ABSTRACT The Internet of Vehicles (IoV) is revolutionising transportation by connecting vehicles, infrastructure and devices, enabling more intelligent and safer mobility. One key challenge is ensuring efficient and secure communication among vehicles with varying capabilities, including different sizes, speeds and sensor configurations. This research introduces a Federated Learning‐Driven Deep Learning (FLDL) approach to intelligent collision avoidance, designed to address the heterogeneity of vehicles in the IoV ecosystem. The system integrates real‐time data from vehicle‐to‐vehicle (V2V) and vehicle‐to‐infrastructure (V2I) communications, while considering factors like vehicle type, road conditions, driver behaviour and Digital Twins. Our approach leverages multiple Federated Learning strategies, which enhance privacy protection, reduce communication overhead and enable real‐time decision‐making without the need for centralised data storage. Experimental results show that the GNN + FedGC model achieves the highest performance with an accuracy of 98.8%, outperforming other models such as MLP with FedLU (98.5%), DRL with FedPPO (98.3%) and LSTM with FedSGD (97.65%). The integration of Digital Twins further enhances model accuracy by simulating real‐time vehicle behaviour and environmental conditions. This FL‐based system not only improves collision prediction but also enhances safety, reduces accident rates and supports scalable decision‐making in smart city transportation systems.

Reliable channel state information (CSI) is a critical enabler for low-power Internet of Things (IoT) links and emerging 6G edge devices, where receivers must operate under tight energy/latency budgets and in the presence of non-ideal noise and malicious interference. Deep learning (DL)-based channel estimators can surpass classical LS/MMSE baselines; however, they remain vulnerable to distribution shifts and adversarial attacks targeting pilot observations. This paper proposes a lightweight and robust micro-channel estimation (μ-CE) framework based ondefensive distillation, where a compact student convolutional neural network (CNN) is trained under a higher-capacity teacher estimator using a regression-oriented distillation loss. The resulting μ-CE learns a smoother input–output mapping with reduced gradient sensitivity, improving trustworthiness without sacrificing accuracy or computational efficiency. Using MATLAB-and DeepMIMO-generated 5G NR TDL-C channels, we evaluate robustness under diverse non-adversarial noise types and four white-box gradient-based attacks (Fast Gradient Sign Method (FGSM), Basic Iterative Method (BIM), Momentum Iterative Method (MIM), and Projected Gradient Descent (PGD)). Compared with an undefended CNN, the proposed μ-CE improves normalized mean squared error (NMSE) by approximately 0.5–1 dB under the considered non-adversarial noise conditions (including additive white Gaussian noise (AWGN) at a signal-to-noise ratio (SNR) of 15 dB in the default test setting), limits adversarial NMSE degradation to within 1–2 dB of the clean baseline for moderate perturbation budgets, and reduces attack success rate (ASR) by about 25–40%. Moreover, the distilled μ-CE requires roughly 14× fewer parameters and multiply-accumulate (MAC) operations than the teacher model, supporting practical deployment for robust CSI acquisition in resource-constrained IoT and 6G edge receivers.

Accurate and efficient road damage detection is critical for maintaining urban infrastructure and ensuring public safety in Intelligent Internet of Things (IIoT) systems. There remains a significant challenge to achieving a balance between detection accuracy and real-time inference on resource-constrained edge devices despite advances in deep learning. This paper addresses this gap by enhancing the YOLOv9c object detection framework with two distinct backbone architectures: MobileNet V3-Small, which is a lightweight convolutional neural network optimized for edge deployment, and Swin Transformer, which is a hierarchical vision transformer that captures rich contextual features. We present a systematic, dual-backbone performance benchmark that quantifies the critical trade-off between computational efficiency and detection precision, which is essential for guiding IIoT deployment strategies. We conducted experiments on the Street View Road Damage Detection (SVRDD) dataset to evaluate detection accuracy, computational efficiency, and latency. The MobileNet backbone achieves the highest mean Average Precision ([email protected]) of 74.0% (a 1.5% gain over baseline) and recall of 68.8% (a 7.3% gain over baseline), demonstrating improved accuracy while maintaining a low inference time on a baseline GPU, indicating its suitability for deployment on IoT edge devices. Importantly, the MobileNet variant reduces the parameter count from 25.6 M to 2.54 M and the Giga Floating-point Operations Per Second (GFLOPs) from 102.3 to 0.49, making it more efficient for IIoT edge devices. Both backbones performed better than the YOLOv9c baseline model in terms of accuracy, thus providing scalable and practical solutions for real-time infrastructure monitoring. These findings contribute to the development of intelligent, efficient, and scalable object detection systems tailored for smart city and IIoT environments.

The rapid development of the Internet of Medical Things (IoMT) enables automatic recording of surgical reports via interconnected medical devices. However, the reliability of these data is often compromised by missing data, frequently stemming from intermittent IoT communication issues like network disruptions or device malfunctions. This incomplete data critically hinders downstream medical applications and violates implicit network intents related to data integrity and timeliness within an Intent-based Networking (IBN), essential for supporting proactive resource allocation in operating rooms and optimized surgical scheduling. While existing studies focus on addressing missing event types, event time imputation remains a significant, underexplored challenge due to the need to capture implicit temporal contexts and complex cross surgical procedures dependencies. To tackle this for IoMT, we propose a novel Surgical event time IMputation in Intent-Based Networking(SIM-IBN) model. SIM-IBN employs continuous-time LSTMs with attention mechanisms to learn intra-and inter-sequence correlations, effectively recovering missing timestamps. By enhancing data reliability at the source, SIM-IBN serves as a crucial component enabling IBN systems to better fulfill intents for dependable IoMT operations. Rigorous evaluation on real-world surgical event datasets demonstrates SIM-IBN’s superiority over state-of-the-art baselines by up to 11.88% across various missing data scenarios, validating its potential to enable more reliable IoMT systems and enhance operational efficiency in smart healthcare environments.

The routing protocol for low-power and lossy networks (RPL) is a specialized routing protocol designed for optimized data routing, specifically for resource-constrained Internet of Things (IoT) networks with unreliable links and high packet loss. However, RPL is highly vulnerable to significant security challenges, particularly the decrease rank attack (DRA), in which malicious nodes attract child nodes by falsely advertising lower ranks, leading to routing inefficiencies, unnecessary retransmissions, and increased energy consumption. To address this problem, we propose a novel intent-based networking-driven centralized real-time reinforced detection scheme (CRRDS), which translates high-level security intents into policy-driven automated control strategies for DRA detection. In the proposed CRRDS, a resource-rich root node acts as a deep reinforcement learning agent that collects critical information from the child nodes, including the node ID, end-to-end delay, received signal strength indicator, and hop count, to detect suspicious behavior accurately and intelligently. Initially, we implemented a deep Q-network (DQN)-assisted CRRDS in detecting DRA. Subsequently, we utilized double DQN (DDQN) and dueling DDQN due to their enhanced capabilities in value estimation and policy learning. The dueling DDQN performed optimally because of its deeper architecture. Simulation results demonstrate that the proposed dueling DDQN-assisted CRRDS achieves the highest detection accuracy of 98% with notable gains in true positive and false positive rates, even in complex scenarios with up to 30% malicious nodes.

Large-scale deep learning models rely on wireless networks for distributed training approaches, which are essential to meet the immense computational and data demands. However, the stochastic nature of wireless environments introduces significant challenges such as variable delays, noise interference, and packet loss, which lead to degraded gradient synchronization and hinder model convergence. In this work, we propose a novel communication-aware distributed training (CADT) framework that integrates real-time channel state information (CSI) feedback into the gradient aggregation process. Unlike conventional methods that assume static or ideal communication conditions, CADT dynamically reweights gradients from each node based on instantaneous channel quality, enabling robust aggregation under adverse wireless conditions. By dynamically adjusting the contribution of each node based on instantaneous channel conditions, CADT effectively compensates for wireless impairments, thereby ensuring more reliable gradient aggregation and significantly improving both convergence speed and final model accuracy. Extensive experiments on CIFAR-10, CIFAR-100, ImageNet, and SVHN using Vision Transformer and ResNet-50 demonstrate that CADT outperforms baseline methods in terms of convergence, accuracy, and communication efficiency. In addition, we provide a rigorous theoretical analysis that establishes convergence guarantees under realistic wireless conditions, thereby advancing the theoretical foundation of distributed optimization in non-ideal communication environments.Our framework offers a practical solution for real-world scenarios such as edge computing, where communication constraints and environmental variability are dominant factors.

Social networks, particularly Twitter, significantly influence public emotions during health crises, often amplifying distress and misinformation. Effective sentiment analysis is crucial for mitigating social unrest and enabling timely interventions. This study introduces a novel two-stage framework, the fuzzy-integrated case-based and adaptive deep-belief neural network (2-SCBAADBNN) model, for real-time sentiment classification in public health emergencies. The framework integrates neural architecture search (NAS) and large machine learning models (LMMs) such as bidirectional encoder representations from transformers (BERT) to optimize fuzzy logic components and enhance feature extraction, improving sentiment detection accuracy. The two-stage classification first distinguishes between personal and news-related tweets using a fuzzy clue-based method, followed by sentiment classification of personal tweets into positive or negative categories. By combining fuzzy logic with deep learning, this multimodal approach aligns with advancements in emotion AI, offering greater scalability, adaptability, and precision in sentiment analysis. Comparative evaluations show that 2-SCBAADBNN outperforms existing models, providing a robust solution to monitor emotional distress and combat misinformation during crises. This research advances emotion AI by integrating NAS and LMM, allowing more context-sensitive real-time sentiment analysis. It contributes to developing AI-driven empathy-based systems capable of understanding and responding to public sentiment more effectively in critical social scenarios.

With the growing availability of multimodal health data including patient behavior signals, clinical text, and medical images, AI systems have an increasing potential to support early disease detection and decision-making in aging populations. As healthcare systems evolve into complex socio-technical environments, integrating explainable AI with human-centered design is essential to improve transparency, trust, and adoption. In this study, we propose a multimodal human-centered deep learning framework (MDLHC) to support breast cancer diagnosis by integrating patient data, imaging, and explainable attribution (XAI) methods. The framework is designed with the social and cognitive needs of elderly patients and clinicians in mind and uses demographic data and mammography images for personalized diagnostics. To bridge structured and unstructured data, we incorporate large language models (LLMs) for natural language alignment and summarization of clinical insights. For improved image understanding, a CNN-based residual integrated attention (RIAC) module is applied for noise reduction, followed by optimized feature selection using evolutionary PSO with Laplacian centrality (EPSO-LC). Classification is performed via a deep backpropagation CNN (DL-BP-CNN), enhanced with two explainability modules: ensemble random SHAP (ERS) and submodular selection-based LIME (SMS-LIME) for both localized and global transparency. This framework contributes to the development of a transparent, accurate, and personalized AI system that aligns with the scope of computational social systems in healthcare care, particularly for aging populations that require reliable diagnostic support.

Computer-aided detection through deep learning is becoming a prevalent approach across various fields, including the detection of anomalies in medical procedures. One such medical procedure involves the placement of medical tubes to provide nutrition or other medical interventions in critically ill patients. Medical tube placement can be highly complex and prone to subjective errors. Malposition of medical tubes is often observed and associated with significant morbidity and mortality. In addition, continuous verification using manual procedures such as capnography, pH testing, auscultation, and visual inspection through chest X-ray (CXR) imaging is required. In this paper, we propose a Conv-MTD, a medical tube detection (MTD) model that detects the placement of medical tubes using CXR images, assisting radiologists with precise identification and categorizing the tubes into normal, abnormal, and borderline placement. Conv-MTD leverages the EfficientNet-B7 architecture as its backbone, enhanced with an auxiliary head in the intermediate layers to mitigate vanishing gradient issues common in deep neural networks. The Conv-MTD is further optimized using post-training 16-bit floating-point (FP16) quantization, which significantly reduces memory consumption by 50% and 2x improvement in inference speed without compromising accuracy. This optimization allows Conv-MTD to achieve efficient performance without requiring high-end computational resources, making it suitable for deployment on point-of-care devices. Conv-MTD provided the best performance, with an average area under the receiver operating characteristic curve (AUC) of 0.95 using the open-source RANZCR CLiP dataset. The proposed Conv-MTD has the potential to operate on resource-constrained point-of-care devices due to its use of FP16 computation, enabling low-cost and automated assessments in various healthcare settings.

The increasing acceptance of Electric Vehicles (EVs) leads to significant challenges for traditional forecasting methods due to external variables such as weather conditions, availability of renewable energy sources, and real-time traffic data. These factors affect the forecasting accuracy because of the unpredictable nature of renewable energy sources and weather. Conventional methods have limitations in terms of adapting dynamic conditions, leading to problems in allocating power and managing energy in EV Charging Stations (EVCS). To address these challenges, we propose a novel AI-driven approach called Dynamic Allocation and Management Optimization (DYNAMO), which integrates cutting-edge demand forecasting, power allocation, and efficiency-enhanced methods for smart city EV infrastructure. DYNAMO uses a Lite Transformer Gated Recurrent Unit (LT-GRU) for advanced demand prediction by considering critical factors like the number of incoming EVs, session duration, and station usage frequency. In LT-GRU, we integrate the strengths of transformer attention mechanism and sequential data processing of GRU to improve the prediction accuracy by capturing the long-term dependencies and prioritizing the important features even though in dynamic conditions. Additionally, an Intelligent Central Manager (ICM) groups EVCS into high, moderate, and low demand clusters, allowing for dynamic optimization of charging infrastructure. Furthermore, a Game Theory-based Deep Reinforcement Learning (GT-DRL) approach is employed, which considers variables such as vehicle demand, battery capacity, charging speed, and weather conditions, while preventing overloads and outages. Our approach not only enhances the operational efficiency of EVCS but also contributes to the development of more sustainable and reliable EV charging networks. Overall, the proposed framework’s ability to adapt in real-time ensures that it can support the increasing demand for EV infrastructure, minimize inefficiencies, and improve user experience.

Internet of Vehicles (IoV) is a new type of network that enables communication among vehicles, infrastructure, and users, providing better traffic systems. When exchanging information, the IoV systems face challenges such as data privacy, access control, and trust management issues. The security mechanisms are utilized to address privacy and trust issues. However, existing solutions still face adaptability, scalability, and efficiency issues when handling the dynamic requirements of IoV ecosystems. This study addressed security issues by designing the Quantum-Inspired Metaheuristic Framework (QIMF), which integrates a quantum optimization algorithm and adaptive privacy agreements to enhance security between IoV entities. During the analysis, the trust score is evaluated for all entities, which helps to minimize unauthorized access and manage trustworthiness using the quantum-inspired approach while exchanging information. The private agreement is assessed via the computed trust score, which improves the policy’s construction. According to the policy, secure access control is achieved by integrating the quantum superposition and tunnelling features to ensure scalable and secure transactions. The discussed system is implemented using the Python tool, and the CICIoV2024 dataset is used to evaluate the discussed system’s efficiency. The QIMF achieves 99.2% trust accuracy with a minimum false acceptance and rejection rate. The integrated approach ensures scalable and secure solutions for improving vehicular networks.

