The increasing complexity of Beyond 5G and 6G networks necessitates new paradigms for autonomy and assur- ance. Traditional O-RAN control loops rely heavily on RIC- based orchestration, which centralizes intelligence and exposes the system to risks such as policy conflicts, data drift, and unsafe actions under unforeseen conditions. In this work, we argue that the future of autonomous networks lies in a multi-agentic architecture, where specialized agents collaborate to perform data collection, model training, prediction, policy generation, verification, deployment, and assurance. By replacing tightly- coupled centralized RIC-based workflows with distributed agents, the framework achieves autonomy, resilience, explainability, and system-wide safety. To substantiate this vision, we design and evaluate a traffic steering use case under surge and drift conditions. Results across four KPIs: RRC connected users, IP throughput, PRB utilization, and SINR, demonstrate that a naive predictor-driven deployment improves local KPIs but destabilizes neighbors, whereas the agentic system blocks unsafe policies, preserving global network health. This study highlights multi- agent architectures as a credible foundation for trustworthy AI- driven autonomy in next-generation RANs.

With the recent emergence of artificial intelligence (AI), edge users in industries and manufacturing have been extensively using AI-based services, which pose privacy and security risks to data. Distributed learning approaches deployed in the manufacturing industries help reduce data risks. However, traditional approaches cannot handle deep models as well as the scalability of edge-based internet of things (E-IoT) devices, especially in the manufacturing sector. Studies have proposed SplitFed learning (SFL) by combining split learning and the federated learning paradigm, but they fail to achieve an optimal trade-off between communication and computational limitations and are vulnerable to inversion attacks. We present a pruning-oriented security (POST) method that is designed around the SFL paradigm that not only helps in achieving a balance between communication and computation load for E-IoT devices, but also preserves the data and model privacy against inversion attacks. The POST leverages the concept of using a higher number of layers in the E-IoT devices, which restrains the attacker from reconstructing the outputs. Furthermore, the POST adds communication and computation constraints in the optimization function to reduce the overall cost of the method. The novel pruning method adopts the regularization and adversarial training approach to further improve the preservation of the privacy of intermediate features in the SFL paradigm. We conduct our experiments on publicly available datasets in real-world settings to illustrate the efficacy of the POST method in terms of preserving privacy while ensuring the best trade-off for communication and computation load.

In disaster-affected areas where conventional communication infrastructure collapses, Unmanned Aerial Vehicles (UAVs) can act as mobile IoT base stations to restore connectivity. However, maintaining reliable Low Power Wide Area links such as LoRa remains challenging due to terrain-dependent propagation, interference, and energy constraints. This work introduces RescueNav, an intent-driven UAV trajectory planning framework that integrates LoRa-specific signal constraints with reinforcement-learning-based decision-making. Unlike existing methods that treat communication as a secondary factor, RescueNav formalizes the operator’s intent to maintain Line of Sight connectivity, maximize coverage, and conserve UAV energy directly into the trajectory optimization process. By leveraging Q Learning with Prioritized Experience Replay, RescueNav dynamically adapts flight paths to evolving disaster environments, guided by a shaped reward function that encodes communication and energy objectives. Experiments with a Holybro S500 V2 platform equipped with a Pixhawk, Raspberry Pi, and LoRa modules demonstrate that RescueNav improves median signal strength by 4×, enhances throughput by 42%, and achieves a 55% higher cumulative reward than standard Q Learning. These results highlight the potential of intent-based reinforcement learning for resilient IoT communication in mission-critical post-disaster scenarios.

This paper proposes CADiS, a causality-driven anomaly detection framework, to address the challenges of root cause identification in high-dimensional Industrial Internet of Things (IIoT) multivariate time series. The essential difference between CADiS and existing correlation-driven deep models lies in its core innovation: it fundamentally redefines anomalies as the structural decay of an underlying causal mechanism, rather than merely capturing symptomatic deviations or spurious correlations. Specifically, the framework first learns a directed and lag-aware causal prior from normal data, compiling it into a structured attention mask to constrain information flow. Then, a Causal-Phase Decomposition (CPD) technique treats each time window as a micro-experiment, comparing an ante-phase with a post-phase to explicitly capture the dynamics of causal attenuation. Inference relies on a unified Causal-Change Score (CCS), which quantifies the degradation of causal association strength, directly revealing the breakdown of the system’s causal logic. Furthermore, the decomposed causal change matrix allows for fine-grained and auditable root cause diagnosis. Extensive experiments on real-world industrial datasets demonstrate that CADiS significantly outperforms strong baselines, achieving theVROCof 89.93% andVPRof 76.93% on SWaT; TheAPRof 18.04% andVROCof 78.38% on SMD, thereby validating its robustness and diagnostic precision.

Integrating large-scale antenna arrays is essential for overcoming capacity limitations in wireless communications. In this work, we examine a novel sixth-generation (6G) secure simultaneous wireless information and power transfer (SWIPT) system, where a transmitter equipped with an extremely large-scale antenna array (ELAA) operates in the near-field region. In our design, the transmitter concurrently delivers confidential data to information receivers and energy to zero-energy devices (ZEDs) via non-orthogonal multiple access (NOMA). A key innovation of our approach is the specialized near-field beamfocusing technique derived from a three-dimensional spherical channel model, which explicitly accounts for the unique propagation characteristics of near-field communications and distinguishes our method from traditional far-field designs. We formulate a non-convex optimization problem aimed at maximizing the secrecy rate while satisfying minimum quality-of-service and energy harvesting requirements. To solve this problem, we develop an iterative algorithm based on weighted sum-rate maximization and sequential convex approximations that effectively mitigate interference and enhance beamfocusing performance. Numerical simulations demonstrate that, with a 64-element uniform linear array and 40 dBm transmit power, our near-field NOMA system achieves an 18.41% higher secrecy rate than near-field spatial division multiple access (SDMA) and a 36.78-fold improvement over near-field orthogonal multiple access (OMA), along with a 6.39 dBm increase in harvested power relative to SDMA. These results underscore the critical role of specialized near-field design in next-generation 6G networks and its significant implications for industrial internet-of-things (IoT) and Industry 4.0 applications.

With the development of unmanned aerial vehicles (UAVs) and the diversification of low-altitude applications, the cooperation among UAVs with different capabilities and objectives offers an exciting prospect for achieving efficient and ubiquitous communication coverage. However, coordinating the cooperation and competition among heterogeneous UAVs is an intractable challenge. In this paper, we propose a novel centralized-distributed heterogeneous-UAVs intelligent communication network system, which addresses the cooperation-competition issue among heterogeneous UAVs through reasonable task allocation. Specifically, a hub UAV makes ground users (GUs) scheduling decisions based on global information and provides backhaul link support through trajectory optimization. Meanwhile, high-mobility distributed UAVs cooperate to ensure fair, efficient communication for assigned GUs. Although centralized user scheduling offers greater flexibility and better performance, it also faces the serious problems which includes time-varying local observation spaces, hybrid action spaces, heterogeneous state spaces, and reward discrepancies. To solve these problems, we propose a convolutional neural network-assisted heterogeneous-UAVs proximal policy optimization algorithm, which aims to jointly optimize UAV trajectories and user scheduling, maximizing the system’s total fair energy efficiency. The simulation results demonstrate that the proposed CNN-HUPPO algorithm outperforms the four multi-agent deep reinforcement learning (MADRL) benchmark algorithms and two baseline algorithms in terms of fairness and accumulative fair energy efficiency.

Alzheimer’s disease (AD) is considered to be a significant health challenge that affects the cognitive ability of elderly people. The effects can only be slowed down if the disease is detected at an early stage. Researchers have extensively explored the use of machine learning algorithms to ensure early detection and prediction. However, effective models are complex, hence limiting their interpretability and privacy. Federated learning (FL) approaches have also been proposed to add privacy aspect to the machine learning models, however, FL methods are vulnerable to model related attacks. To address this we propose Agentic ElderFedLearn, a novel framework that proceeds in the following steps: 1) model healthcare institutions as autonomous artificial intelligence (AI) agents training local models on multimodal data [electronic health record (EHR) and synthetic magnetic resonance imaging (MRI)]; 2) apply personalized differential privacy (DP) to gradients, adapting budgets based on dataset size and sensitivity; 3) use multiagent reinforcement learning (MARL) to optimize agent interactions, such as privacy adjustments and communication; and 4) perform effective aggregation via weighted trimmed mean to defend against attacks. This innovation ensures privacy, handles heterogeneity, and achieves 94% accuracy with 0.93 F1-score, outperforming centralized approaches while using synthetic data.

Cancer patients are known to have a higher likelihood of developing Cardiovascular Disease (CVD) compared to non-cancer individuals. Although various types of cancer can contribute to the onset of CVD, lung cancer is inherently linked with increased susceptibility. To bridge this hypothesis, we propose a Lung cancer detection and Cardiovascular Disease Prediction (LCDP) system through lung Computed Tomography (CT) scan images. The lung cancer detection module of the LCDP system utilizes Transfer Learning (TL) with AdaDenseNet for classification. It employs the improvised Proximity-based Synthetic Minority Over-sampling Technique (Prox-SMOTE), improving accuracy. In the CVD prediction module, the feature extraction was performed using the VGG-16 model, followed by classification using a Support Vector Machine (SVM) classifier. The impact and interdependence of lung cancer on CVD were evident in our evaluation, with high accuracies of 98.28% for lung cancer detection and 91.62% for CVD prediction.

The proliferation of low-powered devices in the Internet of Things (IoT) necessitates energy-efficient communication paradigms. Backscatter communication (BackCom) combined with cognitive radio-inspired non-orthogonal multiple access (CRNOMA) offers a promising solution. However, optimizing such systems is complex, especially when considering realistic energy harvesting (EH) models. This paper investigates the sum rate optimization of an EH-enabled passive backscatter node (BN) coexisting with primary devices (PDs) in a CR-NOMA network, employing a practical non-linear EH model. We leverage deep reinforcement learning (DRL) to dynamically optimize the BN’s reflection coefficient. Crucially, we conduct a comparative study of several DRL algorithms. These include deep deterministic policy gradient (DDPG), its prioritized replay variants (PERDDPG and CER-DDPG), and the stability-enhanced twin delayed DDPG (TD3). We also evaluate on-policy methods such as proximal policy optimization (PPO), as well as entropy-regularized algorithms like soft actor-critic (SAC) and its recurrent extension (RSAC). Additionally, we include the asynchronous advantage actor-critic (A3C) for comparison. We evaluate their performance in terms of sum rate, reflection coefficient adaptation, and harvested energy, contrasting results under non-linear versus linear EH models. Our findings provide insights into algorithm suitability for optimizing BackCom systems under realistic EH constraints, highlighting performance trade-offs and the impact of EH non-linearity.

