rx, in exchange of high feedback load and switching complexity. Finally, we show that our analytical results are in perfect agreement with the simulation results.

In this paper, we develop multiuser access schemes for spectrum sharing systems whereby secondary users are allowed to share the spectrum with primary users under the condition that the interference observed at the primary receiver is below a predetermined threshold. In particular, we devise two schemes for selecting a user among those that satisfy the interference constraint and achieve an acceptable signal-to-noise ratio level. The first scheme selects the user that reports the best channel quality. In order to alleviate the high feedback load associated with the first scheme, we develop a second scheme based on the concept of switched diversity where the base station scans the users in a sequential manner until an acceptable user is found. In addition to these two selection schemes, we consider two power adaptive settings at the secondary users based on the amount of interference available at the secondary transmitter. In the On/Off power setting, users are allowed to transmit based on whether the interference constraint is met or not, while in the full power adaptive setting, the users are allowed to vary their transmission power to satisfy the interference constraint. Finally, we present numerical results for our proposed algorithms where we show the trade-off between the average spectral efficiency and average feedback load for both schemes.

Cognitive networks in underlay settings operate simultaneously with the primary networks satisfying stringent interference limits. This condition forces them to operate with low transmission powers and confines their area of coverage. In an effort to reach remote destinations, underlay cognitive sources make use of relaying techniques. Selecting the best relay among those who are ready to cooperate is different in underlay settings than traditional non-cognitive networks. In this paper, we present a relay selection scheme which uses the quotient of the relay link signal to noise ratio (SNR) and the interference generated from the relay to the primary user to choose the best relay. The proposed scheme optimizes this quotient in a way to maximize the relay link SNR above a certain value whereas the interference is kept below a defined threshold. We derive closed expressions for the outage probability and bit error probability of the system incorporating this scheme. Simulation results confirm the validity of the analytical results and reveal that the relay selection in cognitive environment is feasible in low SNR regions.

Spectrum sharing systems have been introduced to alleviate the problem of spectrum scarcity by allowing secondary unlicensed networks to share the spectrum with primary licensed networks under acceptable interference levels to the primary users. In this paper, we develop interference-aware random beam selection schemes that provide enhanced throughput for the secondary link under the condition that the interference observed at the primary link is within a predetermined acceptable value. For a secondary transmitter equipped with multiple antennas, our schemes select a random beam, among a set of power- optimized orthogonal random beams, that maximizes the capacity of the secondary link while satisfying the interference constraint at the primary receiver for different levels of feedback information describing the interference level at the primary receiver. For the proposed schemes, we develop a statistical analysis for the signal-to-noise and interference ratio (SINR) statistics as well as the capacity of the secondary link. Finally, we present numerical results that study the effect of system parameters including number of beams and the maximum transmission power on the capacity of the secondary link attained using the proposed schemes.

Under the scenario of an underlay cognitive radio network, we propose in this paper two adaptive schemes using switched transmit diversity and adaptive modulation in order to increase the spectral efficiency of the secondary link and maintain a desired performance for the primary link. The proposed switching efficient scheme (SES) and bandwidth efficient scheme (BES) use the scan and wait combining technique (SWC) where a transmission occurs only when a branch with an acceptable performance is found, otherwise data is buffered. In these schemes, the modulation constellation size and the used transmit branch are determined to minimize the average number of switched branches and to achieve the highest spectral efficiency given the fading channel conditions, the required error rate performance, and a peak interference constraint to the primary receiver (PR). For delay-sensitive applications, we also propose two variations of the SES and BES schemes using power control (SES-PC and BES-PC) where the secondary transmitter (ST) starts sending data using a nominal power level which is selected in order to minimize the average delay introduced by the SWC technique. We demonstrate through numerical examples that the BES scheme increases the capacity of the secondary link when compared to the SES scheme. This spectral efficiency improvement comes at the expense of an increased average number of switched branches and thus an increased average delay. We also show that the SES-PC and the BES-PC schemes minimize the average delay while satisfying the same spectral efficiency as the SES and BES schemes, respectively.