The proliferation of sensory applications has led to the development of the Internet of Things (IoT), which extends connectivity beyond traditional computing platforms and connects all kinds of everyday objects. Marine Ad Hoc Networks are expected to be an essential part of this connected world, forming the Internet of Marine Things (IoMaT). However, marine IoT systems are often highly distributed, and spread across large sparse areas which makes it challenging to implement and manage centralized security measures. Despite some ongoing efforts to establish network connectivity in such environment, securing these networks remains an unreached goal. The use of Certificate-Less Digital Signatures (CLDS) with Elliptic Curve Cryptography (ECC) shows great promise in providing secure communication in these networks and achieving zero trust IoMaT security. By eliminating the need for certificates and associated key management infrastructure, CLDS simplifies the key management process. ECC also enables secure communication with smaller key sizes and faster processing times, which is crucial for resource-limited IoMaT devices. In this paper, we introduce CLDS using ECC as a means of securing IoT networks in a marine environment, creating a zero trust security framework for Internet of Marine Things (IoMaT). To increase security and robustness of the framework, we optimize the ECC parameters using two vital artificial intelligence algorithms, namely Genetic Algorithm (GA) and Particle Swarm Optimization (PSO). Evaluation results demonstrate a reduction in ECC parameter generation time by over 40% with GA optimization and 20% with PSO optimization. Additionally, the computational cost and memory usage for major ECC attacks increased significantly by up to 40% and 67% for Rho attacks, 34% and 53% for brute-force attacks, and 30% and 67% for improved hybrid attacks, respectively.

ABSTRACT This paper presents a new data clustering technique aimed at enhancing the performance of the trainable path‐cost algorithm and reducing the computational complexity of data clustering models. The proposed method facilitates the discovery of natural groupings and behaviours, which is crucial for effective coordination in complex environments. It identifies natural groupings within a set of features and detects the best clusters with similar behaviour in the data, overcoming the limitations of traditional state‐of‐the‐art methods. The algorithm utilises a density peak clustering method to determine cluster centers and then extracts features from paths passing through these peak points (centers). These features are used to train the support vector machine (SVM) to predict the labels of other points. The proposed algorithm is enhanced using two key concepts: first, it employs Q‐Generalised Extreme Value (Q‐GEV) under power normalisation instead of traditional generalised extreme value distributions, thereby increasing modelling flexibility; second, it utilises the random vector functional link (RVFL) network rather than the SVM, which helps avoid overfitting and improves label prediction accuracy. The effectiveness of the proposed clustering algorithm is evaluated through various experiments, including those on UCI benchmark datasets and real‐world data, demonstrating significant improvements across multiple performance metrics, including F1 measure, Jaccard index, purity, and accuracy, highlighting its capability in accurately identifying paths between similar clusters. Its average F1 measure, Jaccard index, purity, and accuracy is measured 76.87%, 56.29%, 80.29%, and 79.64%, respectively.

The dynamic environment of UAV swarms in forest management is characterized by communication instability, heterogeneous nodes, and frequent topology changes due to challenging terrain. These systems are vulnerable to network attacks, requiring advanced intrusion detection technologies. Traditional methods struggle with rapid changes due to data privacy concerns and centralized computational limits, while existing federated learning (FL) algorithms lack robustness against client heterogeneity and dynamic data distribution, especially in complex forest environments. To address these challenges, we propose federated intrusion detection for securing UAV swarms (FIDSUS). FIDSUS improves intrusion detection systems by leveraging collaborative sensing among UAVs, enabling better monitoring and response to security threats in forestry. By quantifying the similarity between UAVs’ local feature extractors through an affinity matrix, FIDSUS guides the aggregation of feature extractors, improving detection capabilities. It also uses AI-driven aerial and distributed computing to enhance data processing efficiency and decision-making speed. The framework addresses data heterogeneity by cross-round feature fusion, improving detection in dynamic environments. Experimental results on the NSL-KDD and UNSW-NB15 datasets show that FIDSUS outperforms existing FL methods with a 4%–34% accuracy improvement. FIDSUS shows robustness and accuracy in dynamic environments, providing an effective solution for securing UAV swarms in forestry.

The development of Artificial Intelligence-based Internet of Things (AIoT) enables wireless vehicular networks to provide energy-efficient and sustainable solutions for green supply chains through optimized data processing, adaptive resource allocation, and automated control. However, there are still many challenges in resource allocation and network congestion, especially in large-scale AIoT-enabled vehicular networks. Traditional approaches often struggle with scalability due to static resource allocation, lack of incentive mechanisms, and high computational complexity. Therefore, we propose a contract theory and harmony search optimization algorithm(HSO-Con) for AIoT-enabled green supply chain management. This method uses the combination of contract theory and VEC to optimize resource allocation in the AIoT environment. Harmony Search dynamically optimizes task scheduling and data processing and uses a cache mechanism to reduce redundant data transmission. In addition, the graph neural network (GNN) further enhances the adaptability of the AIoT network, enabling adaptive parameter adjustments and efficient processing of data streams. Simulation results show that the HSO-Con algorithm has significant potential in reducing network congestion, and enhancing supply chain efficiency in VEC by AIoT. Specifically, our algorithm improves cache hit rate by 4.27% and 5.05% respectively, and bandwidth utilization by 7.01%.

As sustainable development gains attention, integrating carbon-intelligent computing into fault diagnosis systems has emerged as a critical strategy to reduce energy consumption and carbon footprints. This approach uses artificial intelligence (AI) and the Internet of Things (IoT) to optimize task scheduling, aligning it with low-carbon energy sources based on time and location. In fault diagnosis, energy-intensive tasks, such as data processing and model inference, can be scheduled during periods of abundant renewable energy, thereby minimizing emissions. However, drilling machines operate under complex conditions that generate nonstationary noise, which distorts signals and complicates fault diagnosis. Therefore, this article combines bidirectional long short-term memory (BiLSTM) with the Kolmogorov-Arnold network (KAN) and integrates Wavelet Transform and Convolutional Autoencoder, proposing a highly robust fault diagnosis model for drilling machines, named WCBK. The Wavelet Transform converts pressure time-series data, which contains fault information, into time-frequency images, facilitating the detection of fault frequency components. The Convolutional Autoencoder preserves essential features while removing noise by learning low-dimensional representations of the signal, effectively capturing local features in time-frequency images through local connections to enhance denoising performance. Finally, the composite deep learning network, which combines BiLSTM and KAN, achieves highly robust fault diagnosis under complex working conditions. The effectiveness of the proposed WCBK model was validated through ablation experiments, experiments on different individuals, experiments on different parts, and model adaptability evaluations. In experiments involving different individuals and parts, the WCBK model improved fault diagnosis accuracy by 10.9% and 8.8%, respectively, compared to existing models.

Flexible manufacturing systems (FMS), empowered by the Industrial Internet of Things (IIoT), have become a cornerstone of Industry 6.0 by enabling dynamic production adaptation, real-time equipment monitoring, and intelligent scheduling. As these systems increasingly incorporate large language models (LLMs) to support functions such as knowledge querying, decision assistance, and predictive maintenance, ensuring the safety and reliability of human-LLM conversations has become a pressing concern. Specifically, LLMs may generate toxic, biased, or privacy-violating outputs when interacting with sensitive IIoT data and production logic, potentially compromising operational safety. To address this challenge, we propose AugLLMSen, an automated toxicity evaluation framework tailored to the IIoT-driven FMS context. AugLLMSen integrates a question automatic expansion mechanism (Q-Judge) and an output toxicity evaluation model (O-Judge) into a closed-loop pipeline, enabling large-scale assessment of LLM safety across diverse industrial scenarios. Experimental results on open- and closed-source LLMs demonstrate the effectiveness and accuracy of our approach in identifying toxic responses and guiding safe deployment of LLMs in flexible manufacturing environments.

Amidst the rapid integration of Medical Internet of Things (MIoT) into health monitoring ecosystems, electrocardiogram (ECG)-based biometric authentication has emerged as a pivotal component in securing smart healthcare architectures, leveraging its inherent biological uniqueness and real-time monitoring capabilities. Current ECG authentication methodologies face three MIoT-specific challenges: 1) Conventional feature extraction struggles with spatial heterogeneity in multi-device 12-lead signals; 2) Single-cycle analysis lacks generalizability across physiological states; 3) Environmental noise degrades edge computing robustness. To address these limitations, this study proposes ST-AuthNet, a lightweight ECG authentication framework that synergistically integrates spatiotemporal attention mechanisms with enhanced residual networks. First, we redesign the ResNet residual block architecture by replacing conventional 1× 1 convolutional downsampling with hybrid 2× 2 average pooling and 1× 1 convolutional operations, effectively mitigating low-amplitude morphological feature loss (e.g., P/T waves) during feature map compression. Next, a multi-head cross-attention mechanism is introduced to dynamically capture inter-lead spatial correlations and intra-PQRST temporal dependencies across ECG waveforms. Finally, an adaptive threshold decision module is developed to optimize model robustness against physiological variability and environmental perturbations through dynamic classification boundary adjustment. Evaluations demonstrate state-of-the-art performance with 99.77% (CYBHI), 88.60% (MIT), 76.33% (MIT2), and 92.44% (HeartID-V) accuracy, significantly outperforming existing methods in cross-scenario biometric verification.

With the rise of the Internet of Things, wearable devices have enabled real-time health monitoring, particularly through physiological signals like electrocardiograms (ECG). The standard 12-lead ECG records the electrical activity of the heart from multiple perspectives, providing valuable insights into cardiac health. However, existing 12-lead ECG analysis methods often treat leads as channel-level arrangements or rely on spatial adjacency to predefine lead connections, limiting their ability to capture the complex spatial and functional relationships between leads fully. To address this limitation, we propose TGLLNet, a task-driven model that automatically learns interlead relationships to improve multilabel ECG classification. TGLLNet adaptively learns lead connectivity patterns and relational strengths, enhancing ECG representation and improving model generalizability across tasks. Specifically, TGLLNet employs a temporal graph construction module to convert ecg signals into temporal graphs and uses a residual pyramid graph convolution module for multilevel graph embeddings, utilizing a graph convolutional network with independently learnable adjacency matrices. Combined with a temporal context convolution module, TGLLNet captures spatio-temporal dependencies, significantly improving ECG representation. Experimental results on seven tasks from PTB-XL and CPSC2018 datasets demonstrate that TGLLNet outperforms existing methods, showing superior generalizability across different tasks. Our code is available athttps://github.com/rosemary333/TGLLnet.

With the rapid development of distributed edge intelligence (DEI) within Internet of Vehicle (IoV) network, it is required to support heterogeneous rapid, reliable and lightweight authentication which prevents eavesdropping, tampering and replay attacks. Radio frequency fingerprinting (RFF), which leverages unique and tamper-proof hardware characteristics, is an emerging deep learning-based physical layer technology poised to achieve excellent authentication within DEI enhanced heterogeneous IoV. However, centralized collection of critical datasets will bring severe privacy concerns as well as huge communication overheads toward resources-constrained IoV nodes. In this article, we propose a deep federated fractional scattering fingerprinting network (FFSFNet) which amalgamates fractional wavelet scattering and federated learning to achieve excellent identification. Particularly, we first exploit fractional wavelet scattering to extract RFF characteristics from nonstationary waveform, eliminate redundancies and enhance interpretability. To improve the training efficiency and privacy protection capability, we design a novel federated framework, which not only completes distributed training, reduces overhead but also protects privacy. Furthermore, we conducted a comprehensive comparative analysis of different model quantization schemes and validated the proposed scheme with field programmable gate array (FPGA) accelerators. Experimental results demonstrate that the proposed FFSFNet can maintain excellent identification performance with only 5.08% of original samples. The model size and inference latency can be effectively improved by quantization with limited degradation. Moreover, the identification testing accuracy of FFSFNet can eventually converge to 99.4% with 0.64 ms inference latency per sample.

The Internet of Things (IoT) enhances the healthcare industry 5.0 by enabling connected devices and data-driven treatments, but it also introduces cyber threats such as data breaches, and unauthorized access. Mobile Edge Computing (MEC) improves security by reducing reliance on cloud transmissions. However, challenges such as Non-Independent and Identically Distributed (Non-IID) data and device intermittency affect security models in healthcare that require real-time analytics and reliable automation. These limitations are crucial in sensitive medical applications that require real-time analytics and reliable automation. This paper proposes TFedSec-HI, a Transformerdriven Federated Learning (TFL) for improving threat detection in the healthcare industry 5.0. Network traffic data is converted to grayscale and multi-channel RGB images using Local Binary Patterns (LBP) and Sobel edge detection. A lightweight mobile Vision Transformer (ViT) is used for effective feature extraction on edge devices, reducing computational load while retaining high performance. The Federated Proximal (FedProx) algorithm is used during the model aggregation phase to address issues with non-IID data distribution, resulting in consistent and effective learning. The global model is then shared with clients for realtime threat classification. The proposed method is evaluated on two real-world datasets, CICIoT2023 and CICIoMT2024, resulting in exceptional classification accuracies of 99.18% and 99.74%, respectively. TFedSec-HI addresses the Non-IID data challenges in Industry 5.0 healthcare by utilizing TFL to enable private, and adaptive threat detection across medical IoT devices.

Trajectory prediction is a crucial challenge in autonomous vehicle motion planning and decision-making techniques. However, existing methods face limitations in accurately capturing vehicle dynamics and interactions. To address this issue, this article proposes a novel approach to extracting vehicle velocity and acceleration, enabling the learning of vehicle dynamics and encoding them as auxiliary information. The VDI-LSTM model is designed, incorporating graph convolution and attention mechanisms to capture vehicle interactions using trajectory data and dynamic information. Specifically, a dynamics encoder is designed to capture the dynamic information, a dynamic graph is employed to represent vehicle interactions, and an attention mechanism is introduced to enhance the performance of LSTM and graph convolution. To demonstrate the effectiveness of our model, extensive experiments are conducted, including comparisons with several baselines and ablation studies on real-world highway datasets. Experimental results show that VDI-LSTM outperforms other baselines compared, which obtains a 3% improvement on the average RMSE indicator over the five prediction steps.