Rapid advancement of radar technology has led to the emergence of cognitive radar systems, which utilize adaptive mechanisms to optimize performance in dynamic environments. This paper explores the integration of cognitive adaptability into smartphone-based Impulse Radio Ultra-Wideband (IRUWB) radar systems. By dynamically modifying the radar’s operational parameters based on real-time output analysis, we aim to address the limitations of current smartphone radar implementations, including high power consumption, static radar configurations, and the inherent mobility of smartphones. Our proposed Cognitive-Adaptive IR-UWB Radar (CAIR) system improves accuracy, power efficiency, and responsiveness, enabling effective target detection, target classification, gesture recognition, distance estimation, and vital sign monitoring in diverse scenarios. By incorporating cognitive radar principles, we present a novel approach to overcoming the challenges of varying environmental conditions and user contexts, ultimately delivering a more robust and versatile user experience. This paper outlines the CAIR architecture, algorithmic design, and adaptive control mechanisms, showcasing its potential to enhance smartphone radar sensing. When tested against the major smartphone use cases, our system improves accuracy by up to 11.5%, while achieving cognitive adaptability of up to 90%. Additionally, the Artificial Neural Network (ANN)-based cognitive model achieves an accuracy of 95% and an F1-score of 94%.

Connected Autonomous Vehicles (CAVs) are poised to revolutionize intelligent transportation by enhancing road safety and reducing traffic congestion through real-time communication. However, this dependency introduces vulnerabilities to cyberattacks, especially in emergency scenarios where secure, low-latency communication is critical. While Quantum Key Distribution (QKD) provides quantum-secure key exchange, relying solely on it for all communication processes can introduce latency during key generation, which can be problematic in time-sensitive situations. To address this, we propose HyQCAN, a Hybrid Quantum-Classical Authentication Network that integrates QKD with Dynamic Basis Switching (DBS) for vehicle identity authentication of emergency vehicles in Vehicular Ad Hoc Networks (VANETs). QKD ensures quantum-secure encryption, while DBS enables real-time adaptation of the key exchange process based on communication urgency. HyQCAN achieves an optimal balance between security and responsiveness, with an Average Authentication Time (AAT) of 3.34 ms and an Average Key Generation Efficiency (AKGE) of 111.82 bps, effectively safeguarding critical VANET communications in high-priority situations.

This work investigates the performance of rate splitting multiple access (RSMA) in a holographic reconfigurable intelligent surface (HRIS)-aided near-field (NF) driven downlink secure communication system under imperfect channel state information (iCSI) in the presence of an eavesdropper (Eve). We formulate a weighted sum secrecy rate (WSSR) while ensuring a minimum quality of service (QoS) at each node under the available resource constraints, such as the total power budget at the base station (BS). Since the optimization problem is nonconvex due to the coupling of the variables, we propose an iterative algorithm based on alternating optimization (AO) that jointly optimizes transmit beamforming at BS and phase shift at HRIS. Numerical results are shown to validate the effectiveness and convergence of the proposed algorithm. Furthermore, we also discuss the impact of the key system parameters, such as HRIS reflecting elements, minimum QoS constraint, transmit power budget, and number of users. The dominance of RSMA over conventional multiple-access technologies such as non-orthogonal multiple access (NOMA) and space division multiple access (SDMA) is also demonstrated.

The DNS (Domain Name System) protocol has been in use since the early days of the Internet. Although DNS as a de facto networking protocol had no security considerations in its early years, there have been many security enhancements, such as DNSSec (Domain Name System Security Extensions), DoT (DNS over Transport Layer Security), DoH (DNS over HTTPS) and DoQ (DNS over QUIC). With all these security improvements, it is not yet clear what resource-constrained Internet-of-Things (IoT) devices should be used for robustness. In this paper, we investigate different DNS security approaches using an edge DNS resolver implemented as a Virtual Network Function (VNF) to replicate the impact of the protocol from an IoT perspective and compare their performances under different conditions. We present our results for cache-based and non-cached responses and evaluate the corresponding security benefits. Our results and framework can greatly help consumers, manufacturers, and the research community decide and implement their DNS protocols depending on the given dynamic network conditions and enable robust Internet access via DNS for different devices.

The integration of the Internet of Things (IoT) with meta-materials advances both communication and sensing technologies. Using Meta-IoT sensors, environmental data can be acquired by analyzing the frequency response from reflected signals. In this study, we introduce a dual-purpose Meta-IoT sensor capable of simultaneously sensing environmental conditions and enabling communication. Machine learning (ML) plays a key role in optimizing sensor design and power management within these meta-material IoT systems. Hence this work leverages machine learning (ML) to optimize sensor design and power management in Meta-material IoT (Meta-IoT) systems. Specifically, Gaussian process regression (GPR) is used to explore and optimize sensor structures, while reinforcement learning adapts power management strategies dynamically. Simulation results highlight that the ML-driven methods enable adaptable and efficient Meta-IoT systems.

Covert communication has become a hot topic in the wireless transmission field due to the ability to secure transmitted data by hiding the wireless transmissions. Given the extensive use of drone communications and its urgent demand for security, we investigate covert communications in aerial terrestrial integrated networks (ATINs), where an unmanned aerial vehicle (UAV) tries to send private messages to a remote user via multiple terrestrial relays under the supervisions of the warden. On this foundation, one covert scheme for joint power control and relay selection has been proposed. Subsequently, we derive the detection capabilities at warden, and the effective covert rate (ECR) of link from UAV to user. Furthermore, a power optimization problem is designed to maximize ECR with covertness constraint. Finally, numerical results are presented to verify the achievable covert performance of system and prove the effectiveness of the proposed scheme.

Feature shifts between data sources are present in many applications involving healthcare, biomedical, socioeconomic, financial, survey, and multi-sensor data, among others, where unharmonized heterogeneous data sources, noisy data measurements, or inconsistent processing and standardization pipelines can lead to erroneous features. Localizing shifted features is important to address the underlying cause of the shift and correct or filter the data to avoid degrading downstream analysis. While many techniques can detect distribution shifts, localizing the features originating them is still challenging, with current solutions being either inaccurate or not scalable to large and high-dimensional datasets. In this work, we introduce the Feature Shift Localization Network (FSL-Net), a neural network that can localize feature shifts in large and high-dimensional datasets in a fast and accurate manner. The network, trained with a large number of datasets, learns to extract the statistical properties of the datasets and can localize feature shifts from previously unseen datasets and shifts without the need for re-training. The code and ready-to-use trained model are available at \url{https://github.com/AI-sandbox/FSL-Net}.

With the continuous and fast-changing land-scape in communication networks and artificial intelligence (AI), the researchers are interested in expedited standardization and realization of 6G networks. Federated learning (FL) is one of the paradigms that allows the 6G networks to support a diverse range of devices. Very few studies address the problem of flexibility and heterogeneity for AI network architectures in FL paradigm, that could be a potential key changer for standardization and realization of 6G networks. However, they either consider width-only or depth-only to provide flexibility support. Furthermore, the existing studies do not address the problem of weight scale variation while performing the global model aggregation at the server side. In this regard, we propose flexible federated learning (FLEXFL) for the support of heterogeneous AI network architectures in 6G communication systems. The proposed network not only considers the width but also the depth of the network architecture to make it compliant with the global model aggregation. We also address weight scale variation (WSV) while updating the global model with weight normalization, which is one of the problems associated with existing studies. We perform experimental analysis on two publicly available datasets and a few network architectures to show the efficacy of the proposed approach. The results reveal that the FLEXFL outperforms existing state-of-the-art works in both the IID and non-IID settings, accordingly.

Abstract This research involved designing and building an interactive generative AI application to conduct a comparative analysis of two advanced Large Language Models (LLMs), GPT‐4, and Claude 2, using Langsmith evaluation tools. The project was developed to explore the potential of LLMs in facilitating postgraduate course recommendations within a simulated environment at Munster Technological University (MTU). Designed for comparative analysis, the application enables testing of GPT‐4 and Claude 2 and can be hosted flexibly on either Amazon Web Services (AWS) or Azure. It utilizes advanced natural language processing and retrieval‐augmented generation (RAG) techniques to process proprietary data tailored to postgraduate needs. A key component of this research was the rigorous assessment of the LLMs using the Langsmith evaluation tool against both customized and standard benchmarks. The evaluation focused on metrics such as bias, safety, accuracy, cost, robustness, and latency. Additionally, adaptability covering critical features like language translation and internet access, was independently researched since the Langsmith tool does not evaluate this metric. This ensures a holistic assessment of the LLM's capabilities.

With the rapid growth of Internet-of-Things (IoT) devices and unmanned agents (UAs), there is a rising need for energy- and spectrum-efficient wireless networks that can support large-scale, resource-constrained deployments. To meet this demand, integration of deep reinforcement learning (DRL), non-orthogonal multiple access (NOMA), and energy harvesting (EH) offers a promising approach to enhance energy efficiency (EE) and spectrum utilization in future sixth-generation (6G) networks, particularly for sustainable Internet of UA (IUA) communications. In this paper, we investigate an IUA network where multiple low-power secondary users (SUs), equipped with radio frequency energy harvesting (RF-EH) antennas, use a cognitive radio NOMA (CR-NOMA) scheme to share uplink channels with nearby primary users (PUs). We formulate a joint transmit power control and EH scheduling problem to maximize the long-term EE of the SUs and spectrum utilization of the network, subject to quality-of-service (QoS) constraints. To address the decentralized nature of the problem, we model the environment as a multi-agent system where each SU independently optimizes its transmission and EH strategies. A range of DRL and non-DRL algorithms is then applied to solve this optimization problem. We also explore different RF-EH diversity combining techniques to further boost system performance. Simulation results highlight the impact of these techniques on EE of SU, offering insights for optimizing performance under dynamic EH conditions.

Deploying large-scale foundation models (FMs) in resource-constrained devices presents critical challenges due to their substantial computational and memory requirements. This is particularly relevant for multi-task wireless sensing FMs running on sensors. To overcome these limitations, we propose a tiny federated wireless foundation model (WFM) framework that combines spectrogram-guided structured block-wise pruning with federated learning (FL) for efficient on-device deployment. Our approach prunes non-essential encoder blocks in vision transformers (ViTs) by leveraging the masked spectrogram modeling (MSM) pretraining loss as an importance indicator, ensuring only the most structurally significant components are retained. This enables federated adaptation with frozen backbones and lightweight, task-specific heads, minimizing both computational burden and communication overhead. The pruning strategy preserves the integrity of spectrogram reconstruction, while federated fine-tuning supports decentralized learning across clients with heterogeneous data distributions. Experimental results on human activity sensing and radio signal identification tasks confirm the efficacy of our approach. Specifically, the pruned ViT-based WFMs achieve up to 93% multiply-accumulate operations (MACs) reduction, 85% lower CPU inference time, and 49% reduction in communication overhead, all while maintaining high task accuracy. Our method demonstrates strong generalization and robustness across varying pruning ratios and data heterogeneity levels, while substantially reducing communication overhead, making it highly suitable for real-world industrial IoT deployments.

