The Internet of Things (IoT) and cyber–physical systems (CPS) are driving digital transformation and automation. An essential component of CPS is digital twin (DT) technology, which enables real-time synchronization between physical assets and their virtual counterparts. Battery management systems (BMS) in electric vehicles (EVs) face challenges in handling large volumes of sensor data, often leading to reduced accuracy in battery-state estimation. To address these challenges, DTs have been explored to aid real-time diagnosis and monitoring. One critical step toward the success of DTs is to have practical reference architectures. This paper presents proposes a novel six-layer DT architecture tailored for BMS, extending existing CPS/DT-BMS models by integrating high-fidelity electrochemical modeling, robust nonlinear state estimation, and interactive 3D visualization in a Metaverse environment. The architecture is designed with scalability in mind, supporting deployment on lightweight embedded platforms or via cloud-hosted rendering for resource-limited devices. We validate the approach using MATLAB to develop a thermally coupled SPMe-based DT of a lithium-ion NMC battery, synchronized with a virtual battery model in Unreal Engine for immersive visualization. Experimental results demonstrate accurate state-of-charge estimation (RMSE 0.23%) and low-latency real-time monitoring, highlighting the framework’s potential for deployment in large-scale EV BMS applications.

The increasing complexity of connected and autonomous vehicles (CAVs) introduces new security challenges in the Internet of Vehicles (IoV), where traditional detection models struggle with real-time interpretability, scalability, and robustness against spoofing attacks. This paper proposes EQAI—an Explainable Quantum Artificial Intelligence framework that fuses quantum-enhanced learning with interpretable trust inference for securing vehicular communications. The EQAI model employs an 8-qubit variational quantum circuit (VQC) integrated with lightweight classical layers and explainability modules based on SHAP and LIME. Using the CICIoV2024 dataset, the framework achieves a detection accuracy of 92.85%, a Class 3 F1-score of 82.1%, and a low false alarm rate (FAR ≤ 0.026), outperforming existing machine learning, blockchain-based, and federated learning approaches. Its compact design—with only 4,900 trainable parameters and ∼19.5k FLOPs—demonstrates real-time deployability and energy efficiency at the network edge. Moreover, LIME and SHAP analyses reveal transparent feature-level reasoning, enhancing operator trust and system explainability. The proposed EQAI architecture thus establishes a scalable, interpretable, and quantum-empowered foundation for secure, trustworthy, and intelligent vehicular networks, advancing toward resilient IoV and next-generation cybercognitive mobility ecosystems.

Securing Industrial Internet of Things (IIoT) systems presents critical challenges due to resource constraints, expanding attack surfaces, and the inadequacy of conventional security solutions against sophisticated cyber threats. While AI-driven detection and blockchain technologies offer promise, existing frameworks suffer from computational inefficiency, lack of real-time prevention, or insufficient auditability. This paper introduces a unified AI-PureChain Intrusion Prevention Framework that tightly integrates deep learning-based threat detection with an immutable PureChain ledger using Proof of Authority and Association (PoA2) consensus. The proposed architecture achieves high-fidelity intrusion detection through hybrid CNN-BiLSTM models, attaining 99.76% accuracy on IoTForge Pro, 98.33% on WUSTL-IIoT-2021, and 98.11% on X-IIoTID datasets, while maintaining low inference latency (0.0016s). The PureChain layer ensures tamper-proof audit trails with 24.56 TPS throughput and 68ms commit time, enabling verifiable prevention actions. Experimental results demonstrate complete attack mitigation (0% success rate) under high-traffic conditions while maintaining minimal resource consumption (14.49% CPU, 448 MB memory, 12.95W power). This work represents a significant advancement in IIoT security by delivering a tightly coupled framework that simultaneously addresses detection accuracy, prevention reliability, and forensic accountability, thereby bridging critical gaps in current industrial security paradigms.

The Industrial Internet of Things (IIoT) has transformed critical infrastructure but has also introduced severe security vulnerabilities, with breaches capable of causing catastrophic physical and operational damage. While blockchain technology offers a promising foundation for tamper-proof logging, existing platforms are often ill-suited for IIoT due to high latency, low throughput, and excessive energy consumption. Furthermore, most current research treats intrusion detection, secure logging, and system recovery as isolated components, lacking a unified framework for autonomous, verifiable resilience. To bridge this critical gap, this paper introduces PureChain, a holistic, secure, and resilient ecosystem. PureChain integrates a custom lightweight blockchain with a deep learning-based intrusion detection system and a novel verifiable recovery protocol, creating a closed-loop security model. The framework leverages a novel Proof of Authority and Association (PoA2) consensus mechanism, achieving high throughput (16.82 TPS), low latency (0.0594 s), and minimal energy consumption (12.43 W), demonstrating suitability for resource-constrained IIoT environments compared to general-purpose platforms like Ethereum and Hyperledger which are optimized for different use cases. Upon intrusion detection by optimized models like XGBoost (99.87% accuracy), immutable blockchain logs actively trigger and cryptographically attest to infrastructure-enforced recovery actions such as device isolation via SDN switches or state rollback through hardware management controllers. Extensive evaluation on benchmark IIoT datasets (IoT-CAD and IoTForge) demonstrates a detection-to-recovery success rate of up to 98.59% while maintaining 100% data integrity. PureChain establishes a new paradigm that unifies real-time threat intelligence, blockchain-based trust, and provable autonomous recovery for next-generation IIoT security.

The convergence of Non-Terrestrial Networks (NTNs) and Terrestrial Networks (TNs) in 6G presents a paradigm shift for the Internet of Things (IoT), enabling ubiquitous connectivity but introducing severe routing challenges across a dynamic, multi-domain topology. Traditional blockchain-based routing frameworks often fail to adapt to the mobility, heterogeneity, and energy constraints of IoT deployments. This paper proposes a Proof-of-Route (PoR) blockchain consensus protocol, augmented with PoA (Proof-of-Authority), with adaptive validator rotation for secure and scalable routing. The protocol integrates cryptographic route authentication, dynamic validator selection, and wallet-based key management. This ensures its resistance against black holes, Byzantine attacks, and Sybil attacks. Unlike prior work, our framework was evaluated under conditions that mirror real-world operational stress. Modular Docker-based containers were developed to represent devices in a 6G-IoT setting. They simulated intermittent link availability, varying latencies, node churn and handovers. Results revealed that the proposed protocol achieved up to an average latency of42.3 ms, a packet delivery ratio of98.7% with scalability verified up to over500 nodes. This paper offers a robust, scalable, and secure solution for the complex routing demands of 6G networks.

Biochemical threats remain a serious concern in mission-critical environments, particularly those characterized by intermittent connectivity and infrastructure degradation. Traditional centralized detection systems are ill-suited for such conditions, as they depend on stable communication channels and are inherently vulnerable to cyber-physical disruptions. This work introduces a decentralized solution integrating Artificial Intelligence (AI) and blockchain (BC) for autonomous biochemical threat detection within tactical Mobile Ad-hoc Networks (MANETs). The framework uses a Random Forest (RF) classifier trained on acetylcholinesterase sensor data to identify sarin exposure with 100% accuracy and sub-25ms inference latency. Threat verification is secured using a lightweight Proof of Authority and Association (PoA2) BC, which provides tamper-resistant logging and distributed consensus. The architecture supports offline operations and maintains functionality under conditions of 20% packet loss and node disruption. Simulations conducted in degraded network environments confirmed the system’s robustness and scalability, establishing it as a resilient and efficient platform for secure biochemical threat detection in dynamic, resource-constrained mission-critical settings.

Federated learning (FL) in the Internet of Vehicles (IoV) networks is challenged by privacy vulnerabilities, model poisoning attacks, and the limitations of centralized aggregation, which threaten security and scalability. While homomorphic encryption (HE) provides an additional layer of privacy, existing schemes often suffer from cumulative noise growth, resulting in degraded model accuracy and increased inference latency, critical factors for real-time vehicular safety applications. This paper presents PureFL, a novel FL framework that combines adaptive Cheon-Kim-Kim-Song (CKKS) homomorphic encryption with a custom permissioned blockchain (PureChain), utilizing a proof of authority and association (PoA2) consensus mechanism. PureFL incorporates dynamic precision scaling to manage noise accumulation, ensuring computational efficiency without sacrificing privacy or accuracy. The framework also implements a trust-based aggregation mechanism based on cosine-similarity trust scoring, which dynamically weights client contributions according to historical reliability and anomaly detection, thereby enhancing resilience against model poisoning. Experimentation results on the CICIOV2024 and 5G-NIDD datasets demonstrate that PureFL achieves superior anomaly detection accuracy of 99.9%, reduces CKKS HE overhead via precision scaling, and that the proposed PoA2consensus outperforms other consensus mechanisms in terms of throughput and latency, making it suitable for real-time IoV operations.

The Internet of Medical Things (IoMT) enables continuous health monitoring but still faces challenges in achieving personalized predictions and ensuring secure, tamper-proof data integrity. We presentRemoteCare, an AI-driven multi-modal framework that fuses synchronized physiological and network data for dual-task learning, simultaneously performing personalized health state classification (Normal, Warning, Critical) and cyberattack detection in IoMT traffic. Unlike conventional population-based thresholds,RemoteCaredynamically adapts alerts to each patient’s baseline, thereby minimizing false alarms and enhancing clinical reliability. A hybrid CNN–GRU–LSTM architecture jointly captures spatial and temporal dependencies across heterogeneous signals, while SHAP-based explainability provides transparent, patient-specific insights into the features influencing each prediction. To guarantee auditability, all predictions are immutably recorded on thePureChainblockchain integrated with IPFS, ensuring decentralized and tamper-proof storage. Evaluated on the WUSTL-EHMS-2020 dataset (Enhanced Healthcare Monitoring System),RemoteCareachieved 99.7% accuracy for health classification and 96.0% for intrusion detection, with negligible false alarms and efficient inference suitable for real-time deployment. By unifying multimodal prediction, personalization, interpretability, and secure logging,RemoteCareestablishes a trustworthy framework for early intervention, patient-specific risk assessment, and clinician-oriented decision support in remote healthcare.

Vehicular-to-Everything (V2X) communications promise unprecedented safety and efficiency gains but remain vulnerable to confidentiality breaches such as eavesdropping, traffic analysis, and man-in-the-middle attacks. We propose ConfidSPEC-V2X, a focused hybrid framework that integrates continuous-variable quantum key distribution (CV-QKD), a multi-agent deep reinforcement learning (DRL), and an Ethereum-based permissioned blockchainPureChainpublic-key infrastructure (PKI) to deliver information-theoretic secrecy, dynamic traffic obfuscation, and tamper-proof key management. In the quantum module, CV-QKD transceivers embedded in On-Board Units (OBUs) and Roadside Units (RSUs) establish symmetric keys resilient to passive interception and capable of immediate eavesdropping detection. The Artificial Intelligence (AI) module employs multi-agent DRL agents at RSUs to learn optimal dummy-traffic injection policies that obfuscate real V2X message patterns against statistical inference. The blockchain module leverages PureChain smart contracts to register, rotate, and timestamp vehicle public keys, ensuring that any man-in-the-middle attempt to forge or replay keys is invalidated. We implement and evaluate ConfidSPEC-V2X within an OMNeT++/Veins simulation under realistic urban mobility scenarios, measuring the quantum bit error rate, key generation throughput, obfuscation entropy, and key management latency. Results demonstrate that our framework achieves robust confidentiality protection with minimal performance overhead.

Abstract This study introduces an integrated system for detecting and managing driver inattention using a combination of artificial intelligence (AI), blockchain technology, and edge computing. The proposed system utilizes You Look Only Once version 8 Nano (YOLOv8n) for real-time object detection and a Raspberry Pi 5 for edge-based analysis, ensuring efficient and accurate detection of inattentive behaviors such as drowsiness, distraction, and other unsafe driving patterns. Blockchain integration with Hyperledger Besu, using the Istanbul Byzantine Fault Tolerance version 2.0 (IBFT 2.0) consensus protocol, provides a secure and tamper-resistant ledger for recording and verifying driver inattention events. The system demonstrated robust performance metrics, including a mean precision of 92.99%, mean recall of 93.47%, and mean Average Precision at Intersection over Union threshold 0.5 ([email protected]) of 92.5% for YOLOv8n, establishing its superiority among evaluated YOLO models. The blockchain network achieved a throughput of up to 128.5 transactions per second (TPS) and an average latency ranging from 0.84 seconds for transfer operations to 4.43 seconds for open operations, demonstrating its capability to support real-time event logging. This research addresses limitations in traditional centralized systems by offering a scalable, permissioned, and transparent framework for enhancing driver safety through real-time monitoring and secure data management.