Distributed learning empowers social media platforms to handle massive data for image sentiment classification and deliver intelligent services. However, with the increase of privacy threats and malicious activities, three major challenges are emerging: securing privacy, alleviating straggler problems, and mitigating Byzantine attacks. Although recent studies explore coded computing for privacy and straggler problems, as well as Byzantine-robust aggregation for poisoning attacks, they are not well-designed against both threats simultaneously. To tackle these obstacles and achieve an efficient Byzantine-robust and straggler-resilient distributed learning framework, in this article, we present Byzantine-robust and cost-effective distributed machine learning (BCML), a codesign of coded computing and Byzantine-robust aggregation. To balance the Byzantine resilience and efficiency, we design a cosine-similarity-based Byzantine-robust aggregation method tailored for coded computing to filter out malicious gradients efficiently in real time. Furthermore, trust scores derived from similarity are published to the blockchain for the reliability and traceability of social users. Experimental results show that our BCML can tolerate Byzantine attacks without compromising convergence accuracy with lower time consumption, compared with the state-of-the-art approaches. Specifically, it is 6x faster than the uncoded approach and 2x faster than the Lagrange coded computing (LCC) approach. Besides, the cosine-similarity-based aggregation method can effectively detect and filter out malicious social users in real time.

In mixed-autonomy traffic environments, accurately predicting the lane change behavior of human-driven vehicles is critical for ensuring the safety and reliability of autonomous vehicle decision-making. However, existing approaches face two major challenges: 1) they tend to represent the relationships between the target vehicle and surrounding vehicles using parameters like relative position and speed. This approach either requires a fixed number of surrounding vehicles or introduces significant noise by relying on virtual vehicles; and 2) they often fail to fully exploit the vast amount of available vehicle trajectory data, leaving the complexities of vehicular interactions underexplored. To address these issues, this paper presents a novel lane change prediction framework using Transformer-based transfer learning. Our design aims to leverage inter-vehicle interactions learned from trajectory data to improve lane-change prediction accuracy. Specifically, pre-trained trajectory prediction models are used to adapt dynamically to the varying number of surrounding vehicles and to capture interaction context from large sets of trajectory data. We then refine the Transformer model to integrate this context and predict the target vehicle’s lane change intentions. The Transformer encoder transforms trajectory interaction context into a lane-change-oriented context using aggregated multi-head attention. The Transformer decoder, in turn, utilizes this context alongside the target vehicle’s states through relation-aware multi-head attention to forecast lane change behavior. Extensive experiments on two real-world datasets demonstrate that our proposed framework outperforms state-of-the-art baselines in both accuracy and robustness.

Ensuring the smooth operation of road traffic is a momentous target in Intelligent Transportation Systems, which can be expedited by a secure and reliable Internet of Vehicles (IoV). As prominent carriers of the IoV, intelligent vehicles (IVs), that bear the promising potential for alleviating traffic congestion, have become the core road traffic participants. However, the mixed-traffic environment escalates the risk of IVs, as the discretionary lane change behaviors of nearby human-driven vehicles may result in collisions with IVs, compromising the robust performance of the IoV. Recent studies have utilized advanced deep learning techniques to achieve proactive lane change intention prediction, including Recurrent Neural Networks and Transformer. Although attaining reasonable prediction performance, they adopt the data-driven paradigm, which excessively focuses on learning from data while neglecting the domain knowledge. Against this background, we propose to employ the knowledge-driven paradigm and design KLEP, a knowledge-driven lane change prediction framework. KLEP incorporates driving knowledge into lane change modeling, presenting the top-down hierarchical cognitive process of drivers when performing lane change maneuvers. Extensive experiments conducted on two real-world natural driving datasets demonstrate the effectiveness of KLEP. Compared to state-of-the-art lane change prediction baselines, KLEP consistently outperforms them and achieves average improvements of 6.2-7.1% and 53.0-67.2% on intention classification and intention forecast tasks across different datasets, respectively. We also validate that KLEP has strong interpretability that aligns with real-world physical laws in lane change scenarios and is lightweight enough to fulfill online prediction.

With the rapid evolution toward data-intensive applications and sustainable urban mobility, upcoming sixth-generation (6G) wireless networks must deliver enhanced coverage, high spectral efficiency, and energy optimization across densely populated areas. However, achieving these requirements poses significant challenges due to the dynamic nature of urban environments, high interference in multi-cell systems, and limitations in conventional passive beamforming technologies. To address these challenges, reconfigurable intelligent surface (RIS) is considered a highly promising approach for enabling and improving 6G wireless communications. This is because it has the ability to efficiently manipulate wireless channels at a lower cost. Considerable study has focused on the utilization of conventional diagonal RIS, in which each individual RIS component is linked to its own ground load but not interconnected with other elements. Nevertheless, the uncomplicated structure of classical RIS imposes restrictions on its ability to manipulate passive beamforming. In this study, we consider beyond diagonal RIS (BD-RIS) in the multi-cell transportation system, which goes beyond using diagonal phase shift matrices. In particular, we provide a new optimization framework to maximize the sum rate of BD-RIS assisted multi-cell transportation system by optimizing the power allocation of the base station and phase shift design of BD-RIS in each cell. We employ the block coordinate descent method to transform the original optimization problem and achieve a local optimal based on standard convex approaches. Numerical results demonstrate the benefits of adopting BD-RIS in multi-cell transportation systems compared to the classical RIS architecture.

Routing protocol for low-power and lossy network (RPL) is a routing protocol for resource-constrained Internet of Things (IoT) network devices. RPL has become a widely adopted protocol for routing in low-powered device networks. However, it lacks essential security features, including end-to-end security, robust authentication, and intrusion detection capabilities. Blockchain is a decentralized and immutable digital ledger that records transactions across multiple computers. It provides privacy, transparency, security, and trust. In this work, we proposed a blockchain-based reliable RPL protocol called reliable-RPL, which uses node reliability, link reliability, and relative trust scores of RPL-enabled IoT devices. The parent selection and network topology formulation are based on the proposed reliability-aware objective function. A lightweight ECC-based scheme performs registration, identification, and authentication of RPL-enabled IoT devices. The consistent topological updates from these authenticated IoT devices are used to secure routing paths in RPL-enabled networks. Using a modified trickle algorithm, we employed a reputation-based trust system that monitors and labels malicious nodes based on their reliable activities. The novelty of the proposed framework relies on integrating Contiki-NG (as fronted for IoT network simulation) and Hyperledger Fabric (as a backend for blockchain-based device authentication and trust-based attack resilience regarding rank, replay, sinkhole, and route poisoning attacks). The experimental evaluation of reliable-RPL has demonstrated its effectiveness compared to state-of-the-art methods regarding significant performance metrics, including packet loss, routing overhead, and throughput on Hyperledger Caliper.

In this paper, UAVs are used to enlarge the positioning range and eliminate the blind area for object localization. The motion parameters of transceivers are considered to be unavailable, and the localization problem is highly nonlinear to the unknown parameters. To this end, the semidefinite relaxation (SDR) technique is proposed to solve the localization problem. Since the constrained relationship among the variables is difficult to be fully included in the stage-one SDR problem, we develop a novel two-stage SDR solution for this localization problem. The performance of the two-stage SDR solution is proven to be close to the Cramér-Rae Lower Bound (CRLB) accuracy at the small noise levels. The simulated results show that the two-stage SDR solution performs better than the closed-form solution, especially at high noise levels.

PLC control programs are vulnerable to real-time threats, where attackers can disrupt the backhaul/front-end network of industrial production by creating numerous loops or I/O operations, leading to severe consequences. Therefore, formal verification of PLC control logic at the binary level is essential. In this study, we introduce a framework designed for formal verification of PLC control logic at the binary level. Our verification framework is based on simulation execution, which extracts the core control logic from PLC binary code. Initially, we develop an efficient framework for automating the parsing of PLC programs at the binary level and constructing their control flow graphs (CFGs). Next, we devise an algorithm to transform the reversed PLC assembly program into an smv model, a widely accepted formal verification tool. Subsequently, we generate real-time requirements relevant to industrial production and perform formal verification on the constructed models. To assess the real-time performance of our framework in safeguarding PLC systems, we implement a prototype and evaluated it across various representative ICS scenarios. The evaluation results demonstrate the capability of our proposed approach to effectively detect synchronization threats in PLC logic control programs.

The millimeter-wave(mm-Wave) radar based on frequency-modulated continuous wave (FMCW) owns the advantages of non-contact, privacy protection, high resolution, and anti-interference, and it became the hot point that applying the radar in monitoring vital signs for smart home. However, most of current studies focus on how to improve the detection performance under the steady scenarios and give little consideration on the unsteady scenarios with physical interference. In this paper, we propose a method to detect vital signs under unsteady scenarios by a best-effort way. This method automatically differentiates between the steady state and motion state (unsteady) by identifying the motion type, and extracts the vital sign under steady state without physical motion interference. For this end, we first figure out feature spectrograms with range-main velocity information from motion features. And then, employ a sliding windows sampling method to construct data set, and apply ResNet-18 network model in the motion type identification (including steady state). Based on the motion type, the phase signal during steady state and leverage the variational mode decomposition (VMD) algorithm to analyze respiration/heart rate. Experiment results show that using ResNet-18, the recognition accuracy of the motion state and motion type is close to 97%, and the recognition delay is less than 1.1s. Meanwhile, the mean absolute errors of the respiration rate and heart rate drop to 1.7bpm and 3.4bpm respectively.

The convergence of transformative technologies, including the Internet of Things (IoT), Big Data, and Artificial Intelligence (AI), has driven private edge cloud systems to the forefront of research efforts. The access to massive terminals and the emergence of personalized services pose serious challenges for efficient resource management in power private edge cloud systems. To address the challenge of inequitable resource allocation in the private edge cloud, this work proposes an intelligent resource allocation strategy with a slicing and auction approach. By formalizing the resource allocation problem as a Mixed Integer Nonlinear Programming (MINLP) puzzle, the method transforms it into a hierarchical allocation challenge for Mobile Network Operators (MNOs), Mobile Virtual Network Operators (MVNOs), and power terminals. The proposed Multi-hop Progressive Auction Algorithm (MPAA) addresses the sliced resource allocation problem between MNOs and MVNOs. Furthermore, a Terminal Resource Allocation Strategy (TRAS) based on improved particle swarm optimization is proposed to solve the spectrum resource allocation problem between MVNOs and power terminals. Extensive simulation results show that the bidding overhead of MPAA is reduced by 6.12% and the average terminal satisfaction of TRAS is improved by about 1.3% compared to conventional methods, thus improving the utilization of wireless resources within the power AIoT.

Given the severity of air pollution, air quality monitoring has become a crucial aspect of Artificial Intelligence of Things (AIoT) applications, providing essential information for forecasting air pollution. However, the training process for air quality monitoring models heavily relies on the high-performance computing resources, leading to significant energy consumption and associated carbon emissions. This contradicts the objectives of low-carbon and sustainable computing. This article proposes a new hybrid PM2.5 prediction model (NHPPM) for air quality monitoring to address the above challenges. NHPPM prioritizes energy efficiency while maintaining high prediction accuracy by integrating several power-efficient strategies. First, Wiener filtering is used to denoise the multisource air quality data enhancing the efficiency of the multisource data fusion. Second, variational mode decomposition (VMD) decomposes different components of the multisource air quality data, helping to identify and separate the most important factors affecting pollutants. This reduces the data needed for model training and leads to lower resource consumption. Kernel principal component analysis (KPCA) transforms the high-dimensional data into a lower-dimensional representation while retaining the critical information, further minimizing computational demands. Additionally, this article utilizes the informer deep learning model to analyse the trends in air quality data. The model’s effectiveness is validated through the ablation studies, performance evaluation experiments, and short- and long-term prediction experiments. The experimental results show that our model reduces the mean absolute error (MAE) and root mean-square error (RMSE) by 16.2% and 14.9%, respectively, compared to the existing PM2.5 prediction models. Furthermore, it reduces the energy consumption of the model training by 33.8%.

The technology of the Internet of Vehicles (IoV) and digital twins (DTs) is driving deeper connectivity between vehicles and road infrastructure. Through the data exchange of IoV and the simulation of DT technology, vehicle driving decisions, traffic management, and road planning are optimized. However, DT models contain a large amount of private vehicle data, causing the risk of privacy leakage. Distributed artificial intelligence (AI) methods, particularly federated learning (FL) algorithms, ensure data security and privacy by sharing data models rather than sharing private data. Current mainstream algorithms use FL and local differential privacy (LDP) or blockchain approaches to protect data security at the cost of lower model accuracy and larger computation time. In the vehicle road cooperation, we designed a three-layer DT-driven personalized privacy-preserving framework, which includes a physical layer, a DT layer, and an application layer. In our proposed framework, to improve the security and performance of DT models, a time-sensitive PLDP-based FL (TimeSenFLDP) mechanism is proposed to achieve different privacy levels of the DT model of vehicles over sharing time steps. Compared with the mainstream algorithm (e.g., DP-SGD), the experiments prove that our proposed algorithm has 18.07%, 16.32%, and 7.5% accuracy improvement in FedAvg, FedProx, and FedDyn, respectively.

The convergence of blockchain and deep learning (DL) drives the intelligence of the Internet of Things (IoT) with security guarantees. However, the soaring resource consumption resulting from blockchain mining and DL model training has overwhelmed the extremely resource-constrained IoT. In this article, we first build a blockchain and DL-empowered cloud–edge orchestrated framework for an extremely resource-constrained IoT environment. To solve the resource bottleneck of this framework, we then propose a Zero-knowledge Proof of Learning (ZPoL) consensus approach to channel the meaningless Proof of Work (PoW) mining energy waste to valuable DL model training, while protecting the DL model privacy. Besides, to encourage resource-constrained IoT devices to perform meaningful DL model mining in our ZPoL consensus, we design a model quality-aware incentive mechanism based on a two-stage Stackelberg game. Moreover, we conduct extensive simulations and experiments to evaluate our proposed ZPoL-based framework. The numerical simulation illustrates that our proposed incentive mechanism could motivate IoT devices to actively join in DL model mining. Compared with the existing blockchain and DL-enabled IoT system, experimental results demonstrate that our proposed ZPoL-based framework could significantly reduce the communication, computation, and storage cost, which is more applicable to a resource-constrained IoT environment.

Social networking websites are now considered to be the best platforms for the dissemination of news articles. However, information sharing in social media platforms leads to explosion of fake news. Traditional detection methods were focusing on content analysis, while the current researchers examining social features of the news. In this work, we proposed a novel artificial intelligence (AI)-assisted fake news detection with deep natural language processing (NLP) model. The proposed work is characterized in four layers: publisher layer, social media networking layer, enabled edge layer, and cloud layer. In this work, four steps were carried out: 1) data acquisition; 2) information retrieval (IR); 3) NLP-based data processing and feature extraction; and 4) deep learning-based classification model that classifies news articles as fake or real using credibility score of publishers, users, messages, headlines, and so on. Three datasets, such as Buzzface, FakeNewsNet, and Twitter, were used for evaluation of the proposed model, and simulation results were computed. This proposed model obtained an average accuracy of 99.72% and an$F1$score of 98.33%, which outperforms other existing methods.