Age of information (AoI) is a critical metric for ensuring data freshness in carbon-intelligent and energy-efficient industrial Internet-of-things (IIoT) networks. We consider a user-specific sensing framework operating in a time division duplexing (TDD)–based IIoT network, consisting of energy harvesting (EH) sensors, users, and a cache-enabled edge node. The proposed framework aims to minimize AoI during data transmission to users while addressing the sensors’ energy constraints. For the uplink transmission of data from sensors to edge node, a quality-of-service-aware cognitive-radio non-orthogonal multiple access (CR-NOMA) is employed to enhance spectrum efficiency and minimize cache AoI. During the downlink transmission, upon user’s request, the edge node dynamically decides whether to retrieve cached data or request a fresh update from the sensors. This decision-making process is driven by reinforcement learning (RL) using a Q-table-based approach, where the edge node infers sensor battery levels from received updates and prioritizes user requests accordingly. We formulate this problem as a Markov decision process (MDP) and define an optimal policy that strikes a balance between minimizing AoI and adhering to energy constraints. To achieve this, we develop RL-based solutions, including Q-learning and deep Q-networks (DQN). Extensive simulations demonstrate that our approach achieves up to 90% AoI reduction while significantly improving energy efficiency, making it well-suited for real-time, delay-sensitive applications in modern IIoT networks.

Social media has become integral to minors’ daily lives and is used for various purposes, such as making friends, exploring shared interests, and engaging in educational activities. However, the increase in screen time has also led to heightened challenges, including cyberbullying, online grooming, and exploitations posed by malicious actors. Traditional content moderation techniques have proven ineffective against exploiters’ evolving tactics. To address these growing challenges, we propose the EdgeAIGuard content moderation approach that is designed to protect minors from online grooming and various forms of digital exploitation. The proposed method comprises a multi-agent architecture deployed strategically at the network edge to enable rapid detection with low latency and prevent harmful content targeting minors. The experimental results show the proposed method is significantly more effective than the existing approaches.

Autonomous vehicle (AV) usage has become predominant in the rapidly evolving landscape of urban transportation. Integrating AVs and non-AVs in the existing traffic infrastructure has significantly increased the complexity of traffic patterns. This research work primes the enhanced Traffic Management System (e-TMS), a solution implemented to expedite emergency vehicle (EV) travel in the context of connected AVs (CAVs) and ensured secured communication employing public key infrastructure (PKI) among the Internet of Vehicles (IoV) framework. When an EV is detected, the IoV system verifies the EV’s signal using PKI, ensuring its authenticity and integrity by encrypting the communication between the EV and road side units (RSUs). Further, the e-TMS activates the platooning process where CAVs in the EV’s lane shift to the adjacent lanes and dynamically form platoons to create a dedicated lane for the EV. To further optimize the platooning process, an adaptive smart leader selection (ASLS) algorithm is employed to select a leader vehicle spontaneously among the AVs based on the proximity to the EV, communication reliability, and lane position. Radio Detection and Ranging devices aid this platooning process by providing distance and target velocity, which are needed to maintain the required distance between the AVs and ensure safe platoon formation. The e-TMS enhances EV response times and overall traffic flow efficiency and resulted in 27.8% increase in mean speed compared to the traditional methods.

Establishing reliable communication networks in post-disaster environments is essential for effective emergency response. Deploying Unmanned Aerial Vehicles (UAVs) equipped with base stations provides a rapid and promising solution for restoring connectivity. However, onboard path planning is computationally expensive due to the constantly varying terrain, and precomputing paths for all locations is impractical. We propose WAPPOS (Waypoint Assisted Path Planning for Off-board Systems), a data and knowledge-driven framework that optimizes UAV path planning through distributed off-board processing. WAPPOS integrates satellite imagery from Google Earth into its Target Region Mapping module, which employs the DeepLabV3+ model to segment buildings into No-Fly Zones (NFZs) and Fly Zones (FZs) with 92.2% accuracy. To further refine navigation, WAPPOS introduces DBSCAN-PP (Density-Based Spatial Clustering of Applications with Noise for Path Planning). This novel clustering algorithm identifies optimal waypoints by analyzing spatial patterns and building density, which are then transmitted to the UAV for adaptive navigation. A comparative study with onboard Deep Reinforcement Learning (DRL)-based path planning demonstrated that WAPPOS reduced CPU, GPU & Battery usage significantly and extended flight time by 4.4 minutes. By leveraging off-board computation, data-driven segmentation, and knowledge-driven clustering, WAPPOS reduces onboard computation, improves flight efficiency, and enhances UAV-based network deployment in disaster-stricken regions.

An efficient traffic light control system (TLCS) is an integral part of monitoring the flow of autonomous vehicles (AVs) through road junctions. Existing TLCS systems have limitations, focusing on specific scenarios like emergency vehicles or considering only the queue length at intersections. Furthermore, the absence of privacy protection in these systems exposes vehicles to potential tracking risks. We propose an intuitive and privacy-preserving TLCS (IPTLCS) to improve the performance of the TLCS for multiple traffic scenarios and prevent tracking of vehicles at traffic signals. The proposed IPTLCS uses a deep Q-learning (DQN) algorithm based on the quantity versus priority concept, adaptive to all scenarios, including pedestrians and emergency vehicles, making the framework applicable to real-time situations. Further, we propose a novel anonymity preserving protocol (APP) to protect the privacy of vehicles using two-party computation (2PC) that can prevent the tracking of AVs in our environment. Extensive experimental studies of the IPTLCS reveal that the model can achieve a reduced waiting time of 3.45 s/vehicle, a queue length of 3.32 vehicles/lane, a run time of 0.002 s, and a communication overhead of 3 KB. The increase in the efficiency of the proposed IPTLCS model in comparison with existing models in terms of waiting time, queue length, run time, and communication overhead is 11.08%–43.25%, 2.35%–24.23%, 33.3%–65.5%, and 38.77%–54.38%, respectively. Impact Statement The infusion of deep learning (DL) methodologies into traffic light systems signifies a substantial leap in advancing the management of AVs on roadways. Confronting the limitations of current traffic light systems, especially in adapting to diverse scenarios with varying quantities and priorities of vehicles, this study introduces a framework for efficient AV navigation that minimizes traffic collisions with reduced delays. Incorporating the proposed privacy measures ensures vehicular data protection, enhancing the overall system’s safety. Results demonstrate that the proposed method addresses the secure management of vehicular data and achieves reduced processing times, paving the way for progressing more intelligent and secure urban mobility solutions and fostering a seamless coexistence between AVs and pedestrians.

Post COVID-19 and recent advancement in terms of language models, researchers have shown a lot of interest in analyzing social media posts for analyzing mental state of the users. Social media platforms are the epitome of sharing individual thoughts and feelings through textual posts and linguistic cues. Therefore, the textual modality from social media posts can be leveraged for detecting early signs of stress, depression or other mental health conditions, accordingly. Existing methods mainly focus on the feature engineering, shallow learning, and employing of deep learning architectures to improve the mental state recognition performance. Seldom the study uses an established knowledge-base that is available to model mentalization and emotional aspect to improving the depression and stress recognition. In this regard, we propose emotion aware contrastive networks (EAC-net) that leverages the existing knowledge-base and propose some new ones to model the emotional and mentalization aspect in order to improve the recognition of stress and depression state from textual posts. Furthermore, we propose a feature-level fusion and weighting mechanism using gated recurrent units (GRUs) and self-attention layers to weight and select the important features. Last, the EAC-Net uses a supervised contrastive learning strategy to train the network. The proposed method is evaluated on four publicly available datasets. Experimental results reveal that the EAC-Net achieves state-of-the-art results by outperforming baselines and existing methods by atleast 1.86%, 0.72%, 3.43%, and 3.64% on four publicly available datasets using F1-measure as the evaluation metric.

This paper explores the potential of aerial reconfigurable intelligent surfaces (ARIS) to enhance coordinated multipoint non-orthogonal multiple access (CoMP-NOMA) networks. We consider a system model where a UAV-mounted RIS assists in serving multiple users through NOMA while coordinating with multiple base stations. The optimization of UAV trajectory, RIS phase shifts, and NOMA power control constitutes a complex problem due to the hybrid nature of the parameters, involving both continuous and discrete values. To tackle this challenge, we propose a novel framework utilizing the multi-output proximal policy optimization (MO-PPO) algorithm. MO-PPO effectively handles the diverse nature of these optimization parameters, and through extensive simulations, we demonstrate its effectiveness in achieving near-optimal performance and adapting to dynamic environments. Our findings highlight the benefits of integrating ARIS in CoMP-NOMA networks for improved spectral efficiency and coverage in future wireless networks.

Unmanned Aerial Vehicles (UAVs) provide a good base platform for dynamic vision-based target detection. The detection process can be enhanced by utilizing multiple UAVs. In such scenarios, precise trajectory planning is essential to achieve objectives while avoiding collisions with obstacles. Furthermore, in most cases, Air-to-Air (A2A) detection of micro-UAVs in large-scale environments is challenging due to their dynamic movements and other complex parameters, such as poor light, motion blur, and occlusion. To solve these challenges, developing an algorithm that can adapt the control strategy based on changing system and environmental parameters is essential. This paper proposes an Adaptive Model Predictive Control (AMPC)-driven hybrid GANYOLOX framework to mitigate these navigation and detection challenges. The proposed AMPC allows model updates during multi-UAV operations, which enables estimation techniques to predict changes in the system model and helps to compute the target UAV position. Alternatively, the framework constructs a hybrid GAN-YOLOX model to overcome various A2A detection challenges. Extensive comparative analysis of the hybrid GANYOLOX framework achieved 94% detection accuracy and out-performed existing DL frameworks by 8%.

Autonomous Vehicles (AVs) have revolutionized transportation by utilizing 6G technologies such as automated driving assistance, navigation, connected intelligence, and independent decision-making. Yet, the increasing reliance on AVs exposes the Internet of Vehicles (IoV) to potential vulnerabilities, making it susceptible to cyber attacks. One prominent threat is Distributed Denial of Service (DDoS) attacks, which can significantly impact AVs' safety and operational integrity. DDoS attacks directly disrupt the fundamental functionality of AVs to make timely and informed decisions, potentially leading to accidents or system failures. Despite the existence of numerous systems for detecting DDoS attacks, their continuous evolution in various attack patterns poses a significant challenge for effective detection. This paper provides a vision of 6G Security by proposing an Advanced DDoS Attack Detection System (ADADS) to enhance the detection capabilities of DDoS attacks by employing a Hybrid Detection Model (HDM) and a Continuous Learning Model (CLM) to adapt the evolving patterns of DDoS attacks over time dynamically. The collaborative integration of these models leverages the overall efficiency of DDoS attack detection, delivering a robust and adaptive defense mechanism. The experimental findings reveal that the proposed ADADS achieves a remarkable accuracy 98.7% with rapid stabilization in a few iterations for the current 6G specifications and applications.

In autonomous vehicle navigation, the effectiveness and robustness of object detection models are directly influenced by the quality, quantity, and diversity of data. Detecting Vul-nerable Road Users (VRU) poses significant challenges due to their constant motion and dynamic behaviors. Utilizing real-time datasets like KITTI for training VRU detection models may not be optimal, as they lack coverage of adversarial situations and undervalue objects like pedestrians. Relying solely on such datasets for model training can lead to catastrophic real-world results. To address these issues, we present PointGAN, a framework supporting 3D object detection models that leverage conditional Generative Adversarial Networks (cGAN) to enhance dataset diversity specifically for the pedestrian class. PointGAN employs generative neural networks trained through multiple iterations to generate realistic point cloud data, guided by feedback from the discriminator until it closely mirrors real-world data. This strategy intends to significantly improve the overall performance of 3D object detection models by skillfully detecting pedestrians in challenging and diverse scenarios. The generative model achieves a Minimum Matching Distance - Earth Mover's Distance (MMD-EMD) score of 0.025, outperforming the existing state-of-the-art models trained under different categories.