Abstract Land administration in Nigeria continues to face critical challenges, including document inconsistencies, opaque verification procedures, slow processing times, and persistent administrative malpractice associated with centralized and conventional, non-automated record-management systems. These systemic weaknesses create opportunities for double allocation, unauthorized alterations, and hidden registry manipulation, highlighting the need for more secure and transparent digital approaches. This paper proposes BERBLOM, a blockchain-enabled land ownership management system tailored to Nigerian land-registry workflows. The system tokenizes land parcels as ERC-4907 assets and stores supporting documents in the InterPlanetary File System (IPFS) to enhance data integrity and reduce single points of failure. BERBLOM supports practical use cases such as government plot allocation, peer-to-peer property transfers, and an on-chain leasing mechanism that automatically reverts ownership upon lease expiration. The framework operates on a permissioned Hyperledger Besu network using the Quorum Byzantine Fault Tolerance (QBFT) consensus protocol, selected for its Byzantine fault tolerance, predictable gas-free operation, and scalability under controlled conditions. Experimental evaluation indicates that QBFT maintains stable throughput and manageable latency as the number of validator nodes increases from 4 to 32. A Flutter-based decentralized application (DApp) enables real-time interaction through event-driven synchronization. While human-driven corruption and malpractice cannot be fully eliminated, the proposed prototype demonstrates how blockchain-based registries can reduce opportunities for hidden technical manipulation and improve on-chain accountability. It is important to note that the primary performance benefits of BERBLOM are realized after tokenization. Initial land registration remains dependent on legally mandated, human-driven governmental approvals; however, post-registration operations such as peer-to-peer transfers and on-chain leasing can be executed without intermediaries and complete within seconds. Consequently, the performance analysis focuses on the lifecycle stages where blockchain automation provides the greatest impact.

Robust object tracking in ISAC systems is challenging due to the inherent sparsity and severe impulsive noise of millimeter-wave (mmWave) radar signals. To address this, we propose a novel tracking framework that combines cross-modal supervision with a Spatio-Temporal Skip-Transformer (ST-Skipformer). An offline LiDAR–camera label generator produces high-fidelity ground-truth supervision, enabling the ST-Skipformer to learn precise spatial features from noisy radar inputs. Furthermore, the ST-Skipformer incorporates a Temporal Skip (TS) Block to effectively filter background clutter while recovering high-frequency spatial details via skip connections. Experimental results on the real-world DeepSense 6 G dataset demonstrate that the proposed method achieves an Average Displacement Error (ADE) of 0.0174 m, reducing localization error by approximately 98% compared to baselines, while attaining a near-perfect F1-score of 0.9967.

PureRx is an innovative blockchain-based prescription management system designed to overcome the limitations of traditional paper prescriptions, including medication errors, fraud, and inefficiencies in tracking patient records. By leveraging Non-Fungible Tokens (NFTs) and batch minting, PureRx enables efficient, secure, and patient-centric control of prescription data. Patients maintain ownership of their medical records, while healthcare providers and pharmacies benefit from transparent and immutable prescription workflows. Experimental evaluation shows that PureRx improves operational efficiency by 37.18% in initial cycles, increasing to 51% in subsequent cycles compared to existing systems, while reducing costs by 46.76% in high-volume scenarios. Security analysis confirmed that no critical vulnerabilities were found and that all prescription issuance and claiming events are tamper-resistant and auditable on-chain. By combining scalability, transparency, and patient empowerment, PureRx demonstrates the potential of blockchain to transform prescription management in modern healthcare systems.

The interconnected and diverse nature of Digital Twin (DT)-based industrial Artificial Internet of Things (AIoT) systems exposes them to potential cyber threats and malicious activities. This paper introduces a novel framework called BLIND-Twin, which leverages blockchain, DT, and Large Language Model (LLM) technologies to address critical security and scalability challenges in industrial AIoT networks. By integrating DT technology, BLIND-Twin continuously mirrors physical environments, enabling real-time monitoring and synthetic data generation to simulate diverse threat scenarios. Data from the DT undergoes feature extraction via a Long Short-Term Memory (LSTM) Autoencoder (LSTM-AE) to extract essential temporal patterns, while the LLM enables adaptive, contextaware intrusion detection without retraining. A permissioned blockchain layer ensures data integrity, privacy, and secure logging through smart contracts, supporting automated threat response with verifiable audit trails. The framework's decentralized architecture mitigates Single Points of Failure (SPoF), addressing scalability and privacy concerns. Performance evaluations utilizing datasets like 5G-NIDD and CICIoT2023 demonstrate BLINDTwin's capability in accurately detecting various cyber threats by achieving 99.63 % accuracy with minimal latency, showcasing its effectiveness for complex industrial AIoT environments.

Efficient task offloading in dynamic fog computing environments requires adaptive decision-making under uncertainty. This paper proposes a Bayesian Deep Neural Network (BDNN)-empowered Thompson Sampling (TS) framework for context-aware task offloading, enabling intelligent resource allocation while balancing exploration and exploitation. The BDNN models the stochastic reward function by learning a posterior distribution over network weights, capturing the uncertainty in offloading decisions. At each time step, the task node samples a set of weights from the learned posterior to estimate the expected reward of each helper node, facilitating adaptive decision-making in dynamic network conditions. Experimental results demonstrate that our approach outperforms conventional heuristics and deep learning-based methods, achieving lower latency, improved resource utilization, and better offloading efficiency in fog computing environments.

Task offloading in multi-tier fog computing networks presents significant challenges due to dynamic resource availability, fluctuating network conditions, and the inherent uncertainty in task execution outcomes. To address these issues, we propose an uncertainty-aware task offloading framework based on Federated Probabilistic Deep Neural Networks (Fed-PDNNs). In our approach, edge devices independently train local PDNNs to estimate both the expected reward and predictive uncertainty for offloading tasks to candidate fog nodes. These models provide a principled way to quantify epistemic uncertainty and enable effective decision-making through Thompson Sampling. To enhance generalization and maintain data privacy, the PDNNs are periodically synchronized via federated learning at the fog tier, where fog nodes aggregate model updates from connected edge devices without requiring access to raw data. Our framework naturally supports decentralized control, adapts to heterogeneous environments, and balances exploration and exploitation during offloading. Extensive experiments on synthetic and real-world workloads demonstrate that Fed-PDNN significantly outperforms baseline methods in terms of task completion delay, offloading success rate, and robustness under dynamic network conditions, offering a scalable, intelligent, and privacy-preserving solution for next-generation edge-fog-cloud systems.

This research examines the incorporation of Artificial Intelligence (AI) in blockchain consensus algorithms, presenting an extensive overview of current improvements and anticipated effects. We conducted a thorough examination of a diverse array of academic sources, encompassing a broad spectrum of AI methodologies, such as machine learning, deep learning, and reinforcement learning, that have been applied to blockchain consensus mechanisms. The study highlights critical areas where AI can bolster blockchain performance, including enhancing effectiveness, dependability, and flexibility. Despite the promising benefits that AI integration offers, it also presents complexities and potential security risks, including data centralization and increased computational power requirements. In this analysis, we review the risks and examine the proposed mitigation strategies from existing studies, such as federated learning to preserve data privacy, secure multi-party computation to protect sensitive data, and decentralized AI marketplaces to distribute AI resources fairly. This study makes a significant contribution to the field by emphasizing the dual potential of AI to both improve and challenge blockchain systems. By advocating for balanced approaches that prioritize decentralization and security, our findings aim to provide direction for future research and practical applications in this multidisciplinary field.

The increasing prevalence of cancer necessitates advanced methodologies for early detection and diagnosis. Early intervention is crucial for improving patient outcomes and reducing the overall burden on healthcare systems. Traditional centralized methods of medical image analysis pose significant risks to patient privacy and data security, as they require the aggregation of sensitive information in a single location. Furthermore, these methods often suffer from limitations related to data diversity and scalability, hindering the development of universally robust diagnostic models. Recent advancements in machine learning, particularly deep learning, have shown promise in enhancing medical image analysis. However, the need to access large and diverse datasets for training these models introduces challenges in maintaining patient confidentiality and adhering to strict data protection regulations. This paper introduces FedViTBloc, a secure and privacy-enhanced framework for medical image analysis utilizing Federated Learning (FL) combined with Vision Transformers (ViT) and blockchain technology. The proposed system ensures patient data privacy and security through fully homomorphic encryption and differential privacy techniques. By employing a decentralized FL approach, multiple medical institutions can collaboratively train a robust deep-learning model without sharing raw data. Blockchain integration further enhances the security and trustworthiness of the FL process by managing client registration and ensuring secure onboarding of participants. Experimental results demonstrate the effectiveness of FedViTBloc in medical image analysis while maintaining stringent privacy standards, achieving 67% accuracy and reducing loss below 2 across 10 clients, ensuring scalability and robustness.

The advancement of intelligent transport systems and the rise of autonomous vehicles offer significant potential for reducing road accidents. However, mountainous regions, such as South Korea, are particularly susceptible to the formation of black ice, which poses a serious risk to both human and autonomous drivers due to its near-invisibility and sudden formation. Traditional road condition monitoring methods often fail to promptly detect black ice, underscoring the need for more advanced sensing systems. This work presents a multimodal system called BlackIceNet, integrating visual, acoustic, and sensor data, including surface and ambient temperatures, to detect black ice. The system utilizes a convolutional neural network (CNN)-based framework for image and audio analysis, followed by data fusion techniques to combine the insights from each modality. The proposed algorithm includes the following steps: preprocessing and normalizing data, feature extraction from visual and acoustic data, multimodal fusion to combine vision, audio, and sensor data, and classification of road surface conditions using BlackIceNet. The dataset has been gathered over the years from various testbeds established across three distinct areas in South Korea, contributing to a comprehensive understanding of the area’s diverse conditions. The evaluation results demonstrate the efficacy of the proposed method, achieving a 97.54% accuracy rate in detecting black ice with a model size of 233.47 MB and a training time of 2293.92 s, offering a more compact and computationally efficient solution. This fusion-based approach overcomes the limitations of individual modalities, providing reliable and early warnings, thereby enhancing road safety in hazardous conditions.

Vulnerabilities in drone networks stem from the reliance on GPS and wireless communication technologies, combined with the lack of robust security mechanisms. This study proposes DroneGuard, a comprehensive cybersecurity framework leveraging supervised machine learning (ML) and explainable artificial intelligence (XAI) to detect intrusions and provide insights into the decision-making process of the security model. We explored various feature selection techniques to design a lightweight model suitable for the resource constraints of drones. Additionally, the synthetic minority oversampling technique (SMOTE) is employed to balance target class distribution and mitigate performance degradation, while randomized search cross-validation (RSCV) aids in selecting optimal hyperparameters for model training. Simulation experiments were conducted using a real-time GPS dataset for autonomous vehicles and a cybersecurity dataset containing variants of Denial of Service (DoS) attacks to evaluate the models’ performance. Comparison with four ML models using essential evaluation metrics validated the robust performance of the decision tree model, which detected spoofed GPS signals and DoS attacks with high accuracy, low-computational complexity, and minimal false alarm rates. Furthermore, the Shapley additive explanation (SHAP) provides intuitive visual explanations of important features contributing to the detection and classification of both GPS spoofing and DoS attacks. Therefore, DroneGuard offers effective and interpretable security solutions for enhanced drone application and adoption.

The rapid expansion of the Internet of Things (IoT) into edge networks, which are populated by resource-constrained devices, introduces significant security challenges. This article introduces a robust intrusion detection systems (IDS) for edge-IoT networks developed as a combination of blockchain technology and federated learning (FL) with a customized aggregation strategy, adaptive trimmed mean aggregation (ATMA). Our design leverages a permissioned blockchain to authenticate clients and immutably store the final global model, guaranteeing that only verified participants contribute to the training. ATMA strategy used in the FL departs from fixed-threshold schemes in other works by dynamically adjusting its trimming parameter according to the observed variance in client updates. This variance-aware trimming provides strong Byzantine resilience without sacrificing model accuracy, and its sorting-based implementation maintains an O(n log n) computational complexity. The proposed setup was evaluated under combined label-flipping and Gaussian-noise attacks at adversarial rates of 0%, 10%, 20%, 30%, 40%, 50%, and 60%, in both IID and non-IID data distributions. The results demonstrated that our blockchain-backed ATMA preserves high detection performance under severe attack scenarios and does so with minimal overhead, making it a scalable, secure solution for safeguarding Edge-IoT deployments.