Multimodal retrieval has received widespread consideration since it can commendably provide massive related data support for the development of computational social systems (CSSs). However, the existing works still face the following challenges: 1) rely on the tedious manual marking process when extended to CSS, which not only introduces subjective errors but also consumes abundant time and labor costs; 2) only using strongly aligned data for training, lacks concern for the adjacency information, which makes the poor robustness and semantic heterogeneity gap difficult to be effectively fit; and 3) mapping features into real-valued forms, which leads to the characteristics of high storage and low retrieval efficiency. To address these issues in turn, we have designed a multimodal retrieval framework based on web-knowledge-driven, calledunsupervised and robust graph convolutional hashing(URGCH). The specific implementations are as follows: first, a “secondary semantic self-fusion” approach is proposed, which mainly extracts semantic-rich features through pretrained neural networks, constructs the joint semantic matrix through semantic fusion, and eliminates the process of manual marking; second, a “adaptive computing” approach is designed to construct enhanced semantic graph features through the knowledge-infused of neighborhoods and uses graph convolutional networks for knowledge fusion coding, which enables URGCH to sufficiently fit the semantic modality gap while obtaining satisfactory robustness features; Third, combined with hash learning, the multimodality data are mapped into the form of binary code, which reduces storage requirements and improves retrieval efficiency. Eventually, we perform plentiful experiments on the web dataset. The results evidence that URGCH exceeds other baselines about$1\%$–$3.7\%$in mean average precisions (MAPs), displays superior performance in all the aspects, and can meaningfully provide multimodal data retrieval services to CSS.

The increase in popularity of vehicles encourages the development of smart cities. With this advancement, vehicular ad-hoc networks, or VANETs, are now frequently utilized for inter-vehicular communication to gather data regarding traffic congestion, vehicle location, speed, and road conditions. Such a public network is open to various security risks. Overall, protecting personal information on VANET is a vital responsibility. The integration of fog computing and VANETs has gained significant importance in recent years, driven by advancements in cloud computing, Internet of Things (IoT) technologies, and intelligent transportation systems. However, ensuring secure communication in fog-based VANETs remains a major challenge. To overcome this challenge, we introduce a novel authenticated key agreement protocol that achieves mutual authentication, generates a secure session key for secret communication, and provides privacy protection without the use of bilinear pairing. We rigorously prove the security of our proposed protocol, which is designed specifically for fog-based VANETs, and has been shown to meet their stringent security requirements. Moreover, we performed formal and informal analysis that shows our proposed protocol is highly efficient,our protocol’s computational and communication overhead are lower than those of other relevant protocols by 45.570% and 29.432%, respectively. Finally we use NS-3 simulation to prove that our proposed algorithm is a practical and scalable solution for secure communication in fog-based VANETs.

Artificial intelligence has been utilized to analyze patients' electroencephalograms (EEG) to diagnose depression. However, attackers can deduce patients' privacy after analyzing patients' EEG time series. Therefore, researchers propose to operate ciphertext calculation in depression diagnosis models based on homomorphic encryption. Nevertheless, homomorphic encryption requires consistent private keys during training, which could result in other participants decrypting the ci-phertexts. Additionally, existing EEG-based models neglect the relationship among electrode positions during EEG acquisition. To address these issues, we propose a novel training strategy for the depression diagnosis model based on fully homomorphic en-cryption (FHE) and electrode topology. Specifically, we establish a training strategy that prioritizes the privacy of patients' EEG data without compromising the cost-effectiveness of the diagnosis model. Furthermore, we incorporate the attention mechanism of electrode topology into our model to improve its performance and verify the relationship among topology locations. Our proposed model outperforms the original convolution neural network model, achieving higher accuracy in depression diagnosis and identifying virtual electrode channels for the first time.

With the rapid development of loT technology, various loT devices enter our daily life. The continuously increasing scale of the massive loT devices in both of numbers and types further bring heavy pressure on loT network management and security. Therefore, how to accurately identify and efficiently manage so massive loT devices has become a challenge. In this paper, we propose BcllS, Blockchain-based Intelligent Identification Scheme of Massive loT Devices. It applies a decentralized identification architecture and realizes learning sustainably as well as efficiently identifying by updating the identification model constantly according to the ledger which is maintained by all gateways collaboratively. Experiments show that the identification accuracy can achieve up to 99.5 %.

The study aims to leverage the vending machine's historic product sales data to predict future demand using machine learning (ML) techniques with the goal of strategic inventory planning, reducing stock waste, and increasing operational efficiency and revenue. The study deploys different ML algorithms including XGBoost, FB Prophet, Autoregressive Integrated Moving Average and Support Vector Regression. This is among the first studies of its kind to explore ML for predictive restocking in the vending industry. The experiment is divided into two parts. In the first part, we used common historic sales data variables to make the prediction where XGBoost emerged as the best-performing model in terms of the mean absolute error. In the second part, we used additional features such as public holidays, day of the week, and sales deviation flags to make the prediction. Using additional variables slightly improved the performance of the ML algorithms with XGBoost having the lowest mean absolute error of 8. Overall, the study demonstrates the efficacy of utilising ML techniques and additional features in accurately predicting future product demand for vending machines, thus enabling strategic inventory planning, minimised stock waste, improved operational efficiency and increased revenue for the vending industry.

This work studies the built-in multicast model in Contiki OS to provide the basis of a comparative evaluation for a new optimisation model using Radio Duty Cycling (RDC) mechanism. A significant amount of energy is consumed at the edge node executing various multicast routing protocols in Low-Power and Lossy Networks (LLN). The optimisation of the routing protocol and selection of an efficient multicast transmission model has the potential to reduce energy consumption in Edge Computing (EC) enabled LLN. With the precise objective of reducing energy consumption, this paper utilises a well-known RDC technique in multicast communication scenarios. To this end, a series of experiments are conducted to evaluate the performance of the existing RDC mechanisms proposed in the literature. The evaluation results are then utilised to develop an efficient RDC-based multicast transmission model. The comparative performance analysis reveals a 23.7% reduction in the RDC rate compared to the traditional model, consequently improving the energy consumption of EC-enabled LLN.

Underwater Wireless Sensor Networks (UWSNs) are among the most promising research areas these days due to their unique characteristics and diverse underwater applications. Though a number of routing protocols have been designed and implemented for UWSNs over the past few years, the researchers face several challenges, e.g., low speed of propagation, small bandwidth, limited battery power, etc., while designing routing protocols for communication in UWSNs. Acoustic sensor nodes are equipped with batteries with limited power and it is quite costly to replace or recharge them. The network will not survive for the desired period of time if the power of node batteries is not efficiently used. To effectively resolve this issue, this paper proposes a Shifted Energy Efficiency and Priority (SHEEP) routing protocol for UWSNs. The proposed protocol aims to enhance the efficiency of the state-of-the-art Energy Balanced Efficient and Reliable Routing (EBER2) protocol for UWSNs. SHEEP is built upon the depth and energy of the current forwarding node, the depth of the expected next forwarding node, and the average energy difference among the expected forwarders. Simulation results demonstrate that SHEEP improves the energy efficiency and packet delivery ratio of EBER2 by 7.4% and 13% respectively.

Recent technological advancements have considerably improved healthcare systems to provide various intelligent services, improving life quality. The Metaverse, often described as the next evolution of the Internet, helps the users interact with each other and the environment, thus offering a seamless connection between the virtual and physical worlds. Additionally, the Metaverse, by integrating emerging technologies, such as artificial intelligence (AI), cloud edge computing, Internet of Things (IoT), blockchain, and semantic communications, can potentially transform many vertical domains in general and the healthcare sector (healthcare Metaverse) in particular. The healthcare Metaverse holds huge potential to revolutionize the development of intelligent healthcare systems, thus presenting new opportunities for significant advancements in healthcare delivery, personalized healthcare experiences, medical education, collaborative research, and so on. However, various challenges are associated with the realization of the healthcare Metaverse, such as privacy, interoperability, data management, and security. Federated learning (FL), a new branch of AI, opens up enormous opportunities to deal with the aforementioned challenges in the healthcare Metaverse by exploiting the data and computing resources available at the distributed devices. This motivated us to present a survey on adopting FL for the healthcare Metaverse. Initially, we present the preliminaries of IoT-based healthcare systems, FL in conventional healthcare, and the healthcare Metaverse. Furthermore, the benefits of the FL in the healthcare Metaverse are discussed. Subsequently, we discuss the several applications of FL-enabled healthcare Metaverse, including medical diagnosis, patient monitoring, medical education, infectious disease, and drug discovery. Finally, we highlight the significant challenges and potential solutions toward realizing FL in the healthcare Metaverse.

A common practice among programmers is to reuse existing code, accomplished by performing natural language queries through search engines. The main aim of code retrieval is to search for the most relevant snippet from a corpus of code snippets. However, code retrieval frameworks for low-resource languages are insufficient. Retrieving the most relevant code snippet efficiently can be accomplished only by eliminating the semantic gap between the code snippets residing in the repository and the user’s query (natural language description). The primary objective of the research is to contribute to this field by providing a code search framework that can be extended for low-resource languages. The secondary objective is to provide a code retrieval mechanism that is semantically relevant to the user query and provide programmers with the ability to locate source code that they want to use when developing new applications. The proposed approach is implemented using a web platform to search for source code. As code retrieval is a sophisticated task, the proposed approach incorporates a semantic search mechanism. This research uses a semantic model for code retrieval, which generates meanings or synonyms of words. The proposed model integrates ontologies and Natural Language Processing. System performance measures and classification accuracy are computed using precision, recall, and F1-score. We also compare the proposed approach with state-of-the-art baseline models. The retrieved results are ranked, showing that our approach significantly outperforms robust code matching. Our evaluation shows that semantic matching leads to improved source code retrieval. This study marks a substantial advancement in integrating programming expertise with code retrieval techniques. Moreover, our system lets users know when and how it is used for successful semantic searching.

The rumors in the healthcare system have the attributes of fast spread and severe social influence. Even worse, it may cause the collapse of medical services and the death of many patients. To prevent its serious impact on society, the target of rumor suppression for the healthcare system is to restrain the spread of rumors (negative opinions) and maximize the spread of antirumors (positive opinions). Therefore, in this article, for the first time, we propose comprehensive learning-based particle swarm optimization with opinion maximization (OM) to address the rumors suppression problem in the healthcare system. We define the rumor suppression problem in the healthcare system based on OM and devise two opinion propagation models. Then, we propose a directed acyclic graph-based objective function to evaluate the opinion propagation and solve this problem using comprehensive learning particle swarm optimization. Experimental results show that our proposed scheme achieves better results for positive opinion propagation in the scenario of rumor suppression in the healthcare system than the baseline algorithms.

Federated learning (FL) is receiving much attention in the Healthcare Internet of Things (H-IoT) to support various instantaneous E-health services. Today, the deployment of FL suffers from several challenges, such as high training latency and data privacy leakage risks, especially for resource-constrained medical devices. In this article, we develop a three-layer FL architecture to decrease training latency by introducing split learning into FL. We formulate a long-term optimization problem to minimize the local model training latency while preserving the privacy of the original medical data in H-IoT. Specially, a Privacy-ware Model Partitioning Algorithm (PMPA) is proposed to solve the formulated problem based on the Lyapunov optimization theory. In PMPA, the local model is partitioned properly between a resource-constrained medical end device and an edge server, which meets privacy requirements and energy consumption constraints. The proposed PMPA is separated into two phases. In the first phase, a partition point set is obtained using Kullback-Leibler (KL) divergence to meet the privacy requirement. In the second phase, we employ the model partitioning function, derived through Lyapunov optimization, to select the partition point from the partition point set that that satisfies the energy consumption constraints. Simulation results show that compared with traditional FL, the proposed algorithm can significantly reduce the local training latency. Moreover, the proposed algorithm improves the efficiency of medical image classification while ensuring medical data security.

As an important carrier of healthcare data, Electronic Medical Records (EMRs) generated from various sensors, i.e., wearable, implantable, are extremely valuable research materials for artificial intelligence and machine learning. The efficient circulation of EMRs can improve remote medical services and promote the development of the related healthcare industry. However, in traditional centralized data sharing architectures, the balance between privacy and traceability still cannot be well handled. To address the issue that malicious users cannot be locked in the fully anonymous sharing schemes, we propose a trackable anonymous remote healthcare data storing and sharing scheme over decentralized consortium blockchain. Through an "on-chain & off-chain" model, it relieves the massive data storage pressure of medical blockchain. By introducing an improved proxy re-encryption mechanism, the proposed scheme realizes the fine-gained access control of the outsourced data, and can also prevent the collusion between semi-trusted cloud servers and data requestors who try to reveal EMRs without authorization. Compared with the existing schemes, our solution can provide a lower computational overhead in repeated EMRs sharing, resulting in a more efficient overall performance.

As technology advances, cities are getting smarter. Smart mobility is the key element in smart cities and Autonomous Driving (AV) are an essential part of smart mobility. However, the vulnerability of unmanned vehicles can also affect the value of life and human safety. In this paper, we provide a comprehensive analysis of 3D Point-Cloud (3DPC) processing and learning in terms of development, advancement, and performance for the AV system. 3DPC has recently attracted growing interest due to its extensive applications, such as autonomous driving, computer vision, and robotics. Light Detection and Ranging Sensors (LiDAR) is one of the most significant sensors in AV, which collects 3DPC that can accurately capture the outer surfaces of scenes and objects. Learning and processing tools in the 3DPC are essential for creating maps, perceptions, and localization devices in AV. The intention behind 3DPC learning and practical processing tools is to be considered the most essential modules to create, locate, and perceive maps in an AV system. The goal of the study is to know “what has been tested in AV system so far and what is necessary to make it safer and more practical in AV system.” We also provide insights into the necessary open problems that are required to be resolved in the future.

The Internet of Things (IoT) is delivering solutions with improved efficiency and security, and providing better productivity in manufacturing, retail, and other sectors. Maritime Transportation Systems (MTSs) is currently adopting the IoT to move toward a digitalized, data-driven world with increased efficiency and lower costs, and creating new revenue opportunities. Integration of the IoT also enables real-time tracking of shipments, improved efficiency in cargo handling, pre-emptive maintenance, route optimization, reduced fuel consumption, and improved safety in maritime transportation systems. With IoT technology expanding and evolving rapidly, more applications are predicted to assist and improve all aspects of MTSs, making them hassle-free and safe.

In order to fulfill the requirements of Intelligent Transportation Systems (ITS) on ultra-delay service response, task scheduling for trajectory analysis is being shifted from the data center into the network edge of ITS. Such a decentralized paradigm motivates the computing power of the edge device and makes traditional analysis tasks open to the users around ITS. However, since these ITS users have differentiated identities and roles with differentiated security demands and privacy protection, assigning tasks for different users requires identifying and assessing the vulnerability of edge intelligence entities (EIEs). Otherwise, sensitive tasks assigned to the vulnerable EIEs will extremely increase the security risks of industrial control networks. To solve these problems, this paper proposes a vulnerability-aware task scheduling (VATS) mechanism, which integrates vulnerability assessment and access control. With VATS, secure EIEs can obtain more permissions and join in the privacy-sensitive trajectory analysis task, which is essential to enhance privacy protection at edges and ultimately improve the efficiency of task scheduling. The simulation results demonstrate the validity of the proposed scheme to defend insecure task scheduling like trajectory analysis.