Intelligent reflecting surfaces (IRSs) have been considered to revolutionize beyond 5G and 6G systems as they help increase signal strength through their ability to control radio environments effectively. Introducing IRS assistance in a single-input single-output (SISO) network has been proven to improve the system's performance. This paper compares the performance of a single IRS-assisted SISO system against a double IRS-assisted system under various wireless network setups. Our work relies on a shared allocation scheme of IRS elements, where a practical phase-dependent amplitude phase shift model is utilized along with discrete phase shifts to develop a reliable and energy-efficient system. We observe energy efficiency while altering system parameters to identify the limits where each system works better. The simulation results show that two IRSs perform better at large deployments, whereas a single IRS performs better in compact environments.

In past, due to data and model security concerns, modern communication systems mainly focus on the use of edge computing devices for enabling immersive applications and services. Federated learning is one of the preferred solutions but it stresses the computation capability of the edge devices for immersive applications. Much research is now focusing on split learning as an alternative due to its ability of performing joint training with limited computing resources. However, split learning is also vulnerable to data reconstruction, feature space hijacking, and model inversion attacks, which are quite common concerning immersive applications such as Metaverse. In this regard, we propose a ZEro-Trust Attack (ZETA) framework for data reconstruction and model inversion attacks for autonomous vehicles opting for split learning strategies. We propose the joint training of client, server, and shadow models for both the reconstruction and main task to fool existing methods. Our experimental results demonstrate that the proposed method is capable of reconstructing client's data with an error of 0.0032. This study is proposed as a basis to design more sophisticated defense mechanisms for autonomous vehicles to protect user services in 5G/6G networks.

Artificial Intelligence of Medical Things (AIoMT) requires storing, preprocessing, monitoring, and analytics of large-scale sensor data fusion in the cloud. However, migrating to the cloud possesses intrinsic issues of cost, performance constraints, and sustainable computing. This research explores the potential of AIoMT in crafting intelligent models for daily activity patterns and predicting unusual occurrences. It delves into power-efficient and sustainable computing tailored for the IoT sensors, methods, and systems geared toward crafting digitally enhanced smart homes for the elderly. Fusion data is collected from heterogenous sensors to track daily patterns and processed for anomaly detection and alert generation. The AIoMT model has employed the time and energy minimization scheduler (TEMS) algorithm, which considers energy consumption, processing duration, data transmission expenses, and standby device power consumption. This enables local computing in the IoMT systems, mobile edge servers, and cloud controllers, promoting sustainability in healthcare. To optimize execution time and cost-effectiveness, task scheduling options include local Internet of Things devices, cloud infrastructure, and multiaccess edge computing (MEC). This approach could benefit digitally enhanced communities significantly, promoting low-carbon, power-efficient, sustainable computing (LCPESC). The LCPESC AIoMT approach demonstrates precision close to a 95% confidence level. Further, the proposed model is extended beyond individual households to encompass digitally augmented communities.

This study aims to present a comparative analysis of existing waveforms for integrated sensing and communication (ISAC) in vehicular environments. A novel multicarrier framework called generalized adaptive spreading modulation (GASM) is proposed for ISAC-enabled vehicular environments. The GASM waveform offers symbol spreading in both time and frequency domains with tunable spreading parameters, which allows the proposed GASM-based waveform to adapt according to the rapid time-frequency variations of the fading channel. This helps to combat the most common system impairments, such as carrier frequency offset (CFO) and symbol timing offset (STO). The GASM scheme is the generalization of various existing waveforms, such as orthogonal frequency-division multiplexing (OFDM), fractional Fourier transform-based OFDM (FrFT-based OFDM), and orthogonal chirp division multiplexing (OCDM). The proposed GASM-based ISAC system is evaluated in terms of average bit error rate (ABER) for the communication and ambiguity function (AF) for sensing capabilities. The performance of the GASM-based ISAC system is found superior as compared to the existing waveforms, i.e., OFDM, FrFT-based OFDM, OCDM, generalized frequency division multiplexing (GFDM), and orthogonal time frequency space (OTFS) modulation.

In recent years, the cloud infrastructure has been developed as a promising sharing system for the Internet of Vehicles (IoV) communication. During the information exchange, search service over ciphertext called searchable encryption (SE) is an extraordinary method to prevent data breaches. However, two open problems still need to be solved for ranked search, which hinders the application practicality in IoV. First, each data owner must store the extra information to distribute weight values dynamically. Second, ranking in the cloud has not been supported by most existing schemes. In this article, to address the above problems and fit the characteristics of real-time data exchange in IoV, we present a multikeyword-ranked search scheme supporting extreme environments for the IoV. Specifically, our system designs a unique encrypted index tree structure to realize the multikeyword-ranked retrieval, the weight value dynamic adaptive calculation, and dynamic updating in IoV. Moreover, we use a primary–secondary dual-server model to cope with extreme environments and propose a “greedy breadth-first search” algorithm to achieve an effective sublinear search. Finally, comprehensive security analysis and experimental simulation for the proposed system prove that our system can guarantee user privacy and acceptable efficiency.

Industry 5.0 vision, a step toward the next industrial revolution and enhancement to Industry 4.0, conceives the new goals of resilient, sustainable, and human-centric approaches in diverse emerging applications such as factories-of-the-future and digital society. The vision seeks to leverage human intelligence and creativity in nexus with intelligent, efficient, and reliable cognitive collaborating robots (cobots) to achieve zero waste, zero-defect, and mass customization-based manufacturing solutions. However, it requires merging distinctive cyber–physical worlds through intelligent orchestration of various technological enablers, e.g., cognitive cobots, human-centric artificial intelligence (AI), cyber–physical systems, digital twins, hyperconverged data storage and computing, communication infrastructure, and others. In this regard, the convergence of the emerging computational intelligence (CI) paradigm and softwarized next-generation wireless networks (NGWNs) can fulfill the stringent communication and computation requirements of the technological enablers of the Industry 5.0, which is the aim of this survey. In this article, we address this issue by reviewing and analyzing current emerging concepts and technologies, e.g., CI tools and frameworks, network-in-box architecture, open radio access networks, softwarized service architectures, potential enabling services, and others, elemental and holistic for designing the objectives of CI-NGWNs to fulfill the Industry 5.0 vision requirements. Furthermore, we outline and discuss ongoing initiatives, demos, and frameworks linked to Industry 5.0. Finally, we provide a list of lessons learned from our detailed review, research challenges, and open issues that should be addressed in CI-NGWNs to realize Industry 5.0.

The Industrial Internet of Things (IIoT) has been introduced in an era of increasingly broad potentials in the medical industry. In recent years, IIoT-based healthcare applications have grown in popularity, with the majority of them relying on Wireless Body Area Network (WBAN) for flexibility. There have been a few recent works that have investigated SDN-based fog architecture for constructing smart healthcare systems. However, the best fog node from the fog layer must be identified and limit the transmission of unnecessary data. To address this issue, the Intelligent Software-defined Fog Architecture (i-Health) is developed in this work. Based on the prior data pattern of each patient, the controller will decide whether to send the data to the fog layer. Furthermore, we introduced the Fog Ranking Service (FRS) and Fog Probing Service (FPS) to select the best fog node. The performance comparison reveals that the proposed i-Health outperforms existing benchmark approaches.

The concept of the metaverse, first introduced in science fiction, is rapidly becoming a technological reality with profound implications for various sectors, including healthcare. By merging virtual reality (VR), augmented reality (AR), artificial intelligence (AI), and advanced communication technologies, the metaverse promises to create immersive, interactive environments that can transform medical practice, education, and patient care [1].

Real-time healthcare indicates monitoring people's health status in a timely manner. In this regard, wireless techniques can be used to provide immediate access to bio-sensing information, facilitating monitoring and instant communication between healthcare providers [1]. Such a scheme aims to realize real-time decision-making and intervention, improving patient outcomes and efficiency in healthcare delivery.

In this paper, we investigate the reconfigurable intelligent surface (RIS)-assisted non-orthogonal multiple access-based backscatter communication (BAC-NOMA) system under Nakagami-m fading channels and element-splitting protocol. To evaluate the system performance, we first approximate the composite channel gain, i.e., the product of the forward and backscatter channel gains, as a Gamma random variable via the central limit theorem (CLT) and method of moments (MoM). Then, by leveraging the obtained results, we derive the closed-form expressions for the ergodic rates of the strong and weak backscatter nodes (BNs). To provide further insights, we conduct the asymptotic analysis in the high signal-to-noise ratio (SNR) regime. Our numerical results show an excellent correlation with the simulation results, validating our analysis, and demonstrate that the desired system performance can be achieved by adjusting the power reflection and element-splitting coefficients. Moreover, the results reveal the significant performance gain of the RIS-assisted BAC-NOMA system over the conventional BAC-NOMA system.

The fifth generation (5G) networks are designed to support a large range of diverse services with strict performance requirements. Studies suggest that, 5G uses machine learning technologies for variety of tasks ranging from network management, and resource optimization to automated services. The successful integration of 5G with machine learning has also led to the basis for 6G networks. However, the use of machine learning makes the 5G networks susceptible to adversarial attacks. A few works study the effect of differential privacy and adversarial attacks in the 5G systems let alone to provide the proposal of effective defense mechanism. This study proposes Denoising and Adversarial attack-based STacked AutoeNcoder (DASTAN) convolutional neural networks (CNN) to provide defense against a specific differential privacy attack, i.e. membership inference, optimized to detect the device or data distribution potentially used in the training process. DASTAN initiates an intentional attack to camouflage the characteristics of an authorized user from an adversary and uses a de noising stacked autoencoder to recover the information at service provider's end for RF fingerprinting. The aim of RF fingerprinting is to validate the authenticity and identity of the device to preserve the privacy of wireless network. Experimental results demonstrate the efficacy of DASTAN-CNN, which reduces the attack success rate by up to 52.69% in comparison to the case where no defense strategy is employed. The DASTAN-CNN also achieves 75.29% authorized user recognition rate for RF fingerprinting while reducing the attack success rate to 39.23%, which shows the effectiveness in terms of trade-off efficiency.