Increased automation, connectivity, and data sharing enabled by 6G technology have heightened the vulnerability of Internet of Vehicles (IoV) networks. Addressing this challenge requires an intrusion detection system (IDS) capable of accurately identifying data falsification within IoV while adhering to real-time constraints. This paper presents a Blockchain-enhanced feature-engineered IDS to ensure precise attack detection and classification with minimal computational overhead in in-vehicle networks (IVNs). The proposed lightweight IDS utilizes a hybrid Pearson’s Correlation Coefficient (PCC) feature selection technique designed for deployment on the Telematics Control Unit (TCU). Furthermore, we propose a custom private blockchain network utilizing the proof of authority and association (PoA) consensus mechanism, deployable on the Roadside Unit (RSU), for the secure logging of vehicle Electronic Control Unit (ECU) information, detection results, and the automatic isolation of malicious ECUs via smart contracts. Experimentation analysis demonstrates that the proposed approach achieves notable performance, with a 99.9% detection accuracy and minimal computation times of 0.24s and 1.32s on the CICIoV2024 and CAN-Intrusion datasets. Furthermore, the system achieves high blockchain scalability, maintaining stable throughput of 16 tx/s and low transaction latency of 0.062s under increasing ECU density and RSU coverage.

As the Metaverse progresses, its security measures must evolve to safeguard users from cyberattacks. To this end, Artificial Intelligence (AI)-powered Network Intrusion Detection Systems (NIDSs) have been implemented at the network layer to detect and respond to threats in real-time. Our survey -MetaWatch provides a comprehensive overview and analysis of relevant literature, focusing on studies that have explored NIDSs in the Metaverse. Unlike other surveys that have addressed Metaverse security issues more broadly, MetaWatch specifically provides a taxonomy of detection paradigms and defense mechanisms within Metaverse NIDS from 2021 to 2024. Additionally, MetaWatch identifies and discusses the key challenges and problems that impact the development of trustworthy, explainable, scalable, and robust Metaverse NIDS. Overall, the survey provides readers with a concise and informative summary of NIDS issues in the Metaverse and highlights open security problems worth exploring.

In federated learning (FL), devices contribute to global training by uploading only the local model gradients (outcomes), providing connected devices with the ability to learn while preserving privacy. FL-based resource allocation for V2X communications is proposed, referred to as FL-RA-V2X, which optimizes and maximizes the throughput of all vehicle users within the constraints of maximum power and the signal-to-interference-plus-noise ratio (SINR). It ensures fairness in resource allocation, meeting the minimum SINR requirements for cellular users and outage probability constraints for vehicle users. An approximate expression for vehicle users’ throughput is derived, eliminating the non-convexity associated with the SINR expression through iterative calculations of auxiliary variables. The resource allocation is designed to allow each vehicle user to share uplink resources with cellular users, maximizing the number of vehicle users while utilizing their maximum power transmission capability. Simulation results demonstrate the fairness and enhanced throughput efficiency of the proposed approach compared to contemporary algorithms, considering vehicle outage ratio, computational complexity, computing time, maximum transmitting power, cumulative distribution function of achievable sum rates, and convergence metrics. Furthermore, the proposed approach addresses critical aspects, including high mobility and distributed V2V communications, asynchronous training issues in cellular V2X networks, and the convergence analysis under different conditions such as varied vehicle densities and mobility patterns. These considerations broaden the applicability and robustness of the FL-RA-V2X method across diverse scenarios. The analysis also explores the impact of vehicle speed, auxiliary variables, interference effects of cellular users, and the dependence of throughput on FL iterations.

An essential aspect of Industrial Internet of Things (IIoT) systems lies in their reliability and resilience against failures. Fault detection serves as a crucial method for mitigating errors, leading to reduced downtime. Previous studies have predominantly focused on fault detection using centralized Artificial Intelligence (AI) approaches, wherein participant information is centralized and forwarded to a central server. However, Federated Learning (FL) offers a solution to these issues, enhancing the system’s reliability. In this study, we propose a Decentralized FL (DFL) approach for collaborative learning in bearing fault detection. DFL is preferred over centralized FL due to its elimination of a single point of failure. By leveraging the decentralized FL concept, the vulnerability of the collaborative framework to attacks can be minimized. Our proposed DFL integrates continual learning techniques to reduce communication overhead. The results demonstrate that decentralized collaborative learning achieves satisfactory performance, with an accuracy rate of 96.08% and a learning time reduction of up to 37.52%.

The distributed and heterogeneous connections in the digital twin (DT)-based industrial Internet of Things (IIoT) are vulnerable to cyber-attacks and malicious activities. This study proposes a permissioned blockchain-assisted collaborative and decentralized cyber threat detection for securing DT-based IIoT networks. A context-aware network intrusion detection system (C-NIDS) model was developed using factorized and grouped convolution structures to detect adversarial attacks in virtual and physical environments. A verifiable off-chain aggregation technique with a digital signature is implemented to provide a trustworthy and anti-tampering aggregated model with minimum transaction time. The results exhibit the robustness of the proposed model by achieving an attack detection accuracy of 99.50% using a lightweight model structure with trainable parameters of 4,634 and MFLOPs calculation of 0.0088. Moreover, the verifiable off-chain aggregation performs a total transaction time of 0.0244 seconds.

In the realm of dynamic fog networks, the imper-ative to efficiently offload delay-sensitive tasks while minimizing latency remains a formidable challenge. To address this, we propose a novel approach termed Digital Twin-empowered Contextual Bandit Learning based Matching (DT-CBLM). This framework harnesses the synergistic power of digital twins, which provide virtual representations of physical devices and environments, and contextual bandit learning techniques. By integrating digital twins into the task offloading process, DT-CBLM enables intelligent task-peer matching by considering contextual information such as device status, network conditions, and task characteristics. Through adaptive offloading strategies, DT-CBLM aims to minimize task completion latency while optimizing resource utilization and system efficiency in dynamic fog environments. Theoretical foundations, algorithmic details, and empirical evaluations showcase the efficacy of DT-CBLM in enhancing system performance.

This paper presents a novel approach utilizing Multi-Armed Bandit (MAB) for parallel computation in dynamic fog computing networks. Fog computing, vital for processing data near the network edge, faces challenges in task allocation while maintaining performance. To address this, a decentralized matching approach leveraging MAB learning algorithms is proposed. Using Thomson sampling (TS), tasks are allocated based on resource availability and network conditions. This decentralized approach empowers fog nodes to autonomously make offloading decisions, enhancing adaptability. Extensive simulations demonstrate the effectiveness of the proposed method in reducing task completion time and optimizing resource utilization in dynamic fog computing environments.

Matching theory has been efficiently applied in fog computing networks (FCNs) to design distributed task offloading algorithms in the presence of selfishness and rationals of fog nodes. Given the dynamic nature of fog computing environment, it is challenging to obtain the stable matching since the preference relations of two sides of matching game is unknown a prior. To address this challenge, this paper proposes RL-MATCH, a framework for parallel computation offloading in dynamic fog computing networks (FCNs). RL-MATCH is based on the matching theory and Thompson Sampling (TS) empowered Multi-Armed Bandit (MAB) learning to deal with the inherent challenges allowing task nodes with needed computation tasks to estimate the informed preference relations of helper nodes with available computing resource quickly and accurately. Extensive simulation results demonstrate the potential advantages of the TS based learning over the$\epsilon$-greedy and upper confidence bound (UCB) based baselines.

Abstract This paper proposes a whale optimization algorithm (WOA)‐based partial transmit sequence (PTS) scheme called WOA‐PTS to reduce the high peak‐to‐average power ratio (PAPR) for universal filtered multi‐carrier (UFMC) systems. High PAPR is a prevalent challenge encountered in multi‐carrier systems. In the conventional PTS technique, the optimization of phase rotation factors is achieved through multiplication with the sub‐blocks. In this undertaking, WOA optimization is integrated as a phase optimizer in the PTS‐based PAPR reduction scheme. The experimental results show that, when compared with PTS‐based UFMC signal, the UFMC signal with WOA‐PTS can achieve 4.15 dB PAPR reduction at the complementary cumulative distribution function value of 10 −3 , additionally power spectral density performance and bit error rate also improved.

The heterogeneous connections in metaverse environments pose vulnerabilities to cyber-attacks. To prevent and mitigate malicious network activities in a distributed metaverse, conventional intrusion detection systems (IDS) have communication overhead and privacy concerns. Federated learning (FL) techniques are widely employed to develop IDS frameworks and enable privacy-preserving collaborative learning schemes in decentralized ecosystems. However, the vanilla FL system utilizes a centralized FL aggregation technique, which introduces a single point of failure (SPoF) and potential unauthorized aggregators, allowing malicious clients to inject false data parameters, known as poisoning attacks. Furthermore, low-quality clients in the FL system can result in degraded model performance and hinder convergence. This study proposes a secure and reliable blockchain-aided federated learning (BFL)-based IDS framework using a lightweight model for securing metaverse. An authorized federated IDS is proposed to establish a trustworthy decentralized aggregation mechanism, utilizing proof-of-authority (PoA) consensus. The proposed federated IDS implemented a hybrid client selection (HCS) technique, considering the accuracy and reputation of client histories, to select high-quality metaverse edge devices. Additionally, a fairness ERC-20 token-based incentive mechanism was developed to reward selected FL clients as a token of appreciation for their contribution to the FL training processes. According to the IDS framework measurements, the proposed model performs better than the existing approaches for detecting cyber-attacks in metaverse environments, achieving an accuracy of 99.28% with trainable parameters of 1.8K and mega floating-point operations (MFLOPs) of 0.0016.

The accelerated industrial transformation has witnessed the supervisory control and data acquisition (SCADA) transit from monolithic to the Internet of Things (IoT-SCADA). The development also transformed conventional specialized serial-based to transmission control protocol/internet protocol reliant standard communication protocols, such as IEC-60870-5-104 (IEC-104), thereby increasing vulnerability to attacks and intrusions. Maintaining the reliability and availability of IoT-SCADA demands versatile and robust monitoring of network traffic. This study proposes a monitoring technique to detect and characterize the IEC-104 IoT-SCADA network traffic. The proposed trees bootstrap aggregation monitoring technique of GridSearchCV() hyperparameter tuning of 11 n-estimator, 20 max-depth, and 5-k cross-validation achieved early detection and characterization. Experimental results demonstrate its sensitivity and precision in detecting and classifying various network traffic and application types at a minimal execution time while reducing false alarm rates, which is vital for mitigating intrusions in heterogeneous IoT-SCADA networks.

The immersive metaverse environment offers distinct social interactions and opportunities, yet it also presents significant challenges in securely managing misbehavior, including hate speech, bullying, and harassment. Existing solutions primarily focus on detecting such behavior through artificial intelligence but lack robust mechanisms for management and governance. This gap is critical as the metaverse continues to mirror complex real-world interactions and centralized authority systems prove vulnerable to compromise. Our research introduces a novel framework, Meta-Governance, which not only detects but also effectively manages and governs user behavior through smart contracts, ensuring a secure, fair, and transparent metaverse environment. The system incorporates behavior monitoring to identify and condemn inappropriate behavior, specifically targeting problems such as hate speech and cyberbullying. Occurrences of misbehavior are permanently preserved on the blockchain to ensure the capacity to trace and bear accountability. In this article, we deploy a Natural Language Processing (NLP) model and a smart contract-based framework to address unusual behavior monitoring, access control, and credit scoring. Deep learning models are used to identify and classify linguistic patterns that may be considered hazardous. Blockchain technology addresses virtual misconduct using smart contracts, while a distinctive credit scoring mechanism ensures that users are held responsible for making disrespectful statements. The efficacy of the proposed smart contract is comprehensively evaluated within the context of a private Hyperledger Besu system. The integration of AI and blockchain may greatly improve the security and inclusiveness of the metaverse, highlighting the crucial role of these technologies in combating hate speech and enhancing user engagement.