Nowadays, developing environmental solutions to ensure the preservation and sustainability of natural resources is one of the core research topics for providing a better life quality. Using renewable energy sources, such as solar energy, is one of the solutions that can reduce the overuse of natural resources. This research aims to boost the efficiency of solar energy plants by proposing a novel approach to optimize the total flying time of battery-based drone systems to enhance the performance of solar plant systems. The contribution of the proposed approach is to solve scheduling problems based on timing constraints to monitor the solar plant. The main objective of the proposed approach is to maximize the drone’s minimum total flying time, which will increase the availability and reliability of the solar plant monitoring system. Time to empty values is calculated based on battery degradation rates. This problem is proven to be NP-hard. Four categories of enhanced algorithms were developed to solve drones’ scheduling problems in handling various tasks within multiple errands in the extent of solar parks in the monitored power plant to achieve the desired objective. Experimental results of the presented algorithms showed that the$M2S$algorithm has a stable performance behavior in all conducted experiments.

As city boundaries expand and the vehicles continues to proliferate, the transportation system is increasingly overloaded, greatly increasing people’s commuting burden and extending the resulting negative effects to all areas of work and life. It is a big issue that needs to be solved urgently. However, due to the development of infrastructure and technologies in 6G-driven Intelligent Transportation Systems (ITS), it becomes possible to alleviate urban congestion. Existing solutions either optimize the path planning of each vehicle, or only focus on solving the problem of resource allocation of a single road, neither can take advantage of self-organizing networks and easily fall into local optimum. Combining the above reasons, we propose the Direction Decide as a Service (DDaaS) scheme. First, it contains a novel three-layer service architecture based on Swarm Learning (SL), which enables orderly transmission of traffic data and control instructions and protects user privacy. Second, an improved local model and aggregation method is incorporated into DDaaS, which enables to make accurate predictions when the road resources at a single intersection are insufficient. Third, we propose a dynamic traffic control algorithm to provide signal light switching decisions for rapidly changing ITS. Finally, constructing an urban road simulation experiment combined with SUMO, we prove that DDaaS can reduce traffic congestion effectively and has significant advantages compared to other schemes.

Traffic forecasting is essential in improving and maintaining safety and orderliness in intelligent transportation systems (ITS). As a deep learning approach, graph neural networks (GNN) based spatial-temporal association mining methods are promising in traffic forecasting. However, current GNN-based methods usually require a high number of training data, and when the sample volume is small, the performance of the model drops dramatically. The existing transfer methods can solve this problem by leveraging knowledge from other data-rich areas, but the domain adaption method with access to source data still faces the non-neglectable problem of private information leakage in the source area. A solution that can solve cross-area transfer without access to source data is still missing. In this paper, to fill the gap, we propose a Transferable Federated Inductive Spatial-Temporal Graph Neural Network (T-ISTGNN) framework to transfer spatial-temporal dependency information in cross-area data to accomplish traffic state forecasting. First, we introduce a multi-source model aggregation scheme based on federated learning to retain the traffic information of the source areas. Second, we propose a transfer method between source and target areas based on hypothesis transfer learning to achieve domain adaption under source domain data protection. Third, we propose a GNN-based method called Inductive Spatial-Temporal Graph Neural Network (ISTGNN) for traffic forecasting. Experiments on real-world datasets demonstrate that T-ISTGNN is capable of cross-area traffic state forecasting under the restriction of preserving the privacy of source areas.

In Intelligent Transportation Systems, images are the main data sources to be analyzed for providing intelligent and precision cognitive services. Therefore, how to protect the privacy of sensitive images in the process of information transmission has become an important research issue, especially in future no non-private data era. In this article, we design the Rearrangement-Arnold Cat Map (R-ACM) to disturb the relationship between adjacent pixels and further propose an efficient Bit-level Image Encryption Algorithm ($\text{B}{l}$-IEA) based on R-ACM. Experiments show that the correlation coefficients of two adjacent pixels are 0.0022 in the horizontal direction, -0.0105 in the vertical direction, and -0.0035 in the diagonal direction respectively, which are obviously weaker than that of the original image with high correlations of adjacent pixels. What’s more, the NPCR is 0.996120172, and the UACI is 0.334613406, which indicate that$\text{B}{l}$-IEA has stronger ability to resist different attacks compared with other solutions. Especially, the lower time complexity and only one round permutation make it particularly suitable to be used in the time-limited intelligent transportation field.

The traffic anomaly analysis in IoT-based intelligent transportation system (ITS) is crucial to improving public transportation safety and efficiency. The issue is also challenging due to the unbalanced distribution of anomaly data in IoT-based ITS, which may cause overfitting or underfitting in the training phase. However, some research on traffic anomaly analysis injected limited data to address the shortage of anomaly samples or even neglects this issue, which overlooks the potential representation of nodes in graph neural networks. In this paper, we propose an improved contrastive GNN-based learning framework for traffic anomaly analysis that alleviates the problem of imbalanced datasets in the training phase. In this framework, we provide a graph augmentation approach with coupled features to learn different views of graph data. Besides, we design an effective training method based on the contrastive loss for our framework, which can learn the better performance of latent representations utilized in the downstream tasks. Finally, we conduct extensive experiments to evaluate the performance of our proposed frame-works based on real-world datasets. We demonstrate that our framework achieves as high as 6.45% precision improvement compared to the state-of-the-art.

The development of backhaul/fronthaul networks can enable low latency and high reliability, but nodes in future networks like Internet of Things (IoT) can conduct malicious activities like flooding attack and DDoS attack, which can decrease QoS of smart backhaul/fronthaul network. Timely detection of malicious nodes in future networks is significant for low-latency backhaul/fronthaul networks. However, conventional supervised learning-based detection models require abundant malicious training samples, while capturing adequate malicious samples can not meet the requirement of timely detection. In this paper, we propose a novel few-shot malicious node detection system for improving QoS of IoT backhaul/fronthaul network, which can detect malicious nodes with unknown malicious activities through a limited number of network traffic samples. In our proposed system, we first design a fresh IoT traffic sample processing approach, which integrates normal activity samples and known malicious activity samples to generate training pairs. Then, we design a metric learning-based malicious node detection model training method, which employs a contrastive loss over distance metric to distinguish between similar and dissimilar pairs of samples. Besides, the trained model can detect nodes with unknown malicious activities by comparing real-time samples with few-shot samples of malicious nodes. Finally, the proposed system is evaluated on a real-world IoT network dataset named N-BaIoT. The exhaustive experiment results show that our model can achieve an average accuracy around 97.67 % when detecting malicious nodes with unknown malicious activities, which is comparable to state-of-the-art supervised learning models while our model only needs 5-shot samples of malicious node.

Intelligent algorithms-driven industrial decision systems have been a general demand for modeling complex sewage treatment processes (STP). Existing researches modeled complex STP with the use of various neural network models, yet neglecting the fact that latent and occasional relations exist inside complex STP. To deal with the challenge, this paper proposes graph embedding-based intelligent industrial decision for complex STP (GE-STP). The graph embedding (GE) scheme is employed to enhance feature extraction and neural computing structure is utilized to simulate uncertain biochemical transformation inside STP. The introduction of GE can not only improves the fineness of feature spaces, but also improves the representative ability of models towards complex industrial processes. On this basis, the GE-STP is evaluated on a real-world data set collected from a realistic sewage treatment plant equipped with a set of Internet of Things devices. And some typical neural network models that have been utilized for modeling complex STP, are selected as baseline methods. Three groups of experiments show that efficiency of the GE-STP exceeds baselines about 6%–12%, and that the GE-STP is not susceptible to parameter changing.

The existing Underwater Internet of Things (UIoT) is based on the IP architecture, which is not conducive to the efficient storage and distribution of huge amounts of content generated in underwater. Actively pushing all content to users causes much unnecessary resource consumption in the UIoT. The information-centric networking (ICN) architecture opens new horizons up for these challenges. However, the slowness of underwater propagation speed makes traditional ICN not suitable for UIoT, especially considering about delay time. In this article, we propose an information-centric wireless sensor networking scheme with water-depth-aware content caching (ICWSN-WDA) to solve the above challenges. First, we design a naming scheme and a hybrid communication mode suitable for ICWSN-WDA. The communication mode in underwater we design is divided into push and pull traffic, which balances energy consumption and delay time. Second, we define a push level to decide which water depth the content actively pushes to, finding a suitable junction point of two modes. Third, as the water depth is deeper, it becomes more difficult to replace the sensor battery. To save energy consumption of deep-water sensors, the water-depth-aware caching mechanism is proposed based on water depth, popularity, and senor energy. Our extensive evaluation confirms the effectiveness of our proposed scheme, and it balances energy consumption constraints and latency.

Recently, edge artificial intelligence techniques (e.g., federated edge learning) are emerged to unleash the potential of big data from Internet of Things (IoT). By learning knowledge on local devices, data privacy preserving and Quality of Service (QoS) are guaranteed. Nevertheless, the dilemma between the limited on-device battery capacities and the high energy demands in learning is not resolved. When the on-device battery is exhausted, the edge learning process will have to be interrupted. In this article, we propose a novel wirelessly powered edge intelligence (WPEG) framework, which aims to achieve a stable, robust, and sustainable edge intelligence by energy harvesting (EH) methods. First, we build a permissioned edge blockchain to secure the peer-to-peer (P2P) energy and knowledge sharing in our framework. To maximize edge intelligence efficiency, we then investigate the wirelessly powered multiagent edge learning model and design the optimal edge learning strategy. Moreover, by constructing a two-stage Stackelberg game, the underlying energy-knowledge trading incentive mechanisms are also proposed with the optimal economic incentives and power transmission strategies. Finally, simulation results show that our incentive strategies could optimize the utilities of both parties compared with classic schemes, and our optimal learning design could realize the optimal learning efficiency.

The Industrial Internet of Things (IIoT), a typical Internet of Things (IoT) application, integrates the global industrial system with other advanced computing, analysis, and sensing technologies through Internet connectivity. Due to the limited storage and computing capacity of edge and IIoT devices, data sensed and collected by these devices are usually stored in the cloud. Encryption is commonly used to ensure privacy and confidentiality of IIoT data. However, the key used for data encryption and decryption is usually directly stored and managed by users or third-party organizations, which has security and privacy implications. To address this potential security and privacy risk, we propose a Shamir threshold cryptography scheme for IIoT data protection using blockchain: STCChain. Specifically, in our solution, the edge gateway uses a symmetric key to encrypt the data uploaded by the IoT device and stores it in the cloud. The symmetric key is protected by a private key generated by the edge gateway. To prevent the loss of the private key and privacy leakage, we use a Shamir secret sharing algorithm to divide the private key, encrypt it, and publish it on the blockchain. We implement a prototype of STCChain using Xuperchain, and the results show that STCChain can effectively prevent attackers from stealing data as well as ensuring the security of the encryption key.

The Covid-19 pandemic has emerged as one of the most disquieting worldwide public health emergencies of the 21st century and has thrown into sharp relief, among other factors, the dire need for robust forecasting techniques for disease detection, alleviation as well as prevention. Forecasting has been one of the most powerful statistical methods employed the world over in various disciplines for detecting and analyzing trends and predicting future outcomes based on which timely and mitigating actions can be undertaken. To that end, several statistical methods and machine learning techniques have been harnessed depending upon the analysis desired and the availability of data. Historically speaking, most predictions thus arrived at have been short term and country-specific in nature. In this work, multimodel machine learning technique is called EAMA for forecasting Covid-19 related parameters in the long-term both within India and on a global scale have been proposed. This proposed EAMA hybrid model is well-suited to predictions based on past and present data. For this study, two datasets from the Ministry of Health & Family Welfare of India and Worldometers, respectively, have been exploited. Using these two datasets, long-term data predictions for both India and the world have been outlined, and observed that predicted data being very similar to real-time values. The experiment also conducted for statewise predictions of India and the countrywise predictions across the world and it has been included in the Appendix.

As one of the most successful industrial realizations of Internet of Things, a smart grid is a smart IoT system that deploys widespread smart meters to capture fine-grained data on residential power usage. Unfortunately, it always suffers diverse privacy attacks, which seriously increases the risk of violating the privacy of customers. Although some solutions have been proposed to address this privacy issue, most of them mainly rely on a trusted party and focus on the sanitization of metering masurements. Moreover, these solutions are vulnerable to advanced attacks. In this paper, we propose a decentralized mechanism for privacy-preserving computation in smart grid called DDP, which leaverages the differential privacy and extends the data sanitization from the value domain to the time domain. Specifically, we inject Laplace noise to the measurements at the end of each customer in a distributed manner, and then use a random permutation algorithm to shuffle the power measurement sequence, thereby enforcing differential privacy after aggregation and preventing the sensitive power usage mode informaton of the customers from being inferred by other parties. Extensive experiments demonstrate that DDP shows an outstanding performance in terms of privacy from the non-intrusive load monitoring (NILM) attacks and utility by using two different error analysis.

Accessibility to smart devices provides opportunities for side-channel attacks (SCAs) on artificial intelligent (AI) models in the intelligent Internet of Things (IoT). However, the existing literature exposes some shortcomings: 1) incapability of quantifying and analyzing the leaked information through side channels of the intelligent IoT and 2) inability to devise efficient and accurate SCA algorithms. To address these challenges, we propose a side-channel fuzzy analysis-empowered AI model extraction attack in the intelligent IoT. First, the integrated AI model extraction framework is proposed, including power trace-based structure, execution time-based metaparameters, and hierarchical weight extractions. Then, we develop the information theory-based analysis for the AI model extraction via SCA. We derive a mutual information-enabled quantification method, theoretical lower/upper bounds of information leakage, and the minimum number of attack queries to obtain accurate weights. Furthermore, a fuzzy gray correlation-based multiple-microspace parallel SCA algorithm is proposed to extract model weights in the intelligent IoT. Based on the established information-theoretic analysis model, the proposed fuzzy gray correlation-based SCA algorithm obtains high-precision AI weights. Experimental results, consisting of simulation and real-world experiments, verify that the developed analysis method with the information-theoretic perspective is feasible and demonstrate that the designed fuzzy gray correlation-based SCA algorithm is effective for AI model extraction.