Recently, Unmanned Aerial Vehicles (UAVs) have been deployed in various logistics and surveillance applications. Sixth-Generation (6G) cellular networks can further enhance communications to provide ubiquitous coverage, low-latency control, and seamless connectivity among the UAVs. However, achieving constant and end-to-end 3D coverage for user devices is demanding. UAV s have limited battery capacity; thus, energy consumption should be efficiently managed. Optimizing the UAV trajectories improves network performance by diminishing Base Station (BS) load or covering areas with limited radio access. Hence, we propose a Swarm Clustering and Double-Deep-Q-Network (SC-DDQN) framework for efficient communication in aerial networks. The framework constitutes a novel SC- Particle Swarm Optimization (SC-PSO) to improve intra-UAV communication and an Intelligent Trajectory Optimization (ITO) sub-component to optimize Air-to-Ground (A2G) trajectories. The results show that the proposed SC-DDQN framework achieves 40 % faster clustering and a 1.2 % failure probability of reaching a destination compared to the conventional systems, thus providing optimal clustering and trajectory for UAV communications.

This study presents an analysis of the bit error rate (BER) and system capacity in a multi-user multiple-input multiple-output (MU-MIMO) wireless system that deploys or-thogonal frequency-division multiplexing (OFDM) for wideband communication in industrial Internet-of- Things (IIoT) networks. The focus is on analyzing and evaluating the impact of imperfect channel state information (CSI) on MU-MIMO-OFDM system performance in comparison to perfect CSI within industrial settings. For this, we consider an IIoT network consisting of a base station (BS) and multiple IIoT devices, each equipped with multiple antennas. The CSI is computed using the least squares (LS) estimation technique. Furthermore, we investigate the tradeoff between system capacity and BER performance, considering various MIMO configurations to determine an optimal setup. The simulation results demonstrate that both imperfect CSI and MIMO configurations significantly influence BER performance. The findings of this research could provide valuable insights for the design and optimization of MU-MIMO-OFDM-based IIoT networks.

The applications concerning vehicular networks benefit from the vision of beyond 5G and 6G technologies such as ultra-dense network topologies, low latency, and high data rates. Vehicular networks have always faced data privacy preservation concerns, which lead to the advent of distributed learning techniques such as federated learning. Although federated learning has solved data privacy preservation issues to some extent, the technique is quite vulnerable to model inversion and model poisoning attacks. We assume that the design of defense mechanism and attacks are two sides of the same coin. Designing a method to reduce vulnerability requires the attack to be effective and challenging with real-world implications. In this work, we propose simulated poisoning and inversion network (SPIN) that leverages the optimization approach for reconstructing data from a differential model trained by a vehicular node and intercepted when transmitted to roadside unit (RSU). We then train a generative adversarial network (GAN) to improve the generation of data with each passing round and global update from the RSU, accordingly. Evaluation results show the qualitative and quantitative effectiveness of the proposed approach. The attack initiated by SPIN can reduce up to 22% accuracy on publicly available datasets while just using a single attacker. We assume that revealing the simulation of such attacks would help us find its defense mechanism in an effective manner.

Internet of Things (IoT) has led to significant advancements in communication technologies, specifically, concerning IoT-based sustainable information systems. Lately, industry-academic communities have made great strides for the development of security in IoT-based applications, such as traffic management, industrial automation systems, military surveillance systems, transportation, parking, etc. The sustainable IoT converges AI and blockchain technologies for enhancing quality of individual’s life. As a result, emerging IoT applications operate a distributed ledger technology to provide robust-level of encryption and execution for contractual agreement that resolves interoperability and security issues. Thus, this article proposes a blockchain-based remote mutual authentication (B-RMA) that considers smart devices and cloud networks to offer security and privacy. The proposed B-RMA can coexist with the IoT-based smart environment to decentralize the processing of user authentication requests. The prominence of the proposed strategies including security efficiency and privacy protection, is evaluated using informal security analysis. Moreover, a runtime platform “Node.js” was used to analyze the communication metrics, such as execution time, throughput, and overhead ratio, over the concurrent requests. The investigation results prove that the B-RMA achieves a scalable environment, accordingly.

COVID-19 is not the last virus; there would be many others viruses we may face in the future. We already witnessed the loss of economy and daily life through the lockdown. In addition, vaccine, medication, and treatment strategies take clinical trials, so there is a need to tracking and tracing approach. Suitably, exhibiting and computing social evolution is critical for refining the epidemic, but maybe crippled by location data ineptitude of inaccessibility. It is complex and time consuming to identify and detect the chain of virus spread from one person to another through the terabytes of spatiotemporal GPS data. The proposed research aims an HPE edge line computing and big data analytic supported virus outbreak tracing and tracking approach that consumes terabytes of spatiotemporal data. The proposed STRENUOUS system discovers the prospect of applying an individual’s mobility to label mobility streams and forecast a virus-like COVID-19 epidemic transmission. The method and the mechanical assembly further contained an alert component to demonstrate a suspected case if there was a potential exposure with the confirmed subject. The proposed system tracks location data related to a suspected subject in the confirmed subject route, where the location data expresses one or more geographic locations of each user over a period. It recognizes a subcategory of the suspected subject who is expected to transmit a contagion based on the location data. System measure an exposure level of a carrier to the infection based on contaminated location data and a subset of carriers connected with the second location carrier. They investigated whether the people in the confirmed subject’s cross-path can be infected and suggest quarantine followed by testing. The proposed STRENUOUS system produces a report specifying that the people have been exposed to the virus.

Fault diagnostics involving the Internet-of-Things (IoT) sensors and edge devices is a challenging task due to their limited energy and computational capabilities. Another challenge concerning IoT sensors or devices is the incursion of noise when used in an industrial environment. The noisy samples affect the decision support system that could lead to financial and operational losses. This article proposes a noisy encoder using artificial intelligence of things (NEAT) architecture for fault diagnosis in IoT edge devices. NEAT combines autoencoders and Inception module to co-train the clean and noisy samples for solving the said problem. Experimental results on benchmark data sets reveal that the NEAT architecture is noise resilient in comparison to the existing works. Furthermore, we also show that the NEAT architecture has lightweight characteristics as it yields a lower number of parameters, weight storage, training, and testing times that support its real-life applicability in an Industrial IoT environment.

The dynamic property and increasing complexity are the key challenges for modeling financial technology (FinTech)-related applications such as stock markets. Over the years, a lot of inflexible predictive strategies have been proposed for predicting stock price movements that failed to achieve satisfactory results especially when a market crash occurs. To cope with this challenge, we propose a prediction framework based on an adversarial training strategy using reinforcement learning for the said FinTech application. The framework uses a heterogeneous knowledge base, including stock prices, tweets, and global indicators. We propose a modified newton-divided difference polynomial (NDDP) for missing data imputation. The informative patterns representing the intrinsic characteristics of financial markets were extracted using long short-term memory networks (LSTM). The two adversarial networks are heterogeneous data fusion representing market crash (HDFM)$Q$-learning and confrontational$Q$-learning network. Both networks are trained in an adversarial fashion to increase the effectiveness of prediction even when the financial market is volatile. The experimental results show the importance of global indicators and the proposed adversarial learning network (ALN) for improving the predictive performance in comparison with the existing state-of-the-art works.

Autonomous electric vehicles (AEVs) are revolutionizing the world of smart city transportation due to their low-resource consumption, improved traffic efficiency, zero carbon emissions, and improved road safety. To ensure the safe passage of vehicles through a complex environment, it is essential to plan for safe and smart navigation and energy management for AEVs. This demands an effective model for locating the optimal electric charging stations (ECSs) for scheduling and recharging the AEVs when they run on low battery. Many research works, however, do not focus on navigation and scheduling policies for AEV charging that would occur in extreme events in complex environments. This article puts forth a collaborative optimal navigation and charge planning (CONCP) framework based on multiagent deep reinforcement learning (MADRL). To ensure the safe passage of vehicles through the complex environment, it is essential to plan for safe and smart navigation and energy management for AEVs. The CONCP framework aims to achieve the best route from the origin to the final destination for each AEV, scheduling the optimal ECS while avoiding obstacles, reducing traffic congestion, and maximizing energy efficiency, accordingly. The experimental results indicate that CONCP achieves 27% higher success rates, 31% fewer collision rates, and 37% higher reward per episode than the other state-of-the-art algorithms.

Multimodal medical images are widely used by clinicians and physicians to analyze and retrieve complementary information from high-resolution images in a non-invasive manner. Loss of corresponding image resolution adversely affects the overall performance of medical image interpretation. Deep learning-based single image super resolution (SISR) algorithms have revolutionized the overall diagnosis framework by continually improving the architectural components and training strategies associated with convolutional neural networks (CNN) on low-resolution images. However, existing work lacks in two ways: i) the SR output produced exhibits poor texture details, and often produce blurred edges, ii) most of the models have been developed for a single modality, hence, require modification to adapt to a new one. This work addresses (i) by proposing generative adversarial network (GAN) with deep multi-attention modules to learn high-frequency information from low-frequency data. Existing approaches based on the GAN have yielded good SR results; however, the texture details of their SR output have been experimentally confirmed to be deficient for medical images particularly. The integration of wavelet transform (WT) and GANs in our proposed SR model addresses the aforementioned limitation concerning textons. While the WT divides the LR image into multiple frequency bands, the transferred GAN uses multi-attention and upsample blocks to predict high-frequency components. Additionally, we present a learning method for training domain-specific classifiers as perceptual loss functions. Using a combination of multi-attention GAN loss and a perceptual loss function results in an efficient and reliable performance. Applying the same model for medical images from diverse modalities is challenging, our work addresses (ii) by training and performing on several modalities via transfer learning. Using two medical datasets, we validate our proposed SR network against existing state-of-the-art approaches and achieve promising results in terms of structural similarity index (SSIM) and peak signal-to-noise ratio (PSNR).

The advancement of sensory technologies proliferates the development of low-cost electronics systems to operate the environmental features of smart cities. Global urbanization integrates networking systems to offer computing-based practical solutions for improving the quality of application-oriented services. Few existing studies have primarily focused on a single-point vulnerability for decentralized IoT applications. However, very few mechanisms address the issues concerning privacy-preserving and trust-aware authentication for IoT-enabled industrial applications. Moreover, the existing schemes are in fact not applicable to real-time scenarios, such as decentralized networks and long-term evolution advanced networks. Thus, this article presents a trust-aware blockchain-based seamless authentication with privacy-preserving (TAB-SAPP) to resolve the critical things, such as privacy, security, and packet delivery ratio. In the proposed TAB-SAPP, a novel data traffic pattern is utilized using identity management to show that the proposed mechanism can be more functional in expanding users’ connectivity to improve the communication metrics, such as packet delivery ratio and mobility speed.

Falsified faces generated by DeepFake are severe threats to our community. Many smart systems in Industry 4.0, such as electronic payments and identity verification, rely on bioinformation authentication. These applications may compromise with forgeries generated by DeepFake. Notwithstanding many promising results on DeepFake forensics have been reported recently, we are now facing new security challenges brought by antiforensics attacks. With adversarial perturbations injected by antiforensics algorithms, falsified faces could masquerade themselves to disrupt forensics detectors as well as industrial applications. Therefore, to secure biometric data, in particular facial information, we propose a countermeasure against the attacks of DeepFake antiforensics. The proposed model features dual channels and multiple supervisors to capture biological attributes from manifold aspects. After training, the proposed method can purify antiforensics images by eliminating adversarial perturbations. With experimental evaluations, we show that purified faces are highly distinguishable from real ones. The proposed method is justified as a reliable defense tool for protecting facial bioinformation against antiforensics amid Industry 4.0.