Matching theory has been applied to design efficient offloading solutions to the multi-task multi-helper (MTMH) problem in the fog computing networks, which is modeled as a matching game between a set of task nodes (TNs) having task computation needs and a set of helper nodes (HNs) having available computing resources. However, the uncertainty of computing resource availability of HNs as well as dynamics of QoS requirements of tasks result in the lack of preferences of TN side that mainly poses a critical challenge to obtain a stable and reliable matching outcome. To address this challenge, we apply a multi-armed bandit (MAB) learning using Thomson sampling (TS) mechanism to acquire better exploitation and exploration trade-off, allowing TNs to match with their corresponding HNs efficiently. Based on these, this paper proposes online learning based matching (OLM) algorithm for decentralized task offloading to reduce the offloading delay in Fog-enabled IoT Systems. Extensive simulation results demonstrate the potential advantages of the TS-type algorithm over the $\epsilon$-greedy and UCB based offloading algorithms.

Fog computing technology has developed to support delay-sensitive applications by offering shared and adaptable communication, computation, and storage resources along the cloud-to-things continuum in Internet of Things (loT) and cyber-physical systems (CPS). In order to minimize the delay of every task, task nodes (TNs) with computation-intensive and delay-sensitive tasks should have efficient strategies to select the optimal helper nodes (HN s) having spare computation resources for task offloading operations. However, the dynamic nature of fog computing environment characterized by the time varying change of HN computing resources as well as various types of tasks with different quality of service (QoS requirements) impose as inherent challenges for designing the efficient task offloading algorithms. To deal with these challenges, we apply the principle of multi-armed bandit (MAB) learning method to efficiently learn the uncertainty of fog computing environment. In particularly, we use Thomson sampling (TS) technique to acquire better exploitation and exploration trade-off, allowing TNs to select their corresponding HN s efficiently. Extensive simulation results demonstrate the potential advantages of the TS-type algorithm over the$\epsilon-\mathbf{greedy}$and U CB based offloading algorithms.

Abstract The rampant deployment of data distribution service (DDS) as middle‐ware service providers for industrial network platforms has been widely investigated. All DDS‐based node discovery protocols establish communication with its intended target systems by accessing matched endpoints/nodes information. These matched endpoints/nodes information is usually embedded with the system’s programmable control plane network which acts as the conveyor vehicle. The introduction of software defined networking (SDN) is to characterize the control plane from embedded data plane. The DDS implements the simple discovery protocol (SDP) as its inherent node discovery protocol. Deploying DDS for data packet exchange in server‐based collaborative distributed networked control (DNC) systems has gained traction. The current automatic discovery protocol (ADP) based on SDP is fraught with real‐time limitations such as high memory consumption and poor packet transmission. This work presents novel memory‐efficient automatic discovery data distribution service (MAD‐DDS) with enhanced threshold bloom filters (ETBF) where ETBF stores transmission packets at simulation end‐nodes. The packet is further adjusted using optimized binarization and decision thresholds inside ADP, hence guaranteeing memory reduction. The testbed computation recorded significantly improved quality of service (QoS) whereas numerical results depict significant decline in memory consumption with consistent packet transmission rates that produces increased computational capacity.

The pervasiveness in the industrial internet of things (IIoT) due to the application of supervisory control and data acquisition (SCADA) has led to the growth of heterogeneous sensor data, thereby increasing the risk of intrusions and attacks. The existence and effect of intruders and their innovative attack techniques are on the rise. Existing intrusion detection systems (IDS) tend to be computationally expensive with this form of data due to the presence of noise. In real-time domains, available methods lag, necessitating additional research into effective feature extraction schemes, which is fundamental in machine learning (ML) for time exigency. This study, in a comparative analysis of some feature selection techniques (FS), proposes a combination of an efficient ML classifier and an agnostic feature selection (FS) scheme for attack detection and classification in a real-time SCADA network. The flexibility and interoperability of the proposed approach resolve the computational complexity of vulnerability detection schemes while reducing false alarm rates (FAR) and overall model execution time. With the view of an online preprocessing, the proposed technique is phased thus: (i) data preparatory consisting of data cleansing and normalization followed by (ii) the combination of a pre-pruned decision tree (DT) algorithm and an agnostic Chi-square FS approach built to obtain an optimal subset of data features for efficient IDS. (iii) Evaluation of proposed agnostic DT-CH and other FS candidates for anomaly detection.

The intelligence and integrity of a real-time cyber–physical system depend on how trustworthy the data’s legitimacy, appropriation, and authorization are during end-to-end communication between the participating nodes in its network. With the recurrent repugnant global violations of the airspace by drones and their derivatives, there is an urgent need to empirically evaluate the underlying security architectures that govern drone usage operations for priority logistics. This review examines the significant contribution of artificial intelligence models and blockchain to the development of trustworthy and reliable intelligent and secure autonomous systems by integrating cyberspace, intelligence space, and airspace security. PRISMA-SPIDER methodology was adopted for the systematic review of 133 articles based on the inclusion criteria consisting of 91 (68.4%) quantitative studies, 19 qualitative studies (14.2%), and 23 (17.3%) mixed method studies to balance article selection sensitivity and specificity. The review outcome shows a significant disconnect between model proposals and actual implementation. Through the incorporation of zero-trust architecture into the existing blockchain technology and the convergence of newer AI models, dynamic security issues like drone ownership authentication, drone package delivery verification, drone operation authorization, and drone jurisdiction accountability, can be achieved seamlessly for secure smart mobility via drone transportation systems.

Unmanned aerial vehicle (UAV) contributes substantial strategic benefits on the Internet of Military Things (IoMT). However, the untrusted party’s misuse of the UAV may violate the security and even demolish the critical operation in the IoMT system. In addition, data manipulation and falsification using unauthorized access are the significant challenges of the IoMT system. In response to this problem, this study proposes a blockchain-integrated convolution neural network (CNN)-based intelligent framework named IoMT-Net for identification and tracking illegal UAV in the IoMT system. Blockchain technology prevents illicit access, data manipulation, and illegal intrusions, as well as stored data on the central control server (CCS). Concurrently, the proposed CNN analyzed the radio-frequency (RF) signal sent by the antenna array element to determine the Direction of Arrival (DoA) for the localization of the illegal UAV. Therefore, a signal model is designed to process the received signal array through IoMT-Net. Moreover, the proposed CNN model is designed with two different functional modules, such as the resource accuracy tradeoff (RAT) module and the unique feature extraction and accuracy boosting (UAB) module, by adopting depthwise and grouped convolution layers. These sparsely connected convolution layers offer high DoA estimation accuracy while maintaining the network more lightweight. In addition, the skip connection is also leveraged into the subunits of RAT and UAB modules for sharing features and handling the vanishing gradients problem. Based on the simulation results, the proposed network achieves superior DoA estimation accuracy (approximately 97.63% accuracy at 10-dB SNR) and outperforms other state-of-the-art models.

The dynamic nature of the vehicular space exposes it to distributed malicious attacks irrespective of the integration of enabling technologies. The software-defined network (SDN) represents one of these enabling technologies, providing an integrated improvement over the traditional vehicular ad-hoc network (VANET). Due to the centralized characteristics of SDN, they are vulnerable to attacks that may result in life-threatening situations. Securing SDN-based VANETs is vital and requires incorporating artificial intelligence (AI) techniques. Hence, this work proposed an intrusion detection model (IDM) to identify Distributed Denial-of-Service (DDoS) attacks in the vehicular space. The proposed solution employs the radial basis function (RBF) kernel of the support vector machine (SVM) classifier and an exhaustive parameter search technique called grid search cross-validation (GSCV). In this framework, the proposed architecture can be deployed on the onboard units (OBUs) of each vehicle, which receive the vehicular data and run intrusion detection tasks to classify a message sequence as a DDoS attack or benign. The performance of the proposed algorithm compared to other ML algorithms using key performance metrics. The proposed framework is validated through experimental simulations to demonstrate its effectiveness in detecting DDoS intrusion. Using the GridSearchCV, optimal values of the RBF-SVM kernel parameters “C” and “gamma”$(\gamma)$of 100 and 0.1, respectively, gave the optimal performance. The proposed scheme showed an overall accuracy of 99.33%, a detection rate of 99.22%, and an average squared error of 0.007, outperforming existing benchmarks.

The goal of this study is to offer a novel fog data prediction and recovery (FDPR) algorithm that uses deep learning (DL) to forecast and recover missing sensor data in an Internet of Things (IoT) network. Because of the fog layer’s unique qualities compared to other IoT environment layers, the FDPR algorithm is employed in this layer. The most recent studies generally concentrate on data recovery or prediction, with few assessment metrics. In this work, an algorithm that can handle both data prediction and recovery is provided. With the proposed FDPR approach, data prediction and recovery are dealt with by an effective DL network, namely, a deep concatenated multilayer perceptron (DC-MLP). The algorithm consists of a prediction function that forecasts future sensor data for a specified round of data transmission and a recovery function that recover one or two missing data points. The evaluation of the proposed algorithm is performed with simulation and experimental works. Initially, a data set is collected, preprocessed, and fed to various DL models using$K$-fold cross-validation. These DL models are then converted and embedded into a fog layer in the experimental work with nine edge devices. In both simulation and experimental evaluation, the FDPR with DC-MLP can predict future data and recover missing data with an average accuracy of 99.89% while slightly increasing network delay by 2.5 ms compared to traditional IoT. Aside from a slightly increased delay, a 121% improvement in IoT device lifetime is achieved using the FDPR algorithm due to data transmission reduction.

Software-defined networking (SDN)-based Industrial Internet of Things (IIoT) networks have a centralized controller that is a single attractive target for unauthorized users to attack. Cybersecurity in IIoT networks is becoming the most significant challenge, especially from increasingly sophisticated Distributed Denial-of-Service (DDoS) attacks. This situation necessitates efficient approaches to mitigate recent attacks following the incompetence of existing techniques that focus more on DDoS detection. Most existing DDoS detection capabilities are computationally complex and are no longer efficient enough to protect against DDoS attacks. Thus, the need for a low-cost approach for DDoS attack classification. This study presents a competent feature selection method extreme gradient boosting (XGBoost) for determining the most relevant data features with a hybrid convolutional neural network and long short-term memory (CNN-LSTM) for DDoS attack classification. The proposed model evaluated the CICDDoS2019 data set with improved accuracy and low-complexity capability for low latency IIoT requirements. Performance results show that the proposed model achieves a high accuracy of 99.50% with a time cost of 0.179 ms.

Falsification detection is a critical advance in ensuring that real-time information about vehicles and their movement states is certified on the Internet of Vehicles (IoV). Thus, detecting nodes that are propagating inaccurate information is a requirement for the successful deployment of IoV services although only a few research studies have been carried out on Basic Safety Message (BSM) falsification. As such, this paper proposes a Randomized Search Optimization Ensemble-based Falsification Detection Scheme (RSO-FDS). The RSO technique was used to construct the proposed Ensemble-based Random Forest (RF) model. The evaluation was performed on three different datasets developed to evaluate falsification in IoV. In addition, the six most popular supervised learning (SL) algorithms were investigated to evaluate the capability of the proposed RSO-FDS, which had the best performance across all datasets. The performance metrics considered are computational efficiency in terms of prediction time, validation accuracy for overall attack classification, precision, recall, and F1 scores. For validation, the performance of the proposed RSO-FDS was further compared with results from recent works. Furthermore, the irrelevance of data balancing was illustrated for real-life IoV scenarios. The result shows that the proposed model outperformed state-of-the-art algorithms implemented in this work and related works.

Preventive measures to stop copyright infringement are yet to be implemented on current decentralized music-sharing platforms. There is no mechanism to reject modified audio before they go online, so some decentralized music platforms become places full of pirated audio files. To address this problem, a perceptual hash-based audio detection method for copyright protection in decentralized music sharing was proposed. Chromaprint, an open-source audio fingerprint program, generates a hash value to detect copyright infringement. To assess the perceptual hash technique’s robustness, Chromaprint generates a hash value from an audio file that can be modified with several signal processing attacks. The results of the detection system show that Chromaprint is very effective at spotting copyright infringement, with an average match rate of 92.64%. Deployed using a public Ethereum blockchain test network, the execution time from hashing to uploading to the IPFS distributed storage is only 616.3 ms.