Recently, the Internet of Medical Things (IoMT) could offload healthcare services to 5G edge computing for low latency. However, some existing works assumed altruistic patients will sacrifice quality of service for the global optimum. For priority-aware and deadline-sensitive healthcare, this sufficient and simplified assumption will undermine the engagement enthusiasm, i.e., unfairness. To address this issue, we propose a long-term proportional fairness-driven 5G edge healthcare, i.e., FairHealth. First, we establish a long-term Nash bargaining game to model the service offloading, considering the stochastic demand and dynamic environment. We then design a Lyapunov-based proportional-fairness resource scheduling algorithm, which decouples the long-term fairness problem into single-slot subproblems, realizing a tradeoff between service stability and fairness. Moreover, we propose a block-coordinate descent method to iteratively solve nonconvex fair subproblems. Simulation results show that our scheme can improve 74.44% of the fairness index (i.e., Nash product), compared with the classic global time-optimal scheme.

Energy harvesting (EH) is a promising and critical technology to mitigate the dilemma between the limited battery capacity and the increasing energy consumption in the Internet of everything. However, the current EH system suffers from energy-information cross threats, facing the overlapping vulnerability of energy deprivation and private information leakage. Although some existing works touch on the security of energy and information in EH, they treat these two issues independently, without collaborative and intelligent protection cross the energy side and information side. To address the aforementioned challenge, this article proposes a joint protection framework of energy security and information privacy for EH with an incentive federated learning approach. First, we design a federated-learning-based malicious energy user detection method according to energy status and behaviors to provide energy security protection. Second, a differential-privacy-empowered information preservation scheme is devised, where sensitive information is perturbed and protected by the customized demand-based noise. Third, a noncooperative-game-enabled incentive mechanism is established to encourage EH nodes to participate in the joint energy-information protection system. The proposed incentive mechanism derives the optimal energy-information security strategy for EH nodes and achieve a tradeoff between the protection of energy security and information privacy. Evaluation results have verified the effectiveness of our proposed joint protection mechanism.

The proliferation of fifth-generation (5G) networks toward vehicle-to-everything (V2X) communication has paved the way for driverless autonomous vehicles (AVs) in vehicular critical energy infrastructures (CEI). Though technological advancements improve AVs, the safety-critical messages (SCMs) still play a vital role in reducing crashes, preventing injuries, and saving lives. AVs’ high speed and complex network topology challenge disseminating SCMs with a highly successful delivery ratio and extremely low latency. Furthermore, the typical SCM dissemination schemes cause channel congestion and minimize the delivery ratio, making the systems incompatible with the AVs. Therefore, in this article, a software-defined-networking-assisted continuous clustering approach called migrating consignment region (MiCR) based on the federated$K$-means algorithm is proposed for disseminating SCMs to the AVs via 5G V2X communication. Unlike other methods that create clusters for every instance of SCM dissemination, MiCR continuously holds moving clusters for disseminating SCMs to AVs with ultrahigh reliability and low latency. The proposed MiCR approach has been simulated under real-time highway road maps and compared with other methods. The simulation results prove the superiority of MiCR in terms of network overload, SCM delivery ratio, latency, dissemination efficiency, and collision rate compared with the existing methods.

According to statistics, in the 185 countries' 36 types of cancer, the morbidity and mortality of lung cancer take the first place, and non-small cell lung cancer (NSCLC) accounts for 85% of lung cancer (International Agency for Research on Cancer, 2018), (Bray et al., 2018). Significantly in many developing countries, limited medical resources and excess population seriously affect the diagnosis and treatment of alung cancer patients. The 21st century is an era of life medicine, big data, and information technology. Synthetic biology is known as the driving force of natural product innovation and research in this era. Based on the research of NSCLC targeted drugs, through the cross-fusion of synthetic biology and artificial intelligence, using the idea of bioengineering, we construct an artificial intelligence assisted medical system and propose a drug selection framework for the personalized selection of NSCLC patients. Under the premise of ensuring the efficacy, considering the economic cost of targeted drugs as an auxiliary decision-making factor, the system predicts the drug effectiveness-cost then. The experiment shows that our method can rely on the provided clinical data to screen drug treatment programs suitable for the patient's conditions and assist doctors in making an efficient diagnosis.

The rising popularity of ICT and the Internet has enabled Unmanned Aerial Vehicle (UAV) to offer advantageous assistance to Vehicular Ad-hoc Network (VANET), realizing a relay node’s role among the disconnected segments in the road. In this scenario, the communication is done between Vehicles to UAVs (V2U), subsequently transforming into a UAV-assisted VANET. UAV-assisted VANET allows users to access real-time data, especially the monitoring data in smart cities using current mobile networks. Nevertheless, due to the open nature of communication infrastructure, the high mobility of vehicles along with the security and privacy constraints are the significant concerns of UAV-assisted VANET. In these scenarios, Deep Learning Algorithms (DLA) could play an effective role in the security, privacy, and routing issues of UAV-assisted VANET. Keeping this in mind, we have devised a DLA-based key-exchange protocol for UAV-assisted VANET. The proposed protocol extends the scalability and uses secure bitwise XOR operations, one-way hash functions, including user’s biometric verification when users and drones are mutually authenticated. The proposed protocol can resist many well-known security attacks and provides formal and informal security under the Random Oracle Model (ROM). The security comparison shows that the proposed protocol outperforms the security performance in terms of running time cost and communication cost and has effective security features compared to other related protocols.

With recent developments in communication technologies, vehicular networks have become a reality with various applications. However, the cybersecurity aspect of vehicular networks is still an open issue that needs to be addressed with novel defence mechanisms against attacks. This paper first presents the state-of-the-art communication technologies in vehicular networks (either inter-vehicle networking or in-vehicle networking) along with their applications. Then we explore novel technologies including machine learning and blockchain as cybersecurity defence mechanisms in vehicular networks. Based on the extensive survey, we highlight some insights for future research to secure vehicular networks.

Digital Twin (DT) has become the key technology in the Intelligent Transportation Systems (ITS) in smart cities to keep the health and reliability of various DT requesters, such as private vehicles, public transportation, energy systems, etc. The combination of DT and ITS can further release the potential of participants in smart cities and guarantee their efficiency and reliability. Despite the advantages of DT-enabled ITS, not all requesters need the same level of DT service due to the highly dynamic nature of ITS. Safe and reliable matching between DT and ITS still needs to be resolved. To address these issues, we propose the blockchain-enabled Digital Twin as a Service (DTaaS) for ITS. First, we propose an on-demand DTaaS architecture to fully utilize the sensing capabilities of ITS and the macro perspective of DT. Second, a double-auction model and a price adjustment algorithm are proposed to realize the optimal DT matching for ITS requesters and ensure the benefits of participants. Third, a permissioned blockchain and a novel DT-DPoS consensus mechanism are established to enhance the security and efficiency of DTaaS. Simulation shows that the proposed DTaaS and double-auction can efficiently stimulate and facilitate DT transactions. The proposed DT-DPoS also has obvious advantages.

The ever-increasing traffic, various delay-sensitive services, and energy consumption-constrained requirements have brought huge challenges to the current communication networks in the vehicular ad-hoc networks (VANETs). These challenges motivate academia and industry to investigate novel architectures with powerful data transmission and processing capabilities for low-latency and high energy-efficiency vehicular communication. In this paper, we propose an artificial intelligence (AI) and intelligent reflecting surface (IRS) empowered energy-efficiency communication system for VANETs. First, we design a smart and efficient hybrid vehicular communication framework, where IRS-aided dedicated short-range communication and long term evolution-based cellular communication are combined for data transmission in VANETs. Secondly, an IRS-aided data transmission is proposed to improve vehicular communication, in which the head vehicles selection method is designed. Based on the direct and IRS-reflecting signal propagation, fine-grained beamforming is achieved for directional vehicular transmission. Thirdly, a deep reinforcement learning (DRL) empowered network resource control and allocation scheme is proposed. In this scheme, we formulate an energy efficiency-maximizing model under the given transmission latency for VANETs and jointly optimize the settings of all participants to achieve efficient and low-latency communication. Finally, experimental results verify the effectiveness of our proposed communication system for VANETs.

Intelligent vehicular network (IVN) is the underlying support for the connected vehicles and smart city, but there are several challenges for IVN data processing due to the dynamic structure of the vehicular network. Graph processing, as one of the essential machine learning and big data processing paradigm, which provide a set of big data processing scheme, is well-designed to processing the connected data. In this paper, we discussed the research challenges of IVN data processing and motivated us to address these challenges by using graph processing technologies. We explored the characteristics of the widely used graph algorithms and graph processing frameworks on GPU. Furthermore, we proposed several graph-based optimization technologies for IVN data processing. The experimental results show the graph processing technologies on GPU can archive excellent performance on IVN data.

Device identification is of great importance in system management and network security. Especially, it is the priority in industrial internet of things (IIoT) scenario. Since there are massive devices producing various kinds of information in manufacturing process, the robustness, reliability, security and real-time control of the whole system is based on the identification of the massive IIoT devices. Previous IIoT device identification solutions are mostly based on a centralized architecture, which brings a lot of problems in scalability and security. In addition, most traditional identification systems can only identify inherent types of devices which is not suitable for the adaptive device management in IIoT. In order to solve these problems, this paper proposes a Intelligent Identification Scheme(IIS) of Massive IoT Devices, a completely distributed intelligent identification scheme of massive IIoT devices. The scheme changes the traditional centralized architecture and realizes more efficient clustering identification of massive IIoT devices. Moreover, IIS can identify more and more types of devices intelligently with the continuous learning ability since the identification model is constantly updated according to the ledger which is maintained by all gateways collaboratively. We also conduct experiments to evaluate the performance of IIS based on the data obtained from real IIoT devices, which proves that IIS is efficient in device identification and intelligent for the adaptive device management in IIoT.

The Internet-of-Things (IoT) devices, backed by resourceful fog computing, are capable of meeting the requirements of computationally-intensive tasks. However, many existing IoT applications are unable to perform well, due to different Quality-of-Service (QoS) requirements, while communicating with the fog server. Besides, constantly changing traffic demands of applications is another challenge. For example, the demand for real-time applications includes communicating over a path that is less prone to delay, and applications that offload computationally intensive tasks to the fog server need a reliable path that has a lower probability of link failure. This results in a tradeoff between conflicting objectives that are constantly evolving, i.e., minimizing end-to-end delay and maximizing the reliability of paths between IoT devices and the fog server. We propose a novel approach that takes advantage of machine learning (ML) and multiobjective optimization (MOO)-based techniques. The reliability of links is evaluated using an ML-based algorithm in an software-defined network (SDN)-enabled multihop scenario for the IoT-fog environment. By considering the two conflicting objectives, the MOO algorithm is used to find the Pareto-optimal paths. Our experimental evaluation considers two applications with different QoS requirements-a real-time application (App-1) using UDP sockets and a task offloading application (App-2) using TCP sockets. Our results show that: 1) the tradeoff between the two objectives can be optimized and 2) the SDN controller was able to make adaptive decision on-the-fly to choose the best path from the Pareto-optimal set. The App-1 communicating over the selected path finished its execution in 13% less time than communicating over the shortest path. The App-2 had 41% less packet loss using the selected path compared to using the shortest path.

The massive increase in computing and network capabilities has resulted in a paradigm shift from vehicular networks to the Internet of Vehicles (IoV). Owing to the dynamic and heterogeneous nature of IoV, it requires efficient resource management using smart technologies, such as software-defined network (SDN), machine learning (ML), and so on. Roadside units (RSUs) in software-defined-IoV (SD-IoV) networks are responsible for network efficiency and offer several safety functions. However, it is not viable to deploy enough RSUs, and also the existing RSU placement lacks universal coverage within a region. Furthermore, any disruption in network performance or security impacts vehicular activities severely. Thus, this work aims to improve network efficiency through optimal RSU placement and enhance security with a malicious IoV detection algorithm in an SD-IoV network. Therefore, the memetic-based RSU (M-RSU) placement algorithm is proposed to reduce communication delay and increase the coverage area among IoV devices through an optimum RSU deployment. Besides the M-RSU algorithm, the work also proposes a distributed ML (DML)-based intrusion detection system (IDS) that prevents the SD-IoV network from disastrous security failures. The simulation results show that M-RSU placement reduces the transmission delay. The DML-based IDS detects the malicious IoV with an accuracy of 89.82% compared to traditional ML algorithms.

Spamming is emerging as a key threat to the Internet of Things (IoT)-based social media applications. It will pose serious security threats to the IoT cyberspace. To this end, artificial intelligence-based detection and identification techniques have been widely investigated. The literature works on IoT cyberspace can be categorized into two categories: 1) behavior pattern-based approaches and 2) semantic pattern-based approaches. However, they are unable to effectively handle concealed, complicated, and changing spamming activities, especially in the highly uncertain environment of the IoT. To address this challenge, in this article, we exploit the collaborative awareness of both patterns, and propose a Collaborative neural network-based spammer detection mechanism (Co-Spam) in social media applications. In particular, it introduces multisource information fusion by collaboratively encoding long-term behavioral and semantic patterns. Hence, a more comprehensive representation of the feature space can be captured for further spammer detection. Empirically, we implement a series of experiments on two real-world data sets under different scenarios and parameter settings. The efficiency of the proposed Co-Spam is compared with five baselines with respect to several evaluation metrics. The experimental results indicate that the Co-Spam has an average performance improvement of approximately 5% compared to the baselines.

Resource allocation and management in an Internet-of-Things (IoT) paradigm requires precise request and response processing irrespective of its scalability support. Unpredictable traffic patterns and user density demands reliable offloading for handling user request traffic and service response. Considering the need for large-scale IoT in an account of its interoperability and heterogeneous support, this manuscript introduces a response-aware traffic offloading scheme (RTOS) for delay-sensitive user requests. This offloading scheme is supported by a multivariate spline regression machine learning model for classifying traffic for reducing the failure rate. The splines are adaptive based on the classified traffic for performing independent and shared offloading. The computation process for determining the offloading model is inherited from the cyber-physical system (CPS) coupled with the IoT-Cloud architecture. The information from the knowledge base and event logs are exploited for decision making in employing the offloading method for the classified traffic. The simulation analysis of this scheme shows that it is effective in improving the request processing ratio and reducing processing, response time, and delay. The simulation is performed for the varying user density and traffic flows.

Identification of anomaly and malicious traffic in the Internet-of-Things (IoT) network is essential for the IoT security to keep eyes and block unwanted traffic flows in the IoT network. For this purpose, numerous machine-learning (ML) technique models are presented by many researchers to block malicious traffic flows in the IoT network. However, due to the inappropriate feature selection, several ML models prone misclassify mostly malicious traffic flows. Nevertheless, the significant problem still needs to be studied more in-depth that is how to select effective features for accurate malicious traffic detection in the IoT network. To address the problem, a new framework model is proposed. First, a novel feature selection metric approach named CorrAUC is proposed, and then based on CorrAUC, a new feature selection algorithm named CorrAUC is developed and designed, which is based on the wrapper technique to filter the features accurately and select effective features for the selected ML algorithm by using the area under the curve (AUC) metric. Then, we applied the integrated TOPSIS and Shannon entropy based on a bijective soft set to validate selected features for malicious traffic identification in the IoT network. We evaluate our proposed approach by using the Bot-IoT data set and four different ML algorithms. The experimental results analysis showed that our proposed method is efficient and can achieve >96% results on average.