The use of aerial base stations, AI cloud, and satellite storage can help manage location, traffic, and specific application-based services for vehicular social networks. However, sharing of such data makes the vehicular network vulnerable to data and privacy leakage. In this regard, this article proposes an efficient and secure data sharing scheme using community segmentation and a blockchain-based framework for vehicular social networks. The proposed work considers similarity matrices that employ the dynamics of structural similarity, modularity matrix, and data compatibility. These similarity matrices are then passed through stacked autoencoders that are trained to extract encoded embedding. A density-based clustering approach is then employed to find the community segments from the information distances between the encoded embeddings. A blockchain network based on the Hyperledger Fabric platform is also adopted to ensure data sharing security. Extensive experiments have been carried out to evaluate the proposed data-sharing framework in terms of the sum of squared error, sharing degree, time cost, computational complexity, throughput, and CPU utilization for proving its efficacy and applicability. The results show that the CSB framework achieves a higher degree of SD, lower computational complexity, and higher throughput.

Connected and Autonomous Vehicles (CAVs) enable various capabilities and functionalities like automated driving assistance, navigation and path planning, cruise control, independent decision making, and low-carbon transportation in the real-time environment. However, the increased CAVs usage renders the potential vulnerabilities in the Internet of Vehicles (IoV) environment, making it susceptible to cyberattacks. An Intrusion Detection System (IDS) is a technique to report network assaults by potential Autonomous Vehicles (AVs) without encryption and authorization procedures for internal and external vehicular communications. This paper proposes an Intelligent IDS (IIDS) to enhance intrusion detection and categorize malicious AVs using a modified Convolutional Neural Network (CNN) with hyperparameter optimization approaches for IoV systems. The proposed IIDS framework works in a 5G Vehicle-to-Everything (V2X) environment to effectively broadcast messages about malicious AVs. Thus IIDS aids in preventing collisions and chaos, enhancing safety monitoring in the traffic. The experimental results depict that the proposed IIDS achieves 98% accuracy in detecting attacks.

Internet of things (IoT) has emerged as a promising technology that can be widely used in various industries to realize real-time information collection, so as to improve production efficiency and reduce running costs. By combining the technology of IoT, maritime transportation systems (MTS) can prevent vessels collision, improve the efficiency of maritime transportation and reduce the loss of revenue for ports and shipbuilders. The large amount of real-time data generated in IoT-enabled MTS can be efficiently utilized to predict the future trajectories and hotspots of vessels on the sea combined with historical data. However, the maritime traffic data in MTS cannot be effectively processed in traditional big data analysis methods, and the integrity of it needs to be checked before being used to achieve the prediction of trajectories and high-density areas of vessels. In this paper, we propose a flexible data integrity checking scheme with original data recovery in IoT-enabled MTS. In the proposed scheme, the data blocks of vessels are encoded based on the technology of erasure coding. To ensure the availability of the historical data, the existence and the integrity of the data elements stored in the cloud can be checked. Moreover, the original data blocks can be recovered efficiently if the encoded data elements have been corrupted or deleted. Security analysis demonstrates that the proposed scheme can be proved to be correct and is secure against malicious attacks. Performance analysis shows that our scheme is more efficient than the previous schemes.

The immense growth of Autonomous Vehicles (AVs) and networking technologies have paved the way for advanced Intelligent Transportation Systems (ITS). AVs increase data demands from in-vehicle users, which pose a significant risk to the vehicular trajectory data and are extremely vulnerable to security threats. It is challenging to describe and detect the trajectory anomalies in urban motion behavior due to the enormous coverage and complexity of ITS in the V2X environment. Most existing systems rely on a restricted number of single detection strategies, such as determining frequent patterns and have limited accuracy in detecting anomalous trajectories. However, they focus only on outlier detection, failing to consider different patterns of anomalous trajectories. This paper proposes Efficient Trajectory Anomaly Detection and Classification (ETADC) framework in a 6G-V2X environment. The proposed ETADC framework employs the Deep Deterministic Policy Gradient algorithm (DDPG) to improve accuracy and efficiency by analyzing multiple strategies, namely driving speed, driving distance, driving direction, and driving time. The result analysis shows that the proposed ETADC technique outperforms the existing systems by 97% accuracy.

Unmanned Aerial Vehicles (UAVs), in conjunction with 6G, are a potential tool for monitoring agricultural lands and various agricultural applications. There have been several trajectory generation algorithms proposed for surveying agricultural land. However, in most situations, the accuracy of the trajectory is hampered by several factors, namely the complex geographical topography, performance, connectivity with the Ground Control Station (GCS) and positioning error of the UAV during flight, amongst others. Therefore, in this paper, we propose Drones Trajectory Generation employing an improved Genetic Algorithm (GA) and Non-Uniform Rational P-Splines (NURPS) based optimizer (DTG-GN). The improved GA utilizes a novel dual fitness function parameter to select an optimal path to map the weed-infested regions. The path chosen is often impeded by the high number of sudden turns, affecting the UAV’s speed profile and the path’s continuity. Therefore in the NURPS optimization, the computation of the intermediate knots vector between the control points improves the smoothness of the path. Furthermore, the accuracy of detecting the weed-infested area and the path length are employed to optimize the path. Besides, a 6G network is utilized for communicating the path between the GCS and the UAV to ensure seamless connectivity. Thus the time taken by DTG-GN to generate the optimal trajectory reduces by 38.815% for 50 control points. DTG-GN also reduces the average trajectory length by 45.67% for 50 control points, establishing its supremacy over conventional trajectory generation algorithms.

Intelligent Vehicle Systems (IVSs) devote to integrating the data sensing, processing, and transmission in the Vehicle to Everything (V2X) scenarios, where the Unnamed Aircraft Vehicle (UAV)-aided traffic monitoring network is one of the most significant applications. Moreover, since the central premise to support the IVS is timely and effectively sensing data processing, Age of Information (AoI) can precisely reflect the timeliness and effectiveness of the communication process in the UAV-aided traffic monitoring network. However, recent researches pay little attention to AoI minimization issue, especially when the malicious attacker attempts to deteriorate the network performance. The accurately modelling of the adversarial relationship between legitimate UAVs and attacker is not fully investigated. To make up this research gap, we start from the Stackelberg game viewpoint to investigate the AoI optimization problem in the UAV-aided traffic monitoring network under attack. Firstly, the system model and three-layer Stackelberg game-based optimization goal are established. Secondly, based on the Backward Induction (BI) analysis, the follower’s data sensing rate, transmission power, and the leader’s attacking power are determined by the Lagrange duality optimization technology successively. Moreover, the sub-gradient update-based optimization technology is used to achieve the Stackelberg Equilibrium (SE). Finally, simulations are performed under various parameters. The evaluation results present better performance of our proposed approach when compared with the typical baselines.

Cross-modal communications that incorporate audio-visual and tactile signals will bring a more holistic immersive experience to people. However, due to the different transmission requirements of these signals, it is a challenging task to rationalize the allocation of transmission resources. Therefore, this work proposes a joint transmission scheme to deal with the resource allocation problem of diverse signals. Network slicing and puncturing architecture are introduced in the scheme to achieve flexible resource allocation and reduce the wasting of resources. To reduce the negative impact of puncturing transmission on users, we construct the optimization problem related to transmission rate and reliability. This problem can realize the reasonable allocation of radio resources and meet the transmission requirements of the two types of signals. Next, we divide the optimization problem into two parts: video traffic resources allocation and tactile traffic puncturing resources allocation. To solve both of the problems, we leverage the channel matching (CM) algorithm and puncturing resource allocation (PRA) algorithm. In addition, we discuss the advantages and disadvantages of both ways to occupy puncturing resources, namely, occupy resources proportionally (ORP) and occupy resources blocks for transmission (ORB). Finally, the effectiveness of the proposed scheme is verified by comparing the excepted rate and resources loss ratio of system users with different schemes.

To efficiently and reliably obtain the target data, mobile crowdsensing (MCS) is widely used to provide the sensing data collection service. Currently, despite concerns of sensing network scale and mobility can be addressed to some degree in the MCS manner, the freshness and privacy goals of the sensing data are still not considered simultaneously. We combine the Age of Information (AoI) with security-enhanced technique to establish a novel MCS system, which can guarantee data freshness and security, respectively. Hence, the problem is formatted as a joint AoI optimization and privacy-preservation process. To solve this problem, we utilize game theory to achieve AoI-oriented spectrum access, and homomorphic encryption to encrypt communication data. Finally, security analysis and numerical results show that our proposed approach can effectively ensure the security level and improve the AoI performance at the same time in MCS.

Collaborative deep neural network (DNN) inference over edge and cloud is emerging as an effective approach for enabling several Internet of Things (IoT) applications. Edge devices are mainly resource-constrained and hence can not afford the computational complexity manifested by DNNs. Thereby, researchers have resorted to a collaborative computing approach, where a DNN is partitioned between edge and cloud. Recent art on DNN partitioning has either focused on bandwidth-specific partitioning or relied on offline benchmarking of DNN layers. However, edge devices are inherently heterogeneous and possess inconsistent levels and types of resources. Therefore, in this work, we propose a resource-aware partitioning of DNNs for accelerating collaborative inference over edge-cloud. The proposed approach provides the flexibility of partitioning a DNN with respect to the available nature and scale of resources for a certain edge device. Unlike state-of-the-art, we exploit different types of DNN complexities for partitioning them on heterogeneous edge devices. For example, in a bandwidth-constrained scenario, our approach gained 40% efficiency as compared to the offline benchmarking approach. Therefore, given the different nature of edge devices' computational, storage, and energy requirements, this approach provides a suitable configuration for edge-cloud synergetic inference.

Internet of Things (IoT) is a system of interrelated sensors and computers to transfer data over a network. However, the sensors, Unmanned Aerial Vehicles (UAVs), and other IoT equipment used are susceptible to different security attacks. Dumb sensors are used to collect data in hostile environments. Dumb sensors are low powered sensors that lack computational power to perform cryptological operations. These sensors are preferred over high powered sensors due to their low electrical signature, but they have negligible computing power. To overcome the loss of authentication data due to node capture and lack of sensor location verification, we propose the Nexus of 6G and Blockchain for Authentication (NBA) system. The NBA system utilizes a permissioned blockchain-based network of UAVs and smart sensors to prevent code tampering. The system enables two-way trusted data transfer between UAVs and dumb sensors through a novel Hybrid Physical Unclonable Function Hashing (HPUFH) model. The system also utilizes a novel Pattern-based Signal Strength Correlation (PbSSC) algorithm to detect any unexpected location changes in the dumb sensor field. The extensive security and performance evaluation demonstrates that the proposed system is highly efficient and secure with a linear computational cost proportional to the number of challenge-response pairs.