Unauthorized users may attack centralized controllers as an attractive target in software-defined networking (SDN)-based industrial cyber-physical systems (CPS). Managing high-complexity deep learning (DL)-based intrusion classification to recognize and prevent attacks in the industrial Internet of Things (IIoT) networks with low-latency requirements is challenging. Moreover, a centralized DL-based intrusion detection system (IDS) leads to privacy concerns and communication overhead issues during data uploading to a cloud server for training processes in IIoT environments. This study proposes federated learning (FL)-based low-complexity intrusion detection and classification in SDN-enabled industrial CPS. This framework utilizes Chi-square and Pearson correlation coefficient (PCC) feature selection methods to select potential features, which help reduce the model’s complexity and boost performance. The proposed model evaluated the SDN and IIoT-related InSDN and Edge-IIoTset datasets. The model measurement shows that the proposed model achieves high accuracy, low computational cost, and a low-complexity model architecture compared with state-of-the-art approaches.

The constant development and deployment of the supervisory control and data acquisition (SCADA) in the industrial internet of things (IIoT) have enabled vast communication leading to the generation of large volumes of sensor data. This phenomenon has increased SCADA’s susceptibility to vulnerability and attacks which calls for attack detection mechanisms. Existing systems only aim at detection accuracy without considering the effect of false alarm rates in large sensor data. To resolve this issue, we propose a Rational Quadratic Gaussian Process Regression (RQGPR) for the effective reduction of false alarm rate and improved prediction precision. In this algorithm, a Gaussian process regression model is trained with recourse to kernel functions to precisely predict attacks and reduce false alarms. The RQGPR outperforms all other kernels in the reduction of false alarm rates. Through simulations, we show that the proposed model reduces the false alarm rate up to 71.73% higher than other kernels. This result was validated by evaluating the CIRA-CIC-DoHBrw-2020 datasets, which also had a reduction rate of 67.61%. In addition, it also showed superior performance when compared with other state-of-the-art models.

Achieving communication intelligence with a low computational cost is necessary for wireless sensor networks for the drone transportation system. This work proposed a novel localization system with low computational and time efficiency that uses an unmanned aerial vehicle (UAV) as anchor node and lightweight neural networks to evaluate the UAV position information. The scheme takes advantage of the capabilities of artificial intelligence models. Simulation results indicate that the proposed scheme displayed a good performance with the least localization error of 1.75, least training time of 0.0032s, and testing time of 0.00039s without requiring GPS when compared to other algorithms and previous schemes.

The proliferation and wide usage of the Internet of Things (IoT) and related information and communication technologies (ICT) have led to the emergence of smart cities which comprises ubiquitous sensors, and heterogeneous network architectures. These cities are capable of relaying real-time information about the world which can then be used to improve the Qualify of Life (QoL). However, due to the unprecedented access to the city and personal data by smart city applications, there is an increase in both security and privacy threat. In this study, we propose a stacked generalization machine learning algorithm for the detection of cyberattacks in a smart city. The algorithm was tested using datasets from various smart city infrastructures. Simulation results show a high detection accuracy.

The metaverse is a virtual world that is based on numerous technologies. One of such technologies is the wireless communication system. Specifically, 5G wireless communication will have a role to play in the development of the metaverse. Since the metaverse has features that require certain service requirements, it is necessary to analyze the specific benefits that 5G has to offer. The aim of this paper is to discuss the features of the metaverse, the service offerings of 5G standards of communication, and how 5G can help make the metaverse a reality.

In typical air traffic control (ATC) scenario where it is apparently challenging to deploy aircraft for special missions as reconnaissance and surveillance, a proposed ACD-UKF model becomes suitable especially where operational flexibility and without manual aircraft-turning are prioritized objectives. In this paper, novel deep neural network model (DNN) enhanced accurate continuous-discrete unscented Kalman filtering (ACD-UKF) model for a radar’s ordinary differential equation (ODE) solver system navigation tool is presented. The ODE solver system essentially works to control radar navigation parameters with-respect-to (w.r.t) global error control, monitoring metrics and tracking capabilities. With the proposed DNN scheme, limitations resulting from matrix factorization are addressed. A seven-dimensional (7-D) radar tracking drawback in con-strained condition is mirrored, allowing the deployed aircraft to conduct supervised turns using the proposed ACD-UKF model. Performance evaluation was then conducted where real-time factors such as the system’s outage thresholds, network sum-rate and yaw differences for the global navigation satellite system (GNSS) propelled aircraft radar tracker data-set, in stationary and in accelerating positions were trained and validated using the proposed DNN model.

This work proposes the use of blockchain for offline voting. Using the Smart contract feature of the Ethereum blockchain network. The voter’s registration is made. An offline token is generated which is used for offline voting. The offline token and the voting information are sent to the vote counters Smart contact. This is where the votes are counted and results extracted. However if a voter can share the cast vote to another voter who will send the new token to the vote counters. In a situation a vote is submitted by multiple voters, the counter has the ability to identify and count such votes only once.

Internet of Things (IoT) devices generates massive amounts of data continuously, making it difficult to combine this data at the edge node or central edge server for AI techniques to be applied, especially on low-bandwidth networks. Traditional computation offloading involves extensive resource management, queuing, and high bandwidth usage to send data from an edge device to a server. To mitigate this challenge, federated learning is applied in this paper, to offload the computation of the edge server. Simulation results show the efficiency of the proposed method over the centralized method.

Software-defined networks (SDN)-based industrial cyber-physical systems (CPS) enable customizing development opportunities with integrated network interconnection to perform monitoring, measurement, control system, and security tasks. The extensive connectivity and the vast amount of data exchange in the SDN-based industrial CPS environment make it vulnerable to cyberattacks. Furthermore, an SDN controller is a single attractive target for an attack. It is challenging when the SDN controller manages DL-based high-complexity intrusion detection in an IIoT network with low latency requirements to identify and prevent attacks. This study proposes a lightweight intrusion detection model in an SDN-based industrial CPS environment. The proposed model was evaluated using a recent publicly SDN-related cyber-security InSDN dataset. The experimental results show that the proposed model outperforms the state-of-the-art by achieving 98.95% accuracy, 99.00% precision, 98.91% recall, and a 0.164 ms time cost when using the LightGBM feature selection technique.

As unmanned aerial vehicles (UAVs) are progressively deployed for logistics purposes, there is need for paradigm shift from mere drone detection to proactive identification of the conveyed objects and proper risk assessment from a far distance. This paper proposed a timely, efficient, accurate, and situation-aware (TEAS) mission critical operation approach for detecting, localizing, and neutralizing UAVs under 3 scenarios (sunny, cloudy, and evening) and different altitudes using vision- based deep learning model. Two manually generated datasets consisting of 7200 samples from 6 UAV models and 3600 samples from 9 conveyed objects were used for simulation purposes. The proposed model was compared with 7 state-of-the-art models based on selected performance metrics. The results shows that the proposed model achieved superior mean average precision of 99.5%, 100% sensitivity, 11.2% specificity, 21.5% G-mean, and 99.8% F1-score with a latency of 0.021s, and throughput of 16.4 Gbps, which is better than other models. The model also exhibited high efficiency with cost noise at 0.037, and high reliability with minimal detection error which makes it suitable for mission critical operation of proactive and situation-aware countering of drones.

Fog computing systems (FCS) have been widely integrated in the IoT-based applications aiming to improve the quality of services (QoS) such as low response service delay by performing the task computation nearby the task generation sources (i.e., IoT devices) on behalf of remote cloud servers. However, to achieve the objective of delay reduction remains challenging for offloading strategies due to the resource limitation of fog devices. In addition, a high rate of task requests combined with heavy tasks (i.e., large task size) may cause a high imbalance of workload distribution among the heterogeneous fog devices. To cope with the situation, this paper proposes a dynamic task offloading (DTO) approach, which is based on the resource states of fog devices to derive the task offloading policy dynamically. Accordingly, a task can be executed by either a single fog or multiple fog devices through parallel computation of subtasks to reduce the task execution delay. Through the extensive simulation analysis, the proposed approaches show potential advantages in reducing the average delay significantly in the systems with high rate of service requests and heterogeneous fog environment compared with the existing solutions.

In this paper, we propose a deep learning (DL)-based method to automatically identify the modulations of orthogonal frequency-division multiplexing (OFDM) signals in wireless communication systems. In particular, a cost-efficient OFDM modulation classification convolutional neural network (COM-ConvNet) is principally designed with grouped convolutional layers to reduce computing complexity significantly. Remarkably, reconstructing the high-dimensional data array of OFDM signals allows our deep network to learn the underlying sample correlations within every symbol and among different symbols sufficiently. We leverage residual connection and attention connection with element-wise addition and element-wise multiplication layers in specific-designed processing blocks to enhance the pattern learning efficiency. For performance evaluation, we test the proposed method on a synthetic six-modulation OFDM signal dataset under impaired channel conditions and conduct diverse simulations, such as ablation study, parameter investigation, and complexity analysis. COM-ConvNet achieves cost efficiency (i.e., small network size and low computational cost) while maintaining an acceptable accuracy when compared with other DL models.

Abstract This work proposes smart auto mining (SAM) for resource‐efficient mining in a blockchain network. The SAM algorithm stops the miners when there is zero pending transaction and starts the miner when there is at least one transaction sent into the network. The miner listens to the network to identify when a transaction has been made by a node. The model does not need any instruction to start mining when there is a pending transaction. The results show that a private Ethereum network produced over 300% more blocks in a 12‐h period with 599,950 transactions compared to when SAM is applied. The proposed algorithm is also able to reduce the storage used by the chaindata by 14%. The overhead of mining is decreased by reducing the production of empty blocks in the network which saves energy, storage space, network bandwidth and computational complexity.

Internet of Things (IoT) networks are key to the realization of modern industries and societies. A key application of IoT is in smart-grid communications. Smart-grid networks are resource constrained in terms of computing power and energy capacity. Similarly, the wireless links between devices are typically associated with high packet-loss rates, low throughput, and instability. To provide a sustainable communication mechanism, an IoT network stack is proposed for these devices. However, each network stack layer has its own constraints. For example, to facilitate the operation of these low-power and lossy network (LLN) devices, the international engineering task force (IETF) standardized a network-layer protocol called a routing protocol for low-power and lossy networks (RPLs). RPL often creates an inefficient network in densely deployed and varying traffic load conditions. Future dense IoT-based networks are expected to automatically optimize the reliability and efficiency of communication by inferring the diverse features of both the environments and actions of the devices. Machine learning (ML) provides a promising framework for such a dense network environment. In this study, we examine the underlying perspective of ML for such systems. We utilize the multiarmed bandit (MAB)-based expected energy count (BEEX) technique, which provides nodes the ability to effectively optimize their operation. Using the proposed mechanism, nodes can intelligently adapt their network-layer behavior. The performance of the proposed (BEEX) algorithm is evaluated through a Contiki 3.0 Cooja simulation. The proposed method improves the energy consumption and packet delivery ratio and produces a lower control overhead than other state-of-the-art mechanisms.

In oceanic remote sensing operations, underwater acoustic target recognition is always a difficult and extremely important task of sonar systems, especially in the condition of complex sound wave propagation characteristics. The expensively learning recognition model for big data analysis is typically an obstacle for most traditional machine learning (ML) algorithms, whereas the convolutional neural network (CNN), a type of deep neural network, can automatically extract features for accurate classification. In this study, we propose an approach using a dense CNN model for underwater target recognition. The network architecture is designed to cleverly reuse all former feature maps to optimize classification rates under various impaired conditions while satisfying low computational cost. In addition, instead of using time–frequency spectrogram images, the proposed scheme allows directly utilizing the original audio signal in the time domain as the network input data. Based on the experimental results evaluated on the real-world data set of passive sonar, our classification model achieves the overall accuracy of 98.85% at 0-dB signal-to-noise ratio (SNR) and outperforms traditional ML techniques, as well as other state-of-the-art CNN models.

Solar irradiance prediction is an indispensable area of the photovoltaic (PV) power management system. However, PV management may be subject to severe penalties due to the unsteadiness pattern of PV output power that depends on solar radiation. A high-precision long short-term memory (LSTM)-based neural network model named SIPNet to predict solar irradiance in a short time interval is proposed to overcome this problem. Solar radiation depends on the environmental sensing of meteorological information such as temperature, pressure, humidity, wind speed, and direction, which are different dimensions in measurement. LSTM neural network can concurrently learn the spatiotemporal of multivariate input features via various logistic gates. Moreover, SIPNet can estimate the future solar irradiance given the historical observation of the meteorological information and the radiation data. The SIPNet model is simulated and compared with the actual and predicted data series and evaluated by the mean absolute error (MAE), mean square error (MSE), and root MSE. The empirical results show that the value of MAE, MSE, and root mean square error of SIPNet is 0.0413, 0.0033, and 0.057, respectively, which demonstrate the effectiveness of SIPNet and outperforms other existing models.