Satellite communication system is expected to play a vital role for realizing various remote Internet-of-Things (IoT) applications in sixth-generation vision. Due to unique characteristics of satellite environment, one of the main challenges in this system is to accommodate massive random access (RA) requests of IoT devices while minimizing their energy consumptions. In this article, we focus on the reliable design and detection of RA preamble to effectively enhance the access efficiency in high-dynamic low-earth-orbit (LEO) scenarios. To avoid additional signaling overhead and detection process, a long preamble sequence is constructed by concatenating the conjugated and circularly shifted replicas of a single root Zadoff-Chu (ZC) sequence in RA procedure. Moreover, we propose a novel impulse-like timing metric based on length-alterable differential cross-correlation (LDCC), that is immune to carrier frequency offset (CFO) and capable of mitigating the impact of noise on timing estimation. Statistical analysis of the proposed metric reveals that increasing correlation length can obviously promote the output signal-to-noise power ratio, and the first-path detection threshold is independent of noise statistics. Simulation results in different LEO scenarios validate the robustness of the proposed method to severe channel distortion, and show that our method can achieve significant performance enhancement in terms of timing estimation accuracy, success probability of first access, and mean normalized access energy, compared with the existing RA methods.

Pulmonary cancer is one of the most dangerous cancers with a high incidence and mortality. An early accurate diagnosis and treatment of pulmonary cancer can observably increase the survival rates, where computer-aided diagnosis systems can largely improve the efficiency of radiologists. In this article, we propose a deep automated lung nodule diagnosis system based on three-dimensional convolutional neural network (3D-CNN) and support vector machine (SVM) with multiple kernel learning (MKL) algorithms. The system not only explores the computed tomography (CT) scans, but also the clinical information of patients like age, smoking history and cancer history. To extract deeper image features, a 34-layers 3D Residual Network (3D-ResNet) is employed. Heterogeneous features including the extracted image features and the clinical data are learned with MKL. The experimental results prove the effectiveness of the proposed image feature extractor and the combination of heterogeneous features in the task of lung nodule diagnosis.

Summary The vast amount of data is key challenge to mine a new scholar that is plausible to be star in the upcoming period. The enormous amount of unstructured data raise every year is infeasible for traditional learning; consequently, we need a high quality of preprocessing technique to expand the performance of traditional learning. We have persuaded a novel approach, Authors classification algorithm using Transfer Learning (ACTL) to learn new task on target area to mine the external knowledge from the source domain. Comprehensive experimental outcomes on real‐world networks showed that ACTL, Node‐based Influence Predicting Stars, Corresponding Authors Mutual Influence based on Predicting Stars, and Specific Topic Domain‐based Predicting Stars enhanced the node classification accuracy as well as predicting rising stars to compared with contemporary baseline methods.

Summary Recently Internet of Things (IoT) is being used in several fields like smart city, agriculture, weather forecasting, smart grids, waste management, etc. Even though IoT has huge potential in several applications, there are some areas for improvement. In the current work, we have concentrated on minimizing the energy consumption of sensors in the IoT network that will lead to an increase in the network lifetime. In this work, to optimize the energy consumption, most appropriate Cluster Head (CH) is chosen in the IoT network. The proposed work makes use of a hybrid metaheuristic algorithm, namely, Whale Optimization Algorithm (WOA) with Simulated Annealing (SA). To select the optimal CH in the clusters of IoT network, several performance metrics such as the number of alive nodes, load, temperature, residual energy, cost function have been used. The proposed approach is then compared with several state‐of‐the‐art optimization algorithms like Artificial Bee Colony algorithm, Genetic Algorithm, Adaptive Gravitational Search algorithm, WOA. The results prove the superiority of the proposed hybrid approach over existing approaches.

Summary Smartphones are equipped with precise hardware sensors including accelerometer, gyroscope, and magnetometer. These devices provide real‐time semantic data that can be used to recognize daily life physical activities for personalized smart health assessment. Existing studies focus on the recognition of simple physical activities but they lacked in providing accurate recognition of physical activities having complex interclass variations. Therefore, this research focuses on the accurate recognition of physical activities having complex interclass variations. We propose a two‐layered approach calledPARCIVthat first clusters similar activities based on semantic data and then recognize them using a machine learning classifier. Our two‐layered approach first bounds the highly indistinguishable activities in clusters to avoid misclassification with other distinguishable activities and thereafter recognize them on a fine‐grained level within each cluster. To evaluate our approach, we make an android application that collects labeled data by using smartphone sensors from 10 participants, while performing activities.PARCIVrecognizes distinguishable as well as indistinguishable activities with high accuracy of 99% on the self‐collected dataset. Furthermore,PARCIVachieve 95% accuracy on the publicly available dataset used by state‐of‐the‐art studies.PARCIVoutperforms various state‐of‐the‐art studies by 8%‐17% for simple activities as well as complex activities.

Multimodal representation learning is beneficial for many multimedia-oriented applications, such as social image recognition and visual question answering. The different modalities of the same instance (e.g., a social image and its corresponding description) are usually correlational and complementary. Most existing approaches for multimodal representation learning are not effective to model the deep correlation between different modalities. Moreover, it is difficult for these approaches to deal with the noise within social images. In this article, we propose a deep learning-based approach named evolutionary adversarial attention networks (EAANs), which combines the attention mechanism with adversarial networks through evolutionary training, for robust multimodal representation learning. Specifically, a two-branch visual-textual attention model is proposed to correlate visual and textual content for joint representation. Then adversarial networks are employed to impose regularization upon the representation by matching its posterior distribution to the given priors. Finally, the attention model and adversarial networks are integrated into an evolutionary training framework for robust multimodal representation learning. Extensive experiments have been conducted on four real-world datasets, including PASCAL, MIR, CLEF, and NUS-WIDE. Substantial performance improvements on the tasks of image classification and tag recommendation demonstrate the superiority of the proposed approach.

Nowadays, rumor spreading has gradually evolved into a kind of organized behaviors, accompanied with strong uncertainty and fuzziness. However, existing fuzzy detection techniques for rumors focused their attention on supervised scenarios that require expert samples with labels for training. Thus, they are not able to well handle the unsupervised scenarios where labels are unavailable. To bridge such gap, this article proposed a fuzzy detection system for rumors through explainable adaptive learning. Specifically, its core is a graph embedding-based generative adversarial network (Graph-GAN) model. First of all, it constructs fine-grained feature spaces via graph-level encoding. Furthermore, it introduces continuous adversarial training between a generator and a discriminator for unsupervised decoding. The two-stage scheme not only solves the fuzzy rumor detection under unsupervised scenarios, but also improves robustness of the unsupervised training. Empirically, a set of experiments are carried out based on three real-world datasets. Compared with seven benchmark methods in terms of four metrics, the results of the Graph-GAN reveal a proper performance, which averagely exceeds baselines by 5–10%.

To improve the quality of service (QoS) needed by several applications areas, the Internet of Things (IoT) tasks are offloaded into the fog computing instead of the cloud. However, the availability of ongoing energy heads for fog computing servers is one of the constraints for IoT applications because transmitting the huge quantity of the data generated using IoT devices will produce network bandwidth overhead and slow down the responsive time of the statements analyzed. In this article, an energy-aware model basis on the marine predators algorithm (MPA) is proposed for tackling the task scheduling in fog computing (TSFC) to improve the QoSs required by users. In addition to the standard MPA, we proposed the other two versions. The first version is called modified MPA (MMPA), which will modify MPA to improve their exploitation capability by using the last updated positions instead of the last best one. The second one will improve MMPA by the ranking strategy based reinitialization and mutation toward the best, in addition to reinitializing, the half population randomly after a predefined number of iterations to get rid of local optima and mutated the last half toward the best-so-far solution. Accordingly, MPA is proposed to solve the continuous one, whereas the TSFC is considered a discrete one, so the normalization and scaling phase will be used to convert the standard MPA into a discrete one. The three versions are proposed with some other metaheuristic algorithms and genetic algorithms based on various performance metrics such as energy consumption, makespan, flow time, and carbon dioxide emission rate. The improved MMPA could outperform all the other algorithms and the other two versions.

The papers in this special section focus on cognitive analytics of social media for industrial manufacturing. Business innovation and industrial intelligence pave the way to a future in which smart factories, intelligent machines, networked processes, and big data are brought together to foster industrial growth and shift the modalities. Industry 4.0 or the Industrial Internet of Things (IIoT) is the latest catchphrase of technological innovation in manufacturing with the goal of increasing productivity in a flexible and efficient manner. Concurrently, the new collaborative Web (called Web 2.0) resiliently defines the notion of the techno-social system of computer-mediated, web/internet-based technologies and channels that have the primary objective of creating and enabling a collaborative and interactive virtual community of participants who can share or communicate information. These social technologies are essentially transforming the way we communicate, collaborate, consume, and create data and characterize one of the insurgent impacts of information technology on any industry, both within and outside industrial boundaries. Social media augments as a nontrivial element to this industrial value chain with the intent of making it more efficient. Collaborative sensing or crowd sensing can be used to help producers, suppliers, and customers understand and use insights learned from large amounts of sensing data in order to obtain competitive advantages

One of the most promising application areas of the industrial Internet of Things (IIoT) is vehicular ad hoc networks (VANETs). VANETs are largely used by intelligent transportation systems to provide smart and safe road transport. To reduce the network burden, software-defined networks (SDNs) act as a remote controller. Motivated by the need for greener IIoT solutions, this article proposes an energy-efficient end-to-end security solution for software-defined vehicular networks (SDVNs). Besides, SDN's flexible network management, network performance, and energy-efficient end-to-end security scheme plays a significant role in providing green IIoT services. Thus, the proposed SDVN provides lightweight end-to-end security. The end-to-end security objective is handled in two levels: 1) in roadside unit (RSU)-based group authentication scheme, each vehicle in the RSU range receives a group ID-key pair for secure communication; and 2) in private collaborative intrusion detection system (p-CIDS), the SDVN detects the potential intrusions inside the VANET architecture using collaborative learning that guarantees privacy through a fusion of differential privacy and homomorphic encryption schemes. The SDVN is simulated in NS2 and MATLAB, and results show increased energy efficiency with lower communication and storage overhead than existing frameworks. In addition, the p-CIDS detects the intruder with an accuracy of 96.81% in the SDVN.

With the advancement of wireless communication, Internet of Things (IoT), and big data, high performance data analytic tools and algorithms are required. Data clustering, a promising analytic technique is widely used to solve the IoT and big-data-based problems, since it does not require labeled datasets. Recently, metaheuristic algorithms have been efficiently used to solve various clustering problems. However, to handle big datasets produced from IoT devices, these algorithm fail to respond within the desired time due to high computation cost. This article presents a new metaheuristic-based clustering method to solve the big data problems by leveraging the strength of MapReduce. The proposed methods leverages the searching potential of military dog squad to find the optimal centroids and MapReduce architecture to handle the big datasets. The optimization efficacy the proposed method is validated against 17 benchmark functions, and the results are compared with five other recent algorithms, namely, bat, particle swarm optimization, artificial bee colony, multiverse optimization, and whale optimization algorithm. Furthermore, a parallel version of the proposed method is introduced using MapReduce [MapReduce-based MDBO (MR-MDBO)] for clustering the big datasets produced from industrial IoT. Moreover, the performance of MR-MDBO is studied on two benchmark UCI datasets and three real IoT-based datasets produced from industry. The F-measure and computation time of the MR-MDBO is compared with the six other state-of-the-art methods. The experimental results witness that the proposed MR-MDBO-based clustering outperforms the other considered algorithms in terms of clustering accuracy and computation times.

As an effective tool, roadside digital billboard advertising is widely used to attract potential customers (e.g., drivers and passengers passing by the billboards) to obtain commercial profit for the advertiser, i.e., the attracted customers' payment. The commercial profit depends on the number of attracted customers, hence the advertiser needs to adopt an effective advertising strategy to determine the advertisement switching policy for each digital billboard to attract as many potential customers as possible. Whether a customer could be attracted is influenced by numerous factors, such as the probability that the customer could see the billboard and the degree of his/her interests in the advertisement. Besides, cooperation and competition among all digital billboards will also affect the commercial profit. Taking the above factors into consideration, we formulate the dynamic advertising problem to maximize the commercial profit for the advertiser. To address the problem, we first extract potential customers' implicit information by using the vehicular data collected by Mobile CrowdSensing (MCS), such as their vehicular trajectories and their preferences. With this information, we then propose an advertising strategy based on multi-agent deep reinforcement learning. By using the proposed advertising strategy, the advertiser could determine the advertising policy for each digital billboard and maximize the commercial profit. Extensive experiments on three real-world datasets have been conducted to verify that our proposed advertising strategy could achieve the superior commercial profit compared with the state-of-the-art strategies.

A large scale fast-growing data generated in intelligent transportation systems (ITS) has become a ponderous burden on the coordination of heterogeneous transportation networks, which makes the traditional cloud-centric storage architecture no longer satisfy new data analytics requirements. Meanwhile, the lack of storage trust between ITS devices and edge servers could lead to security risks in the data storage process. However, a unified data distributed storage architecture for ITS with intelligent management and trustworthiness is absent in the previous works. To address these challenges, this paper proposes a distributed trustworthy storage architecture with reinforcement learning in ITS, which also promotes edge services. We adopt an intelligent storage scheme to store data dynamically with reinforcement learning based on trustworthiness and popularity, which improves resource scheduling and storage space allocation. Besides, trapdoor hashing based identity authentication protocol is proposed to secure transportation network access. Due to the interaction between cooperative devices, our proposed trust evaluation mechanism is provided with extensibility in the various ITS. Simulation results demonstrate that our proposed distributed trustworthy storage architecture outperforms the compared ones in terms of trustworthiness and efficiency.

In this paper, we aim to give a unified performance limit analysis of the visible light-based positioning (VLP) for a vehicular user equipment (UE), which will help to understand the essence of time-domain localization cooperation and gain insights into how to improve the performance limit of the vehicular VLP system. This is challenging due to the complex system models and the complex dependency between UE location performance and orientation performance. To achieve the above goal, we will first characterize the closed-form error bounds of the UE location and orientation at each time slot, respectively, in terms of Fisher information. Generally, the VLP error will propagate over time as the vehicular UE moves, and hence the VLP error at the current time slot is affected by the VLP performance at the previous time slot, the UE mobility and the channel quality. Based on the obtained VLP error bounds, we then reveal the impact of prior UE location knowledge, UE mobility and signal-to-noise-ratio on the VLP performance. Furthermore, the time-domain evolution of the VLP error is studied, where the convergence of the time-domain VLP error evolution is established and its closed-form stable state is quantified, which will shed light on the long-term performance of the vehicular VLP system.