Apart from high-level computer vision tasks, deep learning has also made significant progress in low-level tasks, including single image dehazing. A well-detailed image looks realistic and natural with its clear edges and balanced colour. To achieve a clearer and vivid view, we exploit the role of edges and colours as a significant part of our proposed work. A progressive two-stage image dehazing network is presented to overcome the challenges of current image dehazing algorithms. The proposed image dehazing framework is divided into two steps; in the first stage, the multiscale image features of the encoder and decoder structure can be extracted. The second stage consists of the Color Correction Model (CCM), which retrieves balanced colour close to the ground truth. The encode-decoder network consists of a dense residual attention unit (DRAU) that comprises channel attention with pixel attention mechanisms. We have seen that weighted information and the haze difference is inconsistent across pixels without DRAU at the various channel-specific features. DRAU deals with different features and pixels unequally, which offers more versatility in handling knowledge of various types of detailed information. Our proposed two-stage network exceeds state-of-the-art algorithms in both visual and quantitative aspects. The findings are tested with the best-published peak signal-to-noise ratio metrics of 33.55–33.44 dB and SSIM 0.9619–0.9714 on SOTS indoor and outdoor test data sets.

Nonorthogonal multiple access (NOMA) with a grant-free access has received a lot of attention due to its support to massive machine-type communication (mMTC) devices. The devices in grant-free systems are allowed to transmit information without undergoing an authentication process. Therefore, in such systems, the base station needs to distinguish between active and nonactive devices, called the active user detection (AUD) process. This process is challenging as the active device needs to be detected from the received signals that are superimposed. Furthermore, the identification of the Internet of Things (IoT) devices from these signals also poses a great challenge, which could help allocate resources in future generation communication systems. Motivated from the aforementioned facts, this article proposes a device detection and identification (DDI) architecture for joint AUD and IoT device identification from the received superimposed signals. The architecture extracts the Fourier patterns as the representative feature vector, which results in an improved detection and identification process. Experimental results show that the architecture not only outperforms the conventional schemes and deep neural network-based approaches in terms of success probability for the AUD task but also yields lower computational complexity. The evaluation of the DDI architecture for IoT device identification problems has also been performed and compared to various shallow learning methods to prove its efficacy.

Faced with the rapid increase in smart Internet-of-Things (IoT) devices and the high demand for new business-oriented services in the fifth-generation (5G) and beyond network, the management of mobile networks is getting complex. Thus, traditional Network Management and Orchestration (MANO) approaches cannot keep up with rapidly evolving application requirements. This challenge has motivated the adoption of the Zero-touch network and Service Management (ZSM) concept to adapt the automation into network services management. By automating network and service management, ZSM offers efficiency to control network resources and enhance network performance visibility. The ultimate target of the ZSM concept is to enable an autonomous network system capable of self-configuration, self-monitoring, self-healing, and self-optimization based on service-level policies and rules without human intervention. Thus, the paper focuses on conducting a comprehensive survey of E2E ZSM architecture and solutions for 5G and beyond networks. The article begins by presenting the fundamental ZSM architecture and its essential components and interfaces. Then, a comprehensive review of the state-of-the-art for key technical areas, i.e., ZSM automation, cross-domain E2E service lifecycle management, and security aspects, are presented. Furthermore, the paper contains a summary of recent standardization efforts and research projects towards the ZSM realization in 5G and beyond networks. Finally, several lessons learned from the literature and open research problems related to ZSM realization are also discussed in this paper.

Given the explosive growth of portable devices, mobile crowdsensing (MCS) is becoming an essential approach that fully utilizes pervasive idle resources to accomplish sensing tasks. The traditional MCS relies on the centralized server for task handle is susceptible to a single point of failure. Targeting this security issue, researchers have proposed a series of blockchain-based MCS. However, nodes in the blockchain suffer from high computation cost for data processing. Simultaneously, most blockchain-based MCS systems lack an efficient incentive mechanism for service requesters and workers. In this work, we integrate the smart contract and mobile devices to establish a secure, interactive, and fair blockchain-based MCS system called BSIF. To prevent illegitimate participants, BSIF requests all users to verify their identities using private keys from the registration phase. In the case of worker location privacy leakage, the location-based symmetric key generator is adopted to coordinate a session key for target range worker selection. Besides, we transfer the data evaluation process to the requester side (e.g., a personal computer), reducing computation cost in the blockchain nodes. Due to the homomorphic feature of the Paillier Cryptosystem and common interest, the requester cannot violate the directives from the blockchain. Subsequently, the Stackelberg game is adopted to investigate the participation level of the workers and the fair reward mechanism for the requesters to achieve a dynamic balance. Finally, the security analysis and performance evaluation demonstrate that our BSIF can defend against possible adversaries while significantly cutting overhead and giving participants the utmost incentive.

Despite massive research in deep learning, the human activity recognition (HAR) domain still suffers from key challenges in terms of accurate classification and detection. The core idea behind recognizing activities accurately is to assist Internet-of-things (IoT) enabled smart surveillance systems. Thereby, this work is based on the joint use of discrete wavelet transform (DWT) and recurrent neural network (RNN) to classify and detect human activities accurately. Recent approaches on HAR exploit the three-dimensional (3-D) convolutional neural networks (CNNs) to extract spatial information, which adds a computational burden. In our case, features are extracted using 3D-DWT instead of 3-D CNNs, performed in three steps of 1D-DWT to reflect the spatio-temporal features of human action. Given the features, the RNN produces an output label for each video clip taking care of the long-term temporal consistency among close predictions in the output sequence. It is noticed that feature extraction through 3D-DWT essentially recovers the multiple angles of an activity. Many HAR techniques distinguish an activity based on the posture of an image frame rather than learning the transitional relationship between postures in the temporal sequence, resulting in degraded accuracy. To address this problem, in this article, we designed a novel rank-based fuzzy approach that segregates activities precisely by ranking the probabilities of activities based on confidence scores. FuzzyAct achieved an average mean average precision (mAP) of 0.8012 mAP on the ActivityNet dataset, and outperformed the baseline counterparts and other state-of-the-art approaches on benchmark datasets. Finally, we present a mechanism to compress the proposed RNN for edge-enabled IoT applications.

Cognitive-inspired Internet of Medical Things (CI-IoMT) combines cognitive science and artificial intelligence to interact with humans and ubiquitous digital environments. The Internet of Things devices generate massive amounts of data and process it with cognitive computing to perform efficient analysis at the edge nodes. Internet of Medical Things (IoMT) uses the said analysis to design smart communication systems to facilitate ubiquitous services. However, the protocols used in IoMT use conventional number theory systems that are vulnerable to quantum-computer attacks. Therefore, an efficient CI-IoMT scheme is required to handle access privacy, preservation, and trust guarantee. This article presents an identity-based seamless privacy preservation (IB-SPP) for CI-IoMT to authorize smart device communications. It is entirely based on fast user authentication to shorten access timing in an emergency situation. The simulation analysis shows that the proposed IB-SPP scheme consumes less response time and minimum data volume than other existing schemes.

The aim of this Special Issue is to share the state-of-the-art research and developments on the emerging Industry 5.0 concepts, technologies, use cases and future applications. The outstanding benefits of Industry 5.0 in terms of cost and efficiency facilitate a reality sooner than expected. However, the benefits of Industry 5.0 must not come at a price-any negative social or economic impact must be prevented. To this end, it is beneficial and important that businesses can identify the ethical issues associated with these technologies and find solutions ahead of implementation. Ethically aligned designs and standards must be the backbone of the next Industrial Revolution. Hence, there is a desperate need for the further exploration of the role of Industry 5.0 in all verticals and for the exploitation of computational intelligence. Following a series of rigorous reviews, twelve papers, presenting original research, have been selected for publication in this Section.

In the upcoming sixth-generation (6G) networks, ultra-reliable and low-latency communication (URLLC) is considered as an essential service that will empower real-time wireless systems, smart grids, and industrial applications. In this context, URLLC traffic relies on short blocklength packets to reduce the latency, which poses a daunting challenge for network operators and system designers since classical communication systems are designed based on the classical Shannon’s capacity formula. Therefore, to tackle this challenge, this article considers an unmanned aerial vehicle (UAV) acting as a decode-and-forward relay to communicate short URLLC control packets between a controller and multiple-mobile robots in a cell to enable a use-case of Agriculture 4.0. Moreover, this article employs perturbation theory and studies the quasi-optimization of the UAV’s location, height, beamwidth, and resource allocation, including time-varying power and blocklength for the two phases of transmission from the controller to UAV and from UAV to robots. In this regard, we propose an iterative optimization method to find the optimal UAV’s height and location, the antenna beamwidth, and the variable power and blocklength allocated to each robot inside the circular cell to minimize the average overall decoding error. It is demonstrated that the proposed algorithm outperforms other benchmark algorithms based on fixed parameters and performs nearly as well as the smart exhaustive search. Lastly, our results emphasize the need to jointly optimize all of the abovementioned UAV’s system parameters and resource allocation for the two phases of transmission to achieve URLLC for multiple-mobile robots.

In the cloud-assisted Internet of things (IoT), most of the data are sent to the cloud for storage and processing. Data privacy and security are extreme concerns since retrieving data from the cloud will yield privacy disclosure risk due to the cloud’s openness. To this end, this article proposes PERT, a privacy-enhanced retrieval technology for cloud-assisted IoT. This architecture is designed through an implicit index maintained by edge servers and a hierarchical retrieval model that preserves data privacy by hiding the information of data transmission between the cloud and the edge servers. For the hierarchical retrieval model, we designed a data partition strategy. The edge server stores partial data. In this way, data privacy is preserved since the attacker must get the data maintained by both cloud and edge servers. The detailed performance analysis and extensive experiments have displayed the effectiveness of the technology for data privacy. It is tested that the architecture can efficiently and securely retrieve the stored data while the computation cost is reduced through operation downsizing. Compared with the benchmark cloud encrypted storage model, the time cost of this method is significantly reduced when the number of users is relatively large.

Data transmission for the industrial Internet of Things (IoT) is crucial for industrial production, especially in the Industry 5.0 era, where human–machine collaboration is increasingly intensive. To ensure the continuity and robustness of industrial IoT communications in the case of damaged infrastructure communication facilities postdisaster, the industrial IoT can be connected with satellite networks in emergencies. This article presents a cross-regional, end-to-end, transmission control scheme for satellite-supported, multihop industrial IoT. The proposed scheme adjusts the window of data transmission from two phases, slow start and congestion avoidance, to accommodate the low-transmission performance caused by a long delay and high bit error rate in converged networks. The window of data transmission is also adjusted to increase the amount of data transmission for the slow start to fill the high bandwidth-delay product of the converged network, while adjusting the threshold of data transmission based on feedback information to distinguish different data losses during congestion avoidance. The feasibility of the heterogeneous network transmission model is experimentally verified. The results show that the scheme can achieve good performance in heterogeneous networks of industrial IoT and satellite networks. The scheme is effective in ensuring the continuity and stability of intelligent machine production in Industry 5.0 in emergency communication cases.