This article presents a novel reconfigurable physical resource block (PRB), where long-term evolution (LTE) and mobile cell-edge terminals are interfaced using low-power tunable second-order$G_{m}-C$filter beamforming circuit, hence achieving an uplink–downlink (UL-DL) cellular system. A total of ten wireless multipoint (MP) terminals were structured and investigated. The BS-to-UAV-enabled terminals are propagated by line-of-sight (LoS) and nonline-of-sight (NLoS) beamforming. The subordinate terminals are handled using the derived Rayleigh signal distribution expressions. To guarantee higher frequency shift, the embedded control logic (CL) circuit is modeled upon the NMOS low dropout (LDO) regulator configurations with center frequency of 9.2 MHz and pass band of 1.4 MHz. The quality factors for both the first and second poles remain stable at 4.1 and 6.5 respectively. Stochastic analysis of the anticipated signal impacts with further estimation of its inherent variation challenges within the confined spectrum-sharing zone was corroborated. Our work is validated using an introduced direct and relay network density variations. The model’s performance evaluation compliments a ≥ 45.3-dB gain, an optimal transmission power and robust network sum rates in both LoS and NLoS conditions.

Ensuring secured and reliable dissemination of information for a mission-critical system such as the Internet of Vehicle (IoV) in real-time is of utmost importance. In this work, a False Location Detection System (FLDS) based on an optimized Ensemble Random Forest (Ens.RF) was proposed. The performance of the Ens.RF was compared with four other Machine Learning (ML) algorithms, using the Veremi dataset where five (5) different location falsification categories and one benign category were modeled. To validate the idea in this work, a performance comparison with recent work was presented. The result shows that the proposed Ens.RF outperformed other algorithms modeled in this work as well as related works with an accuracy of 99.92%

With the expanding diversity of Internet of Things (IoT), more IoT networks are now being attacked easily by aggressors without being easily distinguished as they adapt network traffic characteristics similar to the victim's network. The consequences are the opportunities to gain control of the secure communication antagonistically, influencing internal information and prompting harms to the physical components of the IoT framework without being distinguished quickly. Anomaly-based Identification (AID) has enabled the possibility of solving this problem by helping to detect novel attacks by skimming and authenticating the IoT network designs, with higher accuracy using machine learning (ML) classification. In this work, a stacked ensemble (SE) machine learning classification approach is utilized to investigate IoT network traffic characteristics for improving novel detection of malware and noxious exercise in gadgets. The SE classifier was composed of base and meta-classifiers. The base level consisted of four classifiers; decision tree (DT), gaussian support vector machine (GSVM), ensemble DT, and naive bayes (NB). This classifiers are applied to IoT Network Intrusion Dataset from HCRLab, Korea University and sent trained data to meta classifier which was further employed to detect binary classification on test data. The experimental results shows that SE classifier achieved 99.8% accuracy with lower loss value 0.0020861 and 0.9994 precision. This application can be promising insights into the AID-based security of IoT for effective industry and/or smart factory management.

This paper proposes a system to reduce sensor energy consumption by predicting the next sensor value. The current implementation of the smart factory utilizes wireless sensor network nodes to monitor the environmental condition in real-time. Instead of periodically exploiting those nodes, a deep learning prediction-based algorithm is proposed in the cluster head to reduce sensing times and increase sensor lifetime. The cluster head can learn the behavior of each sensor nodes based on its previous value. The proposed scenario can be combined with existing solutions in sensor failure detection and recovery to provide a robust solution in the industrial environment.

This paper presents a deep learning-based method to automatically recognize low probability of intercept (LPI) radar waveforms against diversified jamming attacks. Concretely, an efficient convolutional neural network (CNN) architecture, namely Densely-Accumulated Network (DANet), is introduced to learn the time-frequency representation transformed by the Wigner-Ville distribution. Such an architecture has several novel densely-accumulated connection modules specified by various symmetric and asymmetric convolutional layers to enrich diversified features at multiple representational maps. Besides, the skip-connection and dense-connection are leveraged to improve feature learning efficiency and prevent the vanishing gradient when the network goes deeper. Some image processing techniques (e.g., global thresholding and digital filtering) are adopted to enhance the quality of time-frequency image. Relying on simulations, we benchmark the proposed method on a synthetic 13-waveform dataset and also investigate the influence of hyper-parameters (such as image size, number of modules, training data size) on the overall recognition performance. Remarkably, with average accuracy of 98.2% at 0 dB signal-to-noise ratio (SNR), DANet outperforms several backbone CNNs and state-of-the-art networks of LPI waveform recognition while keeping a cost-efficient model.

Nowadays, enhancing the living standard with smart healthcare via the Internet of Things is one of the most critical goals of smart cities, in which artificial intelligence plays as the core technology. Many smart services, deployed according to wearable sensor-based physical activity recognition, have been able to early detect unhealthy daily behaviors and further medical risks. Numerous approaches have studied shallow handcrafted features coupled with traditional machine learning (ML) techniques, which find it difficult to model real-world activities. In this work, by revealing deep features from deep convolutional neural networks (DCNNs) in fusion with conventional handcrafted features, we learn an intermediate fusion framework of human activity recognition (HAR). According to transforming the raw signal value to pixel intensity value, segmentation data acquired from a multisensor system are encoded to an activity image for deep model learning. Formulated by several novel residual triple convolutional blocks, the proposed DCNN allows extracting multiscale spatiotemporal signal-level and sensor-level correlations simultaneously from the activity image. In the fusion model, the hybrid feature merged from the handcrafted and deep features is learned by a multiclass support vector machine (SVM) classifier. Based on several experiments of performance evaluation, our fusion approach for activity recognition has achieved the accuracy over 96.0% on three public benchmark data sets, including Daily and Sport Activities, Daily Life Activities, and RealWorld. Furthermore, the method outperforms several state-of-the-art HAR approaches and demonstrates the superiority of the proposed intermediate fusion model in multisensor systems.

In the IoT-based systems, the fog computing allows the fog nodes to offload and process tasks requested from IoT-enabled devices in a distributed manner instead of the centralized cloud servers to reduce the response delay. However, achieving such a benefit is still challenging in the systems with high rate of requests, which imply long queues of tasks in the fog nodes, thus exposing probably an inefficiency in terms of latency to offload the tasks. In addition, a complicated heterogeneous degree in the fog environment introduces an additional issue that many of single fogs can not process heavy tasks due to lack of available resources or limited computing capabilities. To cope with the situation, this article introduces FRATO (Fog Resource aware Adaptive Task Offloading) - a framework for the IoT-fog-cloud systems to offer the minimal service provisioning delay through an adaptive task offloading mechanism. Fundamentally, FRATO is based on the fog resource to select flexibly the optimal offloading policy, which in particular includes a collaborative task offloading solution based on the data fragment concept. In addition, two distributed fog resource allocation algorithms, namely TPRA and MaxRU are developed to deploy the optimized offloading solutions efficiently in cases of resource competition. Through the extensive simulation analysis, the FRATO-based service provisioning approaches show potential advantages in reducing the average delay significantly in the systems with high rate of service requests and heterogeneous fog environment compared with the existing solutions.

In this paper, an algorithm to recover failure sensor data in real-time is proposed. In the current factory automation trends, each device senses the information directly, where humans are no longer involved in huge part of the task. The ability of the system to detect the failure in the device is one of the crucial issues as well as the ability to recover the data of the device when failure happens. The deep learning technique is proposed to learn the behavior of the sensor and to provide exact data as a recovery when the failure occurred. This scenario can be applied along with a faulty detection technique to provide seamless solutions in the current industrial environment.

Modulation classification, recognized as the intermediate step between signal detection and demodulation, is widely deployed in several modern wireless communication systems. Although many approaches have been studied in the last decades for identifying the modulation format of an incoming signal, they often reveal the obstacle of learning radio characteristics for most traditional machine learning algorithms. To overcome this drawback, we propose an accurate modulation classification method by exploiting deep learning for being compatible with constellation diagram. Particularly, a convolutional neural network is developed for proficiently learning the most relevant radio characteristics of gray-scale constellation image. The deep network is specified by multiple processing blocks, where several grouped and asymmetric convolutional layers in each block are organized by a flow-in-flow structure for feature enrichment. These blocks are connected via skip-connection to prevent the vanishing gradient problem while effectively preserving the information identity throughout the network. Regarding several intensive simulations on the constellation image dataset of eight digital modulations, the proposed deep network achieves the remarkable classification accuracy of approximately 87% at 0 dB signal-to-noise ratio (SNR) under a multipath Rayleigh fading channel and further outperforms some state-of-the-art deep models of constellation-based modulation classification.

Modulation classification, an intermediate process between signal detection and demodulation in a physical layer, is now attracting more interest to the cognitive radio field, wherein the performance is powered by artificial intelligence algorithms. However, most existing conventional approaches pose the obstacle of effectively learning weakly discriminative modulation patterns. This paper proposes a robust modulation classification method by taking advantage of deep learning to capture the meaningful information of modulation signal at multi-scale feature representations. To this end, a novel architecture of convolutional neural network, namely Chain-Net, is developed with various asymmetric kernels organized in two processing flows and associated via depth-wise concatenation and element-wise addition for optimizing feature utilization. The network is evaluated on a big dataset of 14 challenging modulation formats, including analog and high-order digital techniques. The simulation results demonstrate that Chain-Net robustly classifies the modulation of radio signals suffering from a synthetic channel deterioration and further performs better than other deep networks.

Recently, regarding several beneficial properties of depth camera, numerous 3D action recognition frameworks have studied high-level features by exploiting deep learning techniques, but nevertheless they cannot seize the meaningful characteristics of static human pose and dynamic action motion of a whole sequence. This paper introduces a deep network configured by two parallel streams of convolutional stacks for fully learning the deep intra-frame joint associations and inter-frame joint correlations, wherein the structure of each stream is learned from Inception-v3. In experiments, besides the compatibility verification with various backbone networks, the proposed approach achieves the state-of-theart performance in battle with several deep learning-based methods on the updated NTU RGB+D 120 dataset..

Recently, deep learning (DL) is an innovative machine learning (ML) technique that has gained the outstanding achievements in computer vision and natural language processing. This work takes advantage of DL for effectively handling automatic modulation classification (AMC), which is the fundamental function of numerous cognitive radio-based and spectrum sensing-based applications in many modern communication systems. Concretely, a novel deep convolutional neural network (DCNN) is proposed for learning a classification model from a massive amount of modulated signals, in which the network architecture has several convolutional blocks specialized to simultaneously capture the temporal intra-signal correlations and the spatial inter-signal relations. To this end, each block comprises various convolutional layers of asymmetric convolution kernels, whose outputs are gathered via a concatenation layer. For the enrichment of multi-scale deep feature and the prevention of gradient vanishing problem, these blocks are associated by skip connections to take into account the useful residual information. In experiments, the proposed CNN-based AMC method achieves the overall 24-modulation classification rate of 88.22% at 10dB SNR on the well-known DeepSig dataset.

Ultra‐reliable low‐latency communication (URLLC) is one of the promising services offered by fifth‐generation technology for an industrial wireless network. Moreover, reinforcement learning is gaining attention due to its potential to learn from observed as well as unobserved results. Industrial wireless nodes (IWNs) may vary dynamically due to inner or external variables and thus require a depreciation of the dispensable redesign of the network resource allocation. Traditional methods are explicitly programmed, making it difficult for networks to dynamically react. To overcome such a scenario, deep Q‐learning (DQL)‐based resource allocation strategies as per the learning of the experienced trade‐offs' and interdependencies in IWN is proposed. The proposed findings indicate that the algorithm can find the best performing measures to improve the allocation of resources. Moreover, DQL further reinforces to achieve better control to have ultra‐reliable and low‐latency IWN. Extensive simulations show that the suggested technique leads to the distribution of URLLC resources in fairness manner. In addition, the authors also assess the impact on resource allocation by the DQL's inherent learning parameters.