In this paper we develop a framework for optimizing the performance of the secondary link in terms of the average spectral efficiency assuming quantized channel state information (CSI) of the secondary and the secondary-to-primary interference channels available at the secondary transmitter. We consider the problem under the constraints of maximum average interference power levels at the primary receiver. We develop a sub-optimal computationally efficient iterative algorithm for finding the optimal CSI quantizers as well as the discrete power and rate employed at the cognitive transmitter for each quantized CSI level so as to maximize the average spectral efficiency. We show via analysis and simulations that the proposed algorithm converges for Rayleigh fading channels. Our numerical results give the number of bits required to sufficiently represent the CSI to achieve almost the maximum average spectral efficiency attained using full knowledge of the CSI.

Under the scenario of an underlay cognitive radio network, we propose in this paper an adaptive scheme using switched transmit diversity and adaptive modulation in order to increase the spectral efficiency of the secondary link. The proposed bandwidth efficient scheme (BES) uses the scan and wait (SWC) combining technique where a transmission occurs only when a branch with an acceptable performance is found, otherwise data is buffered. In our scheme, the modulation constellation size and the used transmit branch are determined to achieve the highest spectral efficiency given the fading channel conditions, the required error rate performance, and a peak interference constraint to the primary receiver. Selected numerical examples show that the BES scheme increases the capacity of the secondary link when compared to an existing switching efficient scheme (SES). This spectral efficiency comes at the expense of an increased average number of switched branches and thus an increased average delay.

In this paper, we study applying dual branch transmit switch-and-stay combining (SSC) technique for underlay cognitive radio (UCR) networks. In UCR, the secondary user is allowed to share the spectrum with the primary (licensed) user under the condition that interference at the primary receiver is below a predetermined threshold. Assuming binary phase-shift keying (BPSK) modulation and Rayleigh fading channels, we develop a closed form expression for the average bit error rate (BER) of the secondary link as a function of the switching threshold. We then find a closed form expression for the optimal switching threshold in the sense of minimizing the average BER. For the sake of comparison we derive an expression for the average BER of the dual branch transmit selection combining (SC) technique. We finally investigate the effect of correlation between secondary and interference channels on the average BER and the associated optimal switching threshold.

The anticipated increase in the density of the deployed wireless sensor networks calls for spectrum sharing through unlicensed access to licensed spectrum. The key technology for spectrum sharing in this scenario is cognitive radio networks. Cognitive relaying scenarios, where a cognitive (unlicensed) user provides relaying services to a licensed (primary) user, have been proposed before as a method to increase chances of spectrum white spaces. In this paper, we develop a wireless sensor network framework containing a cognitive user (sensor node), with delay sensitive data and limited power budget. The cognitive user offers relaying capability to the primary traffic when the primary connection fails to deliver. The cognitive user utilizes a scheduling mechanism that grants priority to relayed traffic over its own traffic. In our framework, the cognitive user is allowed to control the volume of the relayed traffic through an admission control parameter. The objective of the sensor node (cognitive user) is to minimize its traffic delay, subject to certain power budget allowed for relaying the primary traffic. Our key contributions in this work are the development of the aforementioned framework, the establishment of a mathematical formalization for this problem, the derivation of mathematical expressions for average power consumption and average packet delay, and the solution for the developed optimization problem by finding a value for the admission control parameter that minimizes delay while satisfying power budget constraints.

In this paper, we investigate the performance of a cooperative relay network performing location estimation through time of arrival (TOA). We derive Cramer-Rao lower bound (CRLB) for the location estimates using the relay network. The analysis is extended to obtain average CRLB considering the signal fluctuations in both relay and direct links. The effects of the channel fading of both relay and direct links and amplification factor and location of the relay node on average CRLB are investigated. Simulation results show that the channel fading of both relay and direct links and amplification factor and location of relay node affect the accuracy of TOA based location estimation.