Healthcare big data (HBD) allows medical stakeholders to analyze, access, retrieve personal and electronic health records (EHR) of patients. Mostly, the records are stored on healthcare cloud and application (HCA) servers, and thus, are subjected to end-user latency, extensive computations, single-point failures, and security and privacy risks. A joint solution is required to address the issues of responsive analytics, coupled with high data ingestion in HBD and secure EHR access. Motivated from the research gaps, the paper proposes a scheme, that integrates blockchain (BC)-based confidentiality-privacy (CP) preserving scheme, CP-BDHCA, that operates in two phases. In the first phase, elliptic curve cryptographic (ECC)-based digital signature framework, HCA-ECC is proposed to establish a session key for secure communication among different healthcare entities. Then, in the second phase, a two-step authentication framework is proposed that integrates Rivest-Shamir-Adleman (RSA) and advanced encryption standard (AES), named as HCA-RSAE that safeguards the ecosystem against possible attack vectors. CP-BDAHCA is compared against existing HCA cloud applications in terms of parameters like response time, average delay, transaction and signing costs, signing and verifying of mined blocks, and resistance to DoS and DDoS attacks. We consider 10 BC nodes and create a real-world customized dataset to be used with SEER dataset. The dataset has 30,000 patient profiles, with 1000 clinical accounts. Based on the combined dataset the proposed scheme outperforms traditional schemes like AI4SAFE, TEE, Secret, and IIoTEED, with a lower response time. For example, the scheme has a very less response time of 300 ms in DDoS. The average signing cost of mined BC transactions is 3,34 seconds, and for 205 transactions, has a signing delay of 1405 ms, with improved accuracy of ≈ 12% than conventional state-of-the-art approaches.

Autonomous Vehicles (AVs) are a significant part of Vehicular Adhoc NETwork (VANET) as they increase transportation accessibility. However, the presence of unpredictably sized potholes on road surfaces hampers the comfort and safety of autonomous navigation. Existing pothole avoidance mechanisms cannot dynamically adapt in unpredictable environments and do not comfort the traveler well in VANET. This paper proposes a novel Smart Pothole-Avoidance Strategy (SPAS) for safe navigation in a pothole-intensive environment. Potholes are avoided using the Deep Deterministic Policy Gradient (DDPG) algorithm as it performs best in continuous action space tasks and has a faster convergence speed. A Hybrid Recognition Model using the Speech and Gesture mechanism (HRM-SG) is proposed in this paper to collect the traveler’s real-time audio and visual feedback for the DDPG reward function. The received feedback aids in fine-tuning the model to avoid the pothole efficiently than the previous pothole. Traveler’s feedback is coupled with the vehicle’s sensor data and used to decide the time, speed, and angle at which lane change and speed change are executed. Finally, the SPAS continuously optimizes lane change parameters in VANET to achieve maximal traveler comfort during the operation. The result analysis indicates that SPAS achieves a 10-15% improvement in the accuracy of pothole avoidance, 10-12% higher comfort, and 8-10% faster convergence than the existing state-of-the-art techniques.

Connected and Autonomous Vehicles (CAVs) are an emerging solution to the issues of safe and sustainable transportation systems in the future. One major transport technology for CAVs is Cooperative Adaptive Cruise Control (CACC), for which unsignalized autonomous intersection crossing is a growing use case. CACC relies heavily on inter-vehicular communication and is thus vulnerable to message forgery and jamming attacks. Most solutions for CACC focus exclusively on enhancing efficiency or security but do not offer an integrated framework for achieving both on a large scale. In this paper, we propose a Blockchain-integrated Multi-Agent Deep Reinforcement Learning (Block-MADRL) architecture for enhancing the efficiency of CACC while cooperatively detecting attacks, reducing the fuel efficiency of identified attackers and securely notifying the overall network. Our approach uses multi-agent deep reinforcement learning to find fuel and throughput optimizing solutions for CACC and a cooperative verification mechanism based on Extended Isolation Forest (EIF) for attack detection. Attacker data is securely stored in a Road Side Unit (RSU) level blockchain, and we design a low-latency, high throughput consensus protocol for speedy and secure data dissemination. Simulation results indicate over 29.5% better lane throughput with our approach during acceleration forgery attack, up to 23% induced reduction in fuel efficiency of malicious vehicles, 17.6% higher blockchain throughput through our consensus protocol and over 8% improvement in attack detection rate compared to the state-of-the-art.

In this paper, we propose a microservices and deep learning-based scheme, termed as Micro-Safe, for provisioning Safety-as-a-Service (Safe-aaS) in a 6G environment. A Safe-aaS infrastructure provides customized safety-related decisions dynamically to the registered end-users. As the decisions are time-sensitive in nature, the generation of these decisions should incur minimum latency and high accuracy. Further, scalability and extension of the coverage of the entire Safe-aaS platform are also necessary. Considering road transportation as the application scenario, we propose Safe-aaS, which is a microservices- and deep learning-based platform for provisioning ultra-low latency safety services to the end-users in a 6G scenario. We design the proposed solution in two stages. In the first stage, we develop the microservices-enabled application layer to improve the scalability and adaptability of the traditional Safe-aaS platform. Moreover, we apply the state space model to represent the decision parameters requested and the decision delivered to the end-users. During the second stage, we use deep learning models to improve the accuracy in the decisions delivered to the end-users. Additionally, we apply an assortment of activation functions to analyze and compare the accuracy of the decisions generated in the proposed scheme. Extensive simulation of our proposed scheme, Micro-Safe, demonstrates that latency is improved by 26.1 – 31.2%, energy consumption is reduced by 22.1 – 29.9%, throughput is increased by 26.1 – 31.7%, compared to the existing schemes.

As important services of the future sixth-generation (6G) wireless networks, vehicular communication and mobile edge computing (MEC) have received considerable interest in recent years for their significant potential applications in intelligent transportation systems. However, MEC-enabled vehicular networks depend heavily on network access and communication infrastructure, often unavailable in remote areas, making computation offloading susceptible to breaking down. To address this issue, we propose an MEC-enabled vehicular network assisted through aerial-terrestrial connectivity to provide network access and high data-rate entertainment services to a vehicular network. We present a time-varying, dynamic system model where high altitude platforms (HAPs) equipped with MEC servers, connected to a backhaul system of low-earth orbit (LEO) satellites, are used to provide computation offloading capability to the vehicles, as well as to provide network access for vehicle-to-vehicle (V2V) communications. Our main objective is to minimize the total computation and communication overhead of the joint computation offloading and resource allocation strategies for the system of vehicles. Since our formulated optimization problem is a mixed-integer non-linear programming (MINLP) problem, which is NP-hard, we propose a decentralized value-iteration-based reinforcement learning (RL) approach as a solution. In our Q-learning-assisted analysis, each vehicle acts as an intelligent agent to form optimal strategies for offloading and resource allocation. We further extend our solution to deep Q-learning (DQL) and double deep Q-learning to overcome the issues of dimensionality and the over-estimation of the value functions, as in Q-learning. Simulation results prove the effectiveness of our solution in successfully reducing system costs compared to baseline schemes.

We consider a multi-hop cooperative network inside a factory environment with the number of devices which are placed uniformly in a strip-shaped manner. the randomly deployed multiple intermediate relay nodes serve source and destination using the opportunistic large array (OLA) cooperative communication protocol for packet transmission. However, the simultaneous transmission of packets results in interference when the multiple transmissions occur simultaneously in the multihop wireless network. This paper analyzes the impact of such interference in the considered factory automation scenario from the Industry 4.0 perspective. We analyze the system performance in terms of the outage probability, success rate and latency with various network parameters. Moreover, the key insights are obtained related to the impact of packet insertion rate and tiers of interference on the system performance. Specifically, it is observed that the success rate of considered cooperative OLA network significantly increases due to the spatial diversity gains. However, the interference of multiple packets transmission severely affects the network success rate.

Unmanned Aerial Vehicles (UAVs), a new emerging form of Internet of Things (IoT), is a promising technology to be widely used in both civil and military applications. On the fly, the UAVs need to find an efficient and safe path by avoiding both static and dynamic obstacles to carry out any mission successfully. The Artificial Potential Field (APF) algorithm is one of the conventional catalysts in UAV path planning. However, APF-aided UAVs can be easily trapped into a local minimum solution before reaching the destination. Therefore, this paper proposes an efficient APF algorithm for Collision-free Path Planning (eAPF-CPP) in UAVs. In eAPF-CPP, the attractive and repulsive potentials evaluate the quadratic distance to the destination and the obstacle respectively. The evaluation aids the UAV to select the optimal path in navigation. The eAPF-CPP mechanism is simulated in the Software-In-The-Loop (SITL) setup, and the experimental results show that the eAPF-CPP mechanism utilizes an average of 24.4 seconds to track a safe path and has a lower collision rate of 8.56% compared with Artifical Potential Field Approach (APFA).

The Internet of Things (IoT) is considered a key enabler for a wide range of smart applications. In IoT, a large number of heterogeneous devices form anad hocconnection with each other. Thead hocinfrastructure is considered an integral part of IoT-empowered applications because of its efficient, cost-effective, and dynamic nature. These networks need to ensure the quality of service using their limited resources, particularly in multihop communication. Because multihop communication can be an easy target of attackers, it needs a secure and reliable data transmission scheme. In this article, we propose a secured and reliable continuous transmission scheme for cognitive hybrid automatic repeat request (HARQ)-aided IoT (SRCT-HARQ) capable of maintaining high throughput and lower delay. The SRCT-HARQ scheme is analytically modeled using a probability-based approach. The mathematical formulas are derived for delay and throughput using a probability-based analysis, and the results are verified using the Monte Carlo simulations. The performance results elaborate that the network throughput and delay are improved, mainly due to the proposed authentication scheme. Using our experimental results, we evaluated the optimal time for data transmission to protect the legal rights of primary users that resulted in improved performance.

Fault diagnosis plays a major role in railway condition monitoring, as early diagnosis of the emerging faults can save valuable time, reduce maintenance costs and, most significantly, help save people's lives. However, the conventional data-driven methods used to diagnose track faults, especially in underdeveloped countries, use push trolley/train-based track recording vehicles (TRV) that rely heavily on manual extraction of track data. It is a very demanding process and significantly affects the final results due to its reliance on human judgment in assessing track conditions and its suboptimal performance. In contrast, with the advent of IoT-based smart inertial measurement units, the data-driven fault diagnosis became a core component in the smart industrial automation safety system. We proposed, Muhafiz, a prototype that is an automated and portable TRV with a novel design based on axle-based acceleration methodology for rail track fault diagnosis. Our contribution concluded, based on site-specific experimentation, that Muhafiz is 87% more efficient than the traditional push trolley-based TRV mechanism.

5G technology is expected to enable a plethora of new applications with distinct requirements. Provisioning resources to accommodate such applications implies having a flexible network infrastructure that can be tailored to the specific needs of each application. This can be achieved through network slicing. Still, several applications might request network slices, but their request may not be fulfilled due to lack of resources or lack of coverage and provisioning such resources is a cumbersome task. This paper describes an architecture that facilitates the dynamic leasing of resources among network operators to support cross-domain services. The cornerstone of this architecture is a brokering layer, called DBB, that relies on a blockchain-based bidding system to request resources and evaluate resource provisioning offers. The paper also presents a simulation-based use case scenario that illustrates the need for DBB and which was used to evaluate the performance of the proposed architecture.