Recent emergent technologies with the advent of 5G use cases have made it imperative for high demands in broadband radio spectrum as compared to the current 4G technologies and other outdated ones. This study introduces an efficient spectrum management based on localisation of the primary user (PU) position in interweave cognitive radio networks (CRNs) towards 5G. In a typical network consisting of licensed system with PUs; and unlicensed system with secondary users (SUs), the SU opportunistically exploits the unused frequency bands of the licensed network provided there is no harmful interference to the PUs. Since the network is dynamic and the PUs are moving targets, the unused bands become unstable; hence, the SUs meet with limitations of detecting white spaces; finally resulting the interference. To this end, both Kriging interpolation and Kalman filter (KF) techniques for tracking and estimating the PUs position are proposed. The performance work was evaluated with respect to received signal strength indicator (RSSI) scheme. Both KF and Kriging interpolation outperformed RSSI. Moreover, the KF leads to the best performance compared to the other two as per localisation error prediction rate and system throughput; which makes it as the preferable technique to tackle mentioned challenges encountered by the SUs in such environment.

This study designs and presents routing protocols multi‐channel, multi‐hop cognitive radio sensor network (CRSN), which are based on spectrum sensing, spectrum‐availability analysis and per‐hop delay analysis. In order to cope with the spectrum dynamics in the CRSNs, a framework is proposed to estimate the remaining duration of spectrum availability which is based on the expected idle length of channels, sensing period and communication history on the channel. Such methodology allows cognitive users to mitigate communication interruptions caused by arrivals of primary users, thus to improve the transmission performance over each hop. In particular, in combination with the per‐hop delay analysis, the routing paths from sources to the sink can be established such as they provide the shortest delay opportunistically or shorter delay but reliable communication along the selected paths. Extensive simulation results show that the proposed routing algorithms potentially improve the network performances in terms of throughput, delay and energy consumption.

The Physical Internet (PI, or π) paradigm has been developed to be a global logistics system that aims to move, handle, store, and transport logistics products in a sustainable and efficient way. To achieve the goal, the PI requires a high-level interconnectivity in the physical, informational, and operational aspects enabled by an interconnected network of intermodal hubs, collaborative protocols, and standardized, modular, and smart containers. In this context, PI is a key player poised to benefit from the Internet-of-Things (IoT) revolution since it potentially provides an end-to-end visibility of the PI objects, operations, and systems through ubiquitous information exchange. This article is to investigate opportunities of application of the IoT technology in the PI vision. In addition, an IoT ecosystem (π-IoT) encompassing key enabling IoT technologies, building blocks, and a service-oriented architecture (SoA) is proposed as a potential component for accelerating the implementation of PI. The major challenges regarding the deployment of IoT into the emerging logistics concept are also discussed intensively for further research.

Recently, numerous methods have been introduced for three-dimensional (3-D) action recognition using handcrafted feature descriptors coupled traditional classifiers. However, they cannot learn high-level features of a whole skeleton sequence exhaustively. In this paper, a novel encoding technique - namely, pose feature to image (PoF2I), is introduced to transform the pose features of joint-joint distance and orientation to color pixels. By concatenating the features of all skeleton frames in a sequence, a color image is generated to depict spatial joint correlations and temporal pose dynamics of an action appearance. The strategy of end-to-end fine-tuning a pretrained deep convolutional neural network, which completely capture multiple high-level features at multiscale action representation, is implemented for learning recognition models. We further propose an efficient data augmentation mechanism for informative enrichment and overfitting prevention. The experimental results on six challenging 3-D action recognition datasets demonstrate that the proposed method outperforms state-of-the-art approaches.

Industrial image processing and computer vision play significant role in factory automation since industries now employ human-robot interaction for the monitoring of products in areas considered risky and dangerous for humans. The challenge however, is to ensure reliability in image processing such that image sizes and image similarity index are expected to be perfect representation of actual objects. This paper investigated the statistical relationship between the image ratio size and similarity index after compression. Using correlation analysis, a statistical relationship was established between the image size ratio and similarity index of selected images under review. It was observed that an inverse and high correlation existed between the image similarity index and image size ratio of compressed images. The result of the validation shows that the proposed regression model has predictability or good fit of 95%.

This paper proposes a bio-inspired service provisioning scheme for fog-based industrial Internet of Things (IIoT). We use wild-goats algorithm to address the adaptive fog service provisioning problem. Specifically, the master node is configured to monitor the network condition of all fog nodes inside of its domain. Then, the master node will distribute a service to the most suitable fog node based on network latency, computation cost, and storage cost. Therefore, the service can be accomplished in a real-time. The proposed method also considers a probability of node failure during the service provisioning process due to the harsh condition of IIoT environment. The results show that the proposed scheme can achieve low latency compared to the traditional architectures. The results also show that the node failure can escalate the latency of fog-based IIoT network. Thus, the adaptive service provisioning scheme is essential to maintain the network performance of fog-based IIoT.

This paper proposes a load balancing technique in which data traffic is balanced by sinks in a dynamic manner. It is directed to solve the problem of overload on one sink which result in high energy consumption and poor quality of experience in that area of the network. Sinks share responsibility of data aggregation equally throughout the network, by considering energy consumption and cluster size. The simulation works show how proposed routing protocol performance is close to ideal in ensuring all sink do equal work in the network and how network life in this approach varies with allowed time threshold.

Video-based human action recognition recently plays a vital role in many industrial applications thanks to the popularity of depth sensors. A large number of conventional approaches, which have combined handcrafted features and traditional classifiers, cannot deal with various challenges in the field such as the complexity of human actions in the realistic environment. In order to improve recognition performance by exploiting more high-level discriminative features, an efficient skeleton-based action recognition method using deep convolutional neural networks (CNNs) is studied with an image encoder to transform skeleton coordinate data to image-formed data. Since deep learning techniques are fundamentally designed for efficiently working with large datasets, the network overfitting usually occurs if training CNNs on small-scale datasets. To address this issue, a novel data augmentation technique is proposed for both the informative enrichment and overfitting prevention, wherein a skeleton sequence is depicted by manifold action images based on randomly adding some skeleton frames during the data transformation and preparation for the training set. Experimental results on several small-scale challenging datasets demonstrate that the proposed method outperforms state-of-the-art approaches in terms of action recognition accuracy.

This paper proposes a fast and reliable routing protocol (FaReli) for multi-channel, multi-hop cognitive wireless sensor networks (CRSNs). Being aware of the spectrum dynamics in the CRSN, a framework is proposed to estimate the remaining duration of spectrum availability which is based on the expected idle length of channels, sensing period, and communication history on the channel. Specially, in combination with the per hop delay analysis, the routing path from sources to the sink can be established such as it provides a shorter delay and reliable communication. Simulation results are conducted to demonstrate that the proposed routing algorithm based on spectrum and delay analysis potentially improve the network performances in terms of throughput, delay.

This work proposes a framework for distributed data analytic for precision agriculture based on seamless computing paradigm named SeamFarm. Generally, heterogeneous nodes deployed for precision agriculture where these nodes generated an extensive amount of data. Then machine learning can be used to analyze this data for precision agriculture. However, most of the IoT devices are resource-constrained devices, which results in poor performance while conducting a machine learning task. Thus, in SeamFarm, we consider distributing the data as well as the task to all available nodes. The results show that SeamFarm can meet all of the functional and non-functional requirements of distributed data analytic for precision agriculture. Moreover, it can obtain faster data analytic results.

This paper analyzes the reliability of cyber-physical energy systems with the integration of information and communication technology (ICT) and renewable distributed generation (DG) units. ICT architecture including multiple input multiple output (MIMO) systems that communicate with DG units and storage systems through ultra-reliable low-latency communication (URLLC) is proposed for cyber-physical energy systems. Reliability for URLLC is analyzed by measuring bit-error rate and signal to noise ratio performance metrics. The results show that more reliable and sustainable energy can be supplied to consumers with the integration of ICT and renewable DGs into the electrical power grid.

The paper proposes a novel adaptive traffic light scheduling scheme based on two-way traffic-light-to-vehicle communication (TLVC). The target of the paper is to use VANETs technologies to prevent traffic accidents caused by the rapid growth in the number of vehicles worldwide. In the proposed scheme, if vehicles are detected in a yellow-light-dilemma (YLD) zone when traffic light's color is yellow, a traffic light rescheduling algorithm is executed and speed guidance messages are sent to the vehicles to prevent YLD-related accidents happening. The preliminary simulation results show that the number of traffic light violation case caused by the YLD problem is greatly reduced by approximately 63% to 84%, which consequently reduces the number of YLD-related accidents at signalized intersections.

This paper proposes a framework to reduce overhead of controller-switch communication for industrial SDN-based Data Center Networks (DCN). The proposal focuses on OpenFlow (OF) to reduce the number of control messages, consisting of both PACKET_IN and PACKET_OUT messages handled by the OF controller during rule installation on OF switches' flow tables and to selectively choose switches for rule installation. Extensive simulation shows significant results on reduced controller workload. The performance provides a mutual trade-off by considerably improving rule matching rate in the presence of slightly enhanced number of flow entries, conserving resources on both OF controller and OF switches for SDN-based DCN operation. As a consequence, network latency is reduced while throughput is enhanced, which offers a great promise in the future deployment of industrial DCN.

This paper proposes a routing scheme that enhances energy consumption and end-to-end delay for large-scale Industrial Internet of Things (IIoT) systems based on IEEE 802.15.4a MAC. In the current IIoT, a larger-scale and complex deployment has been a noticeable obstacle for minimizing power consumption and routing on real-time. Thus, the proposed algorithm is targeted at large-scale systems where data are aggregated through different clusters on their way to the sink. Moreover, a hierarchical system framework is employed to promote scalability of IIoT elements. By estimating the residual energy and hop counts for each path, the data can be forwarded to the destination through the optimal path. Simulation results show that the scheme can reduce the energy consumption and end-to-end delay effectively.

This paper studies the performance of six transmission schemes, namely single-hop, multihop, selective decode-and-forward, amplify-and-forward, incremental decode-and-forward (IDF), and incremental amplify-and-forward (IAF) schemes. For a fair comparison, these schemes are constrained in terms of maximum outage probability and end-to-end throughput. In this paper, we investigate the impact of propagation channel conditions including both line-of-sight and non-line-of-sight environments by exploiting Nakagami-m fading channel. Our simulation results show that, by utilizing a return channel, the IDF and IAF cooperative schemes achieve better performance than the other schemes in most cases.

As technology evolves, its consumers gain considerable advantages to bring prosperity for all humankind. It is so in medical environment. Even though there always has been standards in hospital or other related medical sites, it is possible for people with the help of technology to study about simple theory of pathology and find another mechanism to meet those standards, i.e., to create new method for healing illnesses. For consumer use, creating the new method can be of a significant benefit for the case of maximizing usability and minimizing cost, and inventing Electrocardiography method is a good example. It is considered difficult for laymen if they want to assess their own heart condition following the rule defined, as so the cost they should afford. Motivated by this problem, this paper investigates detrended fluctuation analysis (DFA) to measure heart electric signal. DFA scales the autocorrelation of nonstationary signal, which can be found in human heartbeat in the form of Electrocardiogram wave. DFA was implemented in a developed Electrocardiogram (ECG) device, created with a low-cost Raspberry pi 2 as the core and some other sensors. As for home environment, smoking habit was considered as the performance metric. The experimental result reveals a cardiac disparity between smoker and nonsmoker, showing a new way of determining smoking habit effect using DFA.

In this paper, an enhanced SDP-Dynamic bloom filters for a DDS node discovery scheme in real-time distributed systems is proposed. Since the previous works of the DDS focuses more on the usage of a Simple Discovery Protocol (SDP) for endpoint to endpoint information communication of industrial-scale networks, attempts have now been made to enhance this approach into the Simple Discovery Protocol Dynamic Bloom Filters (SDP-Dynamic Bloom) focusing more on scalability in the amount of sent and stored message packets in the industrial network system. Simulation result show that the proposed scheme viciously reduces the overall computing and processing time of both stable and unstable industrial network environment which arises during the restructuring process of the existing SDP bloom filters approach.

This paper investigates a real-time water quality monitoring system by using a proposed brokerless publisher-subscriber (pub/sub) architecture framework. On the system, sensors sense the water measurement metrics, including temperature, pH, and dissolved oxygen level. All collected data are stored in a database and computed stochastically for further analysis on water quality. A complementary experiment compares the proposed pub/sub architecture and MQTT, a lightweight protocol on which IoT mostly uses, to show better performance of the proposed architecture in case of network latency and throughput for diverse message payload size, thus suggesting the future IoT implementation of the system. To complete the experiment, the relationship among temperature, pH, and dissolved oxygen is analyzed, and the experiment summarizes that water temperature is inversely proportional to pH and dissolved oxygen value.