In this paper we propose a novel technique for hybrid automatic repeat request (HARQ) systems where turbo codes are used as the forward error correction (FEC) techniques. This technique uses the histogram of the soft values generated by the turbo decoder to control the size and the contents of the retransmissions needed when the packet can not be decoded correctly. These soft values represent the reliabilities of the information bits; hence the proposed technique is a reliability-based (RB) HARQ technique. The proposed technique is compared to the conventional RBHARQ and the conventional rate compatible punctured turbo (RCPT) codes, and is shown to achieve higher throughput and/or less number of transmissions.

In this paper, we present a FPGA prototyping of the MIMO Decoder for the IEEE 802.16e WiMAX mobile systems. The IEEE 802.16e standard supports three types of MIMO space time codes (STC), referred to in the standard by matrix A, B, and C, that achieve different levels of throughput and diversity depending on the quality of the MIMO channels. In particular, the STC matrix A achieves full diversity by employing the Alomuti coding, while the STC matrix B achieves full rate by employing spatial multiplexing and the STC matrix C achieves full rate and diversity by employing the Golden code. In this paper, we present a FPGA architecture of MIMO decoder based on the fixed sphere decoder (FSD) algorithm that achieves close- to ML BER performance with a reduced computational complexity and fixed throughput. We show how a single FSD can be used to decode the different STC by adaptively processing the received signal according to the STC type prior to be fed to the FSD. The FPGA design is incorporated with a QR decomposition of the channel matrix. The proposed FSD achieves fixed and high throughput required for the WiMAX systems. The FPGA implementation is incorporated with a MATLAB simulation model of an FUSC OFDMA-based WiMAX 2times2 MIMO system to validate the hardware design.

In this paper, we present a class of cooperative beamforming algorithms for information relaying in wireless multihop sensor networks. We focus on networks whereby the source is communicating to the destination via a set of multihop relay nodes organized via hierarchical clustering. In particular, at each hop, a set of clusters are formed using a number of relay nodes where for each cluster, the relay nodes employ two different relaying strategies: i) amplify-and-forward via beamforming, ii) decode-and-forward via beamforming. For both strategies, we present algorithms that systematically select the beamforming weights for the relays at each cluster that optimize the uncoded bit error rates at the destination.

We propose a secondary CDMA network that operates as an underlay for a primary CDMA network where the code assignment for the secondary network is done cognitively. A code assignment criterion that minimizes interference from primary users and existing secondary users is formulated. The primary user codes as well as bit boundaries are unknown to the secondary network. The problem is initially formulated as a constrained optimization problem. Exhaustive search has complexity that is exponential in the spreading factor. The constraints are therefore relaxed to obtain a near-optimal solution with a complexity that is linear in the spreading factor and performance very close to the exhaustive search method. We consider the different cases where the primary users are bit- and chip-synchronous, chip-synchronous but bit-asynchronous, and chip-asynchronous over multi-path fading channels. We propose a method for blind epoch acquisition by processing the covariance matrix of the received signal. In all cases the performance improvement of the interference-minimizing code assignment over random code assignment is significant reaching over 3 dB for coded systems.

Abstract In this paper, we propose a code‐division multiple‐access (CDMA) secondary network to operate cognitively as an underlay for a primary network. A novel interference‐minimizing code assignment (IMCA) for secondary users is proposed such that the interference from existing primary and secondary users is minimized. This is accomplished by minimizing the mean square cross‐correlations between the candidate codes and the received signal. Since the codes of the primary CDMA network are unknown to the secondary network the scheme operates blindly and the problem is formulated as a constrained optimization of a Boolean quadratic form. The solution is obtained exhaustively and we demonstrate significant performance gains compared to random code assignment (RCA). We then slightly relax the constraint on the user code space and obtain a near‐optimal solution with complexity that is linear in the spreading factor. For the secondary network, we propose a slightly modified minimum‐output energy receiver that operates semi‐blindly as a first stage followed by parallel interference cancellation. For this receiver structure, we derive improved log‐likelihood ratios for the single‐user decoders based on partial knowledge of the user codes and channel coefficients. Significant error probability performance improvements of 2 dB or more are obtained due to IMCA in the coded case. Copyright © 2008 John Wiley & Sons, Ltd.