This paper proposes an energy-aware routing scheme to enhance the performance of industrial wireless sensor networks (IWSNs) for Internet of Things (IoT) systems. Because of a larger scale and a more complex deployment, to achieve minimal energy consumption for IoT systems is not a simple problem. Additionally, the current works of deploying IWSNs is not compatible to be applied directly into IoT systems. Thus, a hierarchical system framework is deployed in order to promote scalability for IoT elements. Moreover, to minimize energy consumption, the proposed scheme takes transmission distances and residual energy of nodes into account for selecting a relevant cluster head. Then, the data aggregated by cluster heads can be forwarded through the lowest energy consumption path to the sink. The simulation results indicate the potential to either decrease energy consumption and end-to-end delay or prolong network lifetime in IWSNs for IoT systems.

This paper analyzes the outage probability, energy efficiency, energy efficiency-spectral efficiency trade-off, through-put performance, energy efficiency-throughput gain trade-off and derives the optimal transmission power of Single-hop, Multi-hop, Decode-and-Forward (DF) and Incremental Decode-and-Forward (IDF) schemes in order to find out what extent collaborative communication can save energy consumption for successful transmission. Based on the Nakagami-m fading channel, this paper provides a generalized impact of energy saving in both Line-of-Sight (LOS) and Non line-of-sight (NLOS) environments. Simulation results show that IDF protocol, allowing assistant node help relay information, achieves better performance than the other techniques.

This paper proposes an efficient load balancing scheme for distributed controller in Software-Defined Networking-based mission-critical networks. Based on load status and dynamic weight coefficient on each controller, the proposed scheme guarantees load balancing in control plane to achieve better resource usage, reliability and resilience in the network. Furthermore, by using pre-defined load threshold, communication overhead is significantly reduced in comparison with existing approaches. Simulation results demonstrate that the proposed scheme is effective in terms of communication overhead and performance of load balancing in the control plane.

This study proposes rate‐estimation‐based relay selection scheme (RERSS) for large‐scale wireless networks (LSWNs) that effectively distributes traffic of packets from a source to a sink. In an LSWN, direct data transmission from a source and a sink has been becoming a challenge. This is because of longer communication distance and more interference caused by more adjacent nodes. Hence, in order to transmit data packets to the sink, the source exploits neighbour nodes as relay nodes around it to forward packets through single‐hop or multi‐hop until reaching the sink. Different from the conventional cooperative relaying scheme, RERSS introduces a rate‐estimation parameter A to select the forwarder for relaying messages. After determining A value of each neighbour relay node using a link rate stored in the advertising packet, the relay node whose A value meets the requirement of RERSS can be qualified as a forwarder of the source or the other relay node. Simulation results indicate the potential to not only increase throughput but also decrease energy consumption and end‐to‐end delay.

A node discovery scheme is required to establish communication through discovery of matched endpoints. Data distribution service (DDS) uses simple discovery protocol (SDP) as its node discovery scheme. SDP works by sending each endpoint information to all participants that produce high network traffic in naval combat systems (NCS). Moreover, NCS might suffers instability not only from technical problems but also enemy forces attack. A node discovery scheme based on Parallel Dynamic Bloom filters (PDBF) called SDP-ParallelDBF is proposed to improve DDS scalability by reducing the number of sent and stored messages in the network. Proposed scheme reduces unnecessary delay time spent restructuring Bloom filters, especially in unstable network environments. Furthermore, SDP-ParallelDBF offers computation speed-up through parallelization approach to provide additional delay time reduction. Simulation results show that proposed scheme reduces the delay time, number of messages, and messages size in the network while maintain false negative error free on unstable NCS.

This paper proposes a geographical routing algorithm based on Zone Routing Protocol (ZRP) to limit the area for discovering a new route by utilizing location information of nodes. Mobile Ad Hoc Networks (MANETs) have attracted much attention in the research and the industry. In MANETs using ZRP algorithm, nodes use Route REQuest messages (RREQs) to obtain a new route often by bordercasting them to other nodes in the network if they does not find out the destination in their routing zone. This dissemination mechanism guarantees to seek a route from source to destination with high probability. However, it creates many useless routing overhead packets while limited bandwidth and energy consumption are very important issues in MANETs. In order to reduce routing overhead, this paper proposes an approach name Location-Aided Zone Routing Protocol (LAZRP). Simulation results confirm that the proposed algorithm can depress routing overhead and end-to-end delay.

In this paper, a novel spectrum handoff scheme for cognitive ultra-wide band industrial networks (CUWBINs) is proposed, where secondary users (SUs) can access the licensed channels despite the present of primary users' signals. To maintain continuous connectivity between the cognitive users, licensed channels can be opportunistically used by an SU as long as its transmission does not interfere with PUs. According to simulation results, the proposed spectrum handoff algorithm significantly outstrips the existing random sensing based spectrum handoff scheme in terms of spectrum efficiency and switching-handoff delay.

A discovery scheme is needed to establish efficient connection between devices and services. Constrained Application Protocol (CoAP) uses resource discovery protocol by sending complete resources information using plain text format that produce large payload and lookup overhead in large-scale networks. Furthermore, current CoAP resource discovery protocol does not specify the IP address or hostname discovery operations, which means that either an external application would need to provide IP address/hostname or it need to be manually added into the firmware. A discovery scheme based on Partitioned Bloom niters (PBF) called CoAP-PBF is proposed to improve CoAP resource discovery by having each device sends resource summary with PBF. This approach improves CoAP efficiency because all devices receive compact, complete, and encrypted remote devices information. Partitioned hash method is applied to further reduce computational cost of PBF. Furthermore, proposed schemes increase system's security because CoAP-PBF sends resource information in encrypted format. Simulation results show the proposed scheme provide fast, light, and secure autonomous discovery in CoAP while maintain IP compatibility.

This paper proposes a novel routing method called Accumulative-Load Aware Routing (ALAR) for Software-Defined Networks (SDN), that takes into account the cumulative load of flows on each link. By employing knowledge of the whole network topology and traffic in route computation, this approach enhances the utilization of network resources, minimize the probability of congestion and through which the average end to end delay is also improved. Using Mininet network emulator, simulation provides comparisons with conventional shortest path routing, and also presents results demonstrating that ALAR not only can utilize the network resources much better than legacy shortest path routing but also can avoid potential congestion problem of shortest path routing.

This study proposes a method to handle unrecoverable data using a formula called Bézier curve. The proposed method suggests the possibility to approximate the damaged data, which have been processed by the error correction scheme. The proposed method works on the real‐time distributed system which retransmission is considered as unsuitable solution to manage the overall networked system. By using the Bézier curve, the transmitted unrecoverable data are reconstructed again by using the functional approximation. This method provides a smoothing effect on damaged data that usually are normalised on real‐time transmission of PROFIBUS. Three differences Bézier curve methods are compared in PROFIBUS data, four‐points (FP) method, two‐points two‐degrees method and four‐degrees (FD) method. Simulation results show that all three Bézier curve methods can approximate data in PROFIBUS. FD has higher computation complexity compared with others. However, FD compensates with its data size which is only half of FP method.

This paper proposes SDP-Dynamic Bloom, which is an extension of the node discovery scheme in data distribution service (DDS). A node discovery scheme is required to establish communication through discovery of matched endpoints. DDS uses simple discovery protocol (SDP) as its node discovery scheme. SDP works by sending each endpoint information to all endpoints that produce high network traffic in large-scale networks. A node discovery scheme based on dynamic Bloom filters (DBF) is proposed to improve DDS scalability by reducing the number of sent and stored messages in the network. Furthermore, the proposed scheme reduces unnecessary computing time spent restructuring Bloom filters, especially in unstable large-scale network environments. The simulation results show that the proposed scheme improves network latency.

In this paper, we propose a hybrid scheduling algorithm based on renewal process with the awareness of energy consumption in real-time systems. This algorithm overcomes overlapped jobs in multi-task systems by modeling time duration of jobs in a certain task as ON/OF renewal process with the consideration of energy consumption. The positive effects of this approach can not only be extended to the case of shared resources but also be flexible in precedent scheduling methods with minor changes. Simulation results shows that this proposed algorithm is able to effectively reduce average number of preemptions and avoid unnecessary preemptions during total runtime.

This paper proposes a routing algorithm that enhances throughput and decreases end-to-end delay in industrial cognitive radio sensor networks (ICRSNs) based on ISA100.11a. In ICRSNs, the throughput is downgraded by interference from primary networks. The proposed routing algorithm is targeted at large-scale networks where data are forwarded through different clusters on their way to the sink. By estimating the maximum throughput for each path, the data can be forwarded through the most optimal path. Simulation results show that our scheme can enhance throughput and decrease end-to-end delay.

In this paper, a novel discovery protocol using modified counting Bloom filters for data distribution service (DDS) is proposed. In current discovery protocols for DDS, each participant sends its endpoint data to every participant, and receives endpoint data from all other participants. In a large network such as naval warships, a lot of memory is required to store all the data. In many cases, most of the data stored is not needed by the endpoints but occupy memory storage. To reduce the size of data sent and stored, a discovery process combined with counting bloom filter is proposed. This paper presents the delay time for filters construction and the total discovery time needed in a naval warship network topology. The simulation results shows that the proposed method gives low delay time and no false positive probability.

This paper proposes a new adaptive spectrum handoff scheme where sensor nodes opportunistically use licensed channels as long as its transmission does not cause interference with primary receivers (PRs) in cognitive radio-based industrial wireless sensor networks (CR-IWSNs). We incorporate proactive spectrum sensing into the proposed spectrum handoff scheme to reduce the number of spectrum handoff. With the proposed spectrum handoff scheme, the sensor node may still be able to access the licensed channel band even though a primary user (PU) signal is present. Moreover, a recovery spectrum handoff scheme to allow continuous connectivity between the sensor nodes under rapidly changing PU activity and efficiently recover control channel, is proposed. For the scenarios we considered, the proposed adaptive spectrum handoff outperforms the existing spectrum handoff schemes exhibiting higher throughput, reduced the number of spectrum handoff and shorter switching-handoff delay.

This paper proposes a new message scheduling method on shared timeslots of ISA100.11a to enhance real-time performance, called Traffic-Aware Message Scheduling (TAMS) method. Instead of competing to transmit sporadic messages in consecutive cycles, end-nodes are divided into parts, and then access the channel in the specific cycles when the probability of timeslots getting involved in collision exceeds a threshold. The simulation results indicate that the proposed method provides performance improvements in terms of throughput and end-to-end delay.

This paper proposes a routing algorithm that enhances a network lifetime and decreases an end-to-end latency for industrial wireless sensor networks (IWSNs) based on ISA100.11a standard. The proposed algorithm can be applied to large-scale networks where data is conveyed by multi-hop forwarding scheme from source nodes to the sink. By estimating a residual energy and a packet reception rate (PRR) of a next hop, data can be forwarded through the optimal path. Furthermore, the energy consumption and the network latency are minimized by using an integer linear programming (ILP). Simulation results show that the proposed algorithm is fully effective in terms of energy saving and network latency for IWSNs.

This paper proposes a distributed relay assignment scheme with interference limitation for industrial wireless networks that exploits cooperative diversity to cope with problems of wireless channels and to enhance the reliability of data transmission. By combining the selection and incremental relaying schemes and by taking the channel status information and queue length at each node into account, the cooperative scheme improves the packet dropped ratio and end-to-end delay due to retransmissions. In addition, this paper also investigates the interference problem produced by the relay nodes. Simulation results conducted to evaluate the performance of the proposed scheme indicate that it effectively enhances the network performance in terms of the packet delivery ratio, energy consumption, and overall packet delay.

Bit width is a limitation of hardware implementation in baseband signal processing. It influences bit error rate (BER) performance and hardware complexity. This paper investigates BER performance of various bit width. We analyze bit width errors that come from quantization errors and clipping errors. As a result, it is shown that increasing bit width improves BER performance. At some point, increasing bit width does not enhance BER performance. This paper provides direction to determine optimum bit width value for 802.11n receiver design.

In IEEE 802.15.4 beacon-enabled networks, the length of active periods should be configured appropriately in order to save energy and accommodate traffic. This paper proposes ECAP, a bursty traffic adaptation algorithm for IEEE 802.15.4 beacon-enabled networks. To accommodate bursty traffic, the proposed algorithm is designed to extend the active periods dynamically based on the requests from devices. The simulation results show the performance enhancement in terms of end-to-end delay and energy consumption per packet transmission