WLAN location determination systems are gaining increasing attention due to the value they add to wireless networks. In this paper, we present a multivariate analysis technique for enhancing the performance of WLAN location determination systems by taking the correlation between samples from the same access point into account. We show that the autocorrelation between consecutive samples from the same access point can be as high as 0.9. Giving a sequence of correlated signal strength samples from an access point, the technique estimates the user location based on the calculated probability of this sequence from the multivariate distribution. We use a linear autoregressive model to derive the multivariate distribution function for the correlated samples. Using analytical analysis, we show that the proposed technique provides better location accuracy over previous techniques especially for the highly correlated samples in a typical WLAN environment. Implementation of the technique in the Horus WLAN location determination system shows that the average system accuracy is increased by more than 64%. This significant enhancement in the accuracy of WLAN location determination systems helps increase the set of context-aware applications implemented on top of these systems.

We develop algorithms for sequential signal encoding from sensor measurements, and for signal estimation via fusion of channel-corrupted versions of these encodings. For signals described by state space models, we present optimized sequential binary-valued encodings constructed via threshold-controlled scalar quantization of a running Kalman filter signal estimate from the sensor measurements. We also develop methods for robust fusion from observations of these encodings corrupted by binary symmetric channels.

In this paper we propose an admission control policy for wireless ATM networks. The policy is based on the well know method, threshold-based guard channel policy. We modify it to deal with two different types of traffic classes; namely: CBR traffic class and ABR traffic class where we assume two different thresholds, one for each traffic class. In addition, we propose to buffer the handoff ABR calls if no free channels are available rather than rejecting them. For handoff CBR calls, we propose two methods, namely: a blocking method and a preemptive method. For the blocking method, we reject the handoff CBR calls if no channels are available. For the preemptive method, we accept handoff CBR calls in case of no available channels if ongoing ABR calls exist where we buffer one of them in order to serve the handoff CBR call. We study the effect of the thresholds, buffer size and the effect of the proposed methods on call blocking probabilities. Based on these results, we developed an algorithm that uses the proposed policy to estimate the appropriate thresholds and buffer size which meet a certain required call blocking probabilities for each traffic type.

In this paper, we studied the effect of the user mobility parameters on the quality of service parameters of the guard channel policy; namely: new call blocking probability and handoff call blocking probability. The high-way mobility model was utilized to define the traffic parameters of the user in terms of its mobility parameters, namely; average velocity of the user and the radius of the cell. The mathematical equations of the new call blocking probability and handoff call blocking probability were derived and solved iteratively. The results show that the value of the new call blocking probability is lower and that of the handoff call blocking probability is higher when compared with the case of non-mobile users. In addition, there exists a critical value; defined by the user mobility parameters; where the behavior of the new and handoff call blocking probabilities differs in a distinct way.

In this paper, we studied the effect of the user mobility parameters on the quality of service parameters of guard channel policy; namely: new call blocking probability and handoff call blocking probability. The high-way mobility model was utilized to define the traffic parameters of the user in terms of its mobility parameters, namely; average velocity of the user and the radius of the cell. The mathematical equations of the new call blocking probability and handoff call blocking probability were derived and solved iteratively. The results show that the value of the new call blocking probability is lower and that of the handoff call blocking probability is higher when compared with the case of non-mobile users. In addition, there exists a critical value; defined by the user mobility parameters; where the behavior of the new and handoff call blocking probabilities differs in a distinct way.