Volunteer computing uses computers volunteered by the general public to do distributed scientific computing. Volunteer computing is being used in high-energy physics, molecular biology, medicine, astrophysics, climate study, and other areas. These projects have attained unprecedented computing power. However, with the development of information technology, the traditional defense system cannot deal with the unknown security problems of volunteer computing . At the same time, Cyber Mimic Defense (CMD) can defend the unknown attack behavior through its three characteristics: dynamic, heterogeneous, and redundant. As an important part of the CMD, the dynamic scheduling algorithm realizes the dynamic change of the service centralized executor, which can enusre the security and reliability of CMD of volunteer computing . Aiming at the problems of passive scheduling and large scheduling granularity existing in the existing scheduling algorithms, this article first proposes a scheduling algorithm based on time threshold and task threshold and realizes the dynamic randomness of mimic defense from two different dimensions; finally, combining time threshold and random threshold, a dynamic scheduling algorithm based on multi-level queue is proposed. The experiment shows that the dynamic scheduling algorithm based on multi-level queue can take both security and reliability into account, has better dynamic heterogeneous redundancy characteristics, and can effectively prevent the transformation rule of heterogeneous executors from being mastered by attackers.

Fingerprint provides an extremely convenient way of identification for a wide range of real-life applications owing to its universality, uniqueness, collectability, and invariance. However, digitized fingerprints may reveal the privacy of individuals. Differential privacy is a promising privacy-preserving solution that is enforced by injecting random noise into preserved objects, such that an adversary with arbitrary background knowledge cannot infer private input from the noisy results. This study proposes FinPrivacy, a privacy-preserving mechanism for fingerprint identification. This mechanism utilizes the low-rank matrix approximation to reduce the dimensionality of fingerprint and the exponential mechanism to carefully determine the value of the optimal rank. Thereafter, FinPrivacy injects Laplace noise to the singular values of the approximated singular matrix, thereby trading off between privacy and utility. Analytic proofs and results of the comparative experiments demonstrate that FinPrivacy can simultaneously enforce ɛ-differential privacy and maintain an efficient fingerprint recognition.

Fuzzy systems can aid in diminishing uncertainty and noise from biometric security applications by providing an intelligent layer to the existing physical systems to make them reliable. In the absence of such fuzzy systems, a little random perturbation in captured human biometrics could disrupt the whole security system, which may even decline the authentication requests of legitimate entities during the protocol execution. In the literature, few fuzzy logic-based biometric authentication schemes have been presented; however, they lack significant security features including perfect forward secrecy (PFS), untraceability, and resistance to known attacks. This article, therefore, proposes a novel two-factor biometric authentication protocol enabling efficient and secure combination of physically unclonable functions, a physical object analogous to human fingerprint, with user biometrics by employing fuzzy extractor-based procedures in the loop. This combination enables the participants in the protocol to achieve PFS. The security of the proposed scheme is tested using the well-known real-or-random model. The performance analysis signifies the fact that the proposed scheme not only offers PFS, untraceability, and anonymity to the participants, but is also resilient to known attacks using light-weight symmetric operations, which makes it an imperative advancement in the category of intelligent and reliable security solutions.

With the prevalence of Internet of Things (IoT)-based social media applications, the distance among people has been greatly shortened. As a result, recommender systems in IoT-based social media need to be developed oriented to groups of users rather than individual users. However, existing methods were highly dependent on explicit preference feedbacks, ignoring scenarios of implicit feedbacks. To remedy such gap, this paper proposes an implicit feedback-based group recommender system using probabilistic inference and non-cooperative game (GREPING) for IoT-based social media. Particularly, unknown process variables can be estimated from observable implicit feedbacks via Bayesian posterior probability inference. In addition, the globally optimal recommendation results can be calculated with the aid of non-cooperative game. Two groups of experiments are conducted to assess the GREPING from two aspects: efficiency and robustness. Experimental results show obvious promotion and considerable stability of the GREPING compared to baseline methods.

Fatigue driving is one of main causes of traffic accidents. To avoid such traffic accidents, divers' fatigue detection has been used in Intelligent Internet of Vehicles (IIoV). IIoV usually dynamically allocate computing resources according to drivers' fatigue degree to improve the real-time of fatigue detection model. However, the traditional fatigue detection model may have bias on certain groups, which would further cause unfair resource allocation. To solve the problem, this paper proposes an improved IIoV framework, named Fair-Intelligent Internet of Vehicles (FIIoV). Compared with IIoV, we improve two layers in FIIoV, i.e., the detection layer and the normalization layer. The detection layer uses Convolutional Neural Network (CNN) to detect drivers' fatigue degree, and then uses adversarial network to achieve fairness of detection models. The normalization layer achieves the distribution of different sensitive feature values from historical detection results generated in the detection layer, and then uses the distribution to normalize the output of the detection layer to improve the fairness and accuracy of fatigue detection models. Simulation results show that both accuracy and fairness of FIIoV is improved compared with the original IIoV.

Unmanned Aerial Vehicle (UAV) is an emerging technology that assists in various automated activities where human involvement is minimal. Though individual UAVs are extremely useful entities, their productivity can further be increased by deploying multi-UAVs. Pattern formation among multi-UAVs is one of the key functionalities in a swarm environment that is essential for several UAV missions namely military expedition, search and rescue operations, drone based delivery mechanisms etc. In this paper, to facilitate pattern formation among UAVs in an effective manner, a Time-Interleaved Pattern Formation (TIPF) Mechanism is proposed. The existing systems work for a fixed number of drones whose pattern switching mechanisms are preprogrammed. However, the TIPF mechanism enables switching patterns among dynamic number of drones (UAVs) on the fly by inducing a small delay between each UAV movement. The TIPF mechanism avoids collision, which occurs due to the simultaneous movement of UAVs. The proposed TIPF mechanism encompasses a Centralised Coordinate Calculation (CCC) algorithm to easily calculate the coordinates of UAVs in a given pattern. Further, this mechanism has also been simulated and tested in our proposed virtual IP based Software In The Loop (V-SITL) environment. This proposed V-SITL environment offers increased scalability on account of the entire UAV system being simulated in a single computer. The TIPF mechanism has been simulated for 8 drones in a dynamic manner for square and triangle patterns. The simulation results show that the pattern formation time avoids collision in a time interleaving rate of 52.63%.

As increasingly advanced data collection and computing abilities are equipped by devices at the network edge, accompanying the vigorous development of machine learning, edge devices become both the consumer and provider of data. Due to the timeliness of some learning demands and the necessity of learning results, learning resources such as data collection, transmission, and learning should be unified and converged to meet timely learning needs. In this paper, we propose a framework to implement a distributed Learning-as-a-Service function by edge-cloud collaboratively integrating resources required by a learning task. First, the architecture of RALaaS and underlying information interaction are proposed. We then formulate the learning-resource allocation problem and propose a deep reinforcement learning based solution to minimize the required learning resource and achieve better accuracy. More precisely, an A3C algorithm is presented to schedule tasks among smart connected communities and aggregate models. Finally, evaluation results show that our proposed framework can improve the accuracy by 10% compared with conventional algorithms and save about 50% edge resources when 30 nodes participate in the learning task.

Machine Learning (ML) plays very significant role in the Internet of Things (IoT) cybersecurity for malicious and intrusion traffic identification. In other words, ML algorithms are widely applied for IoT traffic identification in IoT risk management . However, due to inaccurate feature selection, ML techniques misclassify a number of malicious traffic in smart IoT network for secured smart applications. To address the problem, it is very important to select features set that carry enough information for accurate smart IoT anomaly and intrusion traffic identification. In this paper, we firstly applied bijective soft set for effective feature selection to select effective features, and then we proposed a novel CorrACC feature selection metric approach. Afterward, we designed and developed a new feature selection algorithm named Corracc based on CorrACC, which is based on wrapper technique to filter the features and select effective feature for a particular ML classifier by using ACC metric. For the evaluation our proposed approaches, we used four different ML classifiers on the BoT-IoT dataset. Experimental results obtained by our algorithms are promising and can achieve more than 95% accuracy.

The Internet of Vehicles has attracted a lot of attention in the automotive industry and academia recently. We are witnessing rapid advances in vehicular technologies that comprise many components, such as onboard units (OBUs) and sensors. These sensors generate a large amount of data, which can be used to inform and facilitate decision making (e.g., navigating through traffic and obstacles). One particular focus is for automotive manufacturers to enhance the communication capability of vehicles to extend their sensing range. However, the existing short-range wireless access, such as dedicated short-range communication (DSRC), and cellular communication, such as 4G, is not capable of supporting the high volume data generated by different fully connected vehicular settings. Millimeter-wave (mmWave) technology can potentially provide terabit data transfer rates among vehicles. Therefore, we present an in-depth survey of the existing research, published in the last decade, and we describe the applications of mmWave communications in vehicular communications. In particular, we focus on MAC and physical layers and discuss related issues, such as sensing-aware MAC protocol, handover algorithms, link blockage, and beamwidth size adaptation. Finally, we highlight various aspects related to smart transportation applications, and we discuss future research directions and limitations.

Edge computing provides a promising paradigm to support the implementation of Industrial Internet of Things (IIoT) by offloading computational-intensive tasks from resource-limited machine-type devices (MTDs) to powerful edge servers. However, the performance gain of edge computing may be severely compromised due to limited spectrum resources, capacity-constrained batteries, and context unawareness. In this article, we consider the optimization of channel selection that is critical for efficient and reliable task delivery. We aim at maximizing the long-term throughput subject to long-term constraints of energy budget and service reliability. We propose a learning-based channel selection framework with service reliability awareness, energy awareness, backlog awareness, and conflict awareness, by leveraging the combined power of machine learning, Lyapunov optimization, and matching theory. We provide rigorous theoretical analysis, and prove that the proposed framework can achieve guaranteed performance with a bounded deviation from the optimal performance with global state information (GSI) based on only local and causal information. Finally, simulations are conducted under both single-MTD and multi-MTD scenarios to verify the effectiveness and reliability of the proposed framework.

A massive increase in the number of mobile devices and data-hungry vehicular network applications creates a great challenge for mobile network operators (MNOs) to handle huge data in cellular infrastructure. However, due to fluctuating wireless channels and high mobility of vehicular users, it is even more challenging for MNOs to deal with vehicular users within a licensed cellular spectrum. Data offloading in the vehicular environment plays a significant role in offloading the vehicle's data traffic from congested cellular network's licensed spectrum to the free unlicensed WiFi spectrum with the help of roadside units (RSUs). In this article, an intelligent reward-based data offloading in the next generation vehicular networks (IR-DON) architecture is proposed for dynamic optimization of data traffic and selection of intelligent RSU. Within the IR-DON architecture, an intelligent access network discovery and selection function (I-ANDSF) module with Q-learning, a reinforcement learning algorithm is designed. The I-ANDSF is modeled under a software-defined network (SDN) controller to solve the dynamic optimization problem by performing an efficient offloading. This increases the overall system throughput by choosing an optimal and intelligent RSU in the network selection process. The simulation results have shown the accurate network traffic classification, optimal network selection, guaranteed quality of service, reduced delay, and higher throughput achieved by the I-ANDSF module.

Internet of Things and the related computing paradigms, such as cloud computing and fog computing, provide solutions for various applications and services with massive and high-dimensional data, while producing threats to the personal privacy. Differential privacy is a promising privacy-preserving definition for various applications and is enforced by injecting random noise into each query result such that the adversary with arbitrary background knowledge cannot infer sensitive input from the noisy results. Nevertheless, existing differentially private mechanisms have poor utility and high-computation complexity on high-dimensional data because the necessary noise in queries is proportional to the size of the data domain, which is exponential to the dimensionality. To address these issues, we develop a compressed sensing mechanism (CSM) that enforces differential privacy on the basis of the compressed sensing (CS) framework while providing accurate results to linear queries. We derive the utility guarantee of CSM theoretically. An extensive experimental evaluation on real-world data sets over multiple fields demonstrates that our proposed mechanism consistently outperforms several state-of-the-art mechanisms under differential privacy.

Millions of devices are becoming part of Internet of Things/5G. Securing these devices against all potential threats is a huge challenge. The 5G specification goals require rigid and robust security protocol against such threats. Quantum cryptography is a recently emerged term in which we test the robustness of security protocols against quantum computers. Therefore, in this article, we propose a security protocol called quantum key GRID for authentication and key agreement (QKG-AKA) scheme for the dynamic security association. This scheme is efficiently deployed in long term evolution architecture without any significant modifications in the underlying base system. The proposed QKG-AKA mechanism is analyzed for robustness and proven safe against quantum computers. The simulation results and performance analysis show drastic improvement regarding security and key management over existing schemes.

The Internet of Things (IoT) is growing day by day, and new IoT devices are introduced and interconnected. Due to this rapid growth, IoT faces several issues related to communication in the edge computing network. The critical issue in these networks is the effective edge computing IoT device selection whenever there are several edge nodes to carry information. To overcome this problem, in this paper, we proposed a new framework model named SoftSystem based on the soft set technique that recommends useful IIoT devices. Then, we proposed an algorithm named Softsystemalgo. For the proposed system, three different parameters are selected: IoT Device Security (IDSC), IoT Device Storage (IDST), and IoT Device Communication Speed (IDCS). We also find out the most significant parameters from the given set of parameters. It is evident that our proposed system is effective for the selection of edge computing devices in the IoT network.

We introduce a full duplex non-orthogonal multiple access (FD-NOMA)-based decentralized vehicle to everything (V2X) system model and focus on its capacity performance analysis. In order to solve the computation complicated problems of the involved exponential integral functions and infinite factorial expressions, we give approximate closed-form expressions with controllable arbitrary small errors. We find the accuracy of our approximate expressions is controlled by the division of $\frac{\pi}{2}$ in the urban and crowded (UC) scenario, and the truncation point $T$ in the suburban and remote (SR) scenario. Numerical results manifest 1) Increasing the number of V2X device, NOMA power and Rician factor value yields better capacity performance. 2) Effect of FD-NOMA is determined by the FD self-interference and the channel noise. 3) FD-NOMA has better latency performance compared to other schemes.

In order to meet the requirements of massively connected devices, different quality of services (QoS), various transmit rates, and ultra-reliable and low latency communications (URLLC) in vehicle-to-everything (V2X) communications, we introduce a full duplex non-orthogonal multiple access (FD-NOMA)-based decentralized V2X system model. We, then, classify the V2X communications into two scenarios and give their exact capacity expressions. To solve the computation complicated problems of the involved exponential integral functions, we give the approximate closed-form expressions with arbitrary small errors. Numerical results indicate the validness of our derivations. Our analysis has that the accuracy of our approximate expressions is controlled by the division of π/2 in the urban and crowded scenarios, and the truncation point T in the suburban and remote scenarios. Numerical results manifest that: 1) increasing the number of V2X device, NOMA power, and Rician factor value yields a better capacity performance; 2) effect of FD-NOMA is determined by the FD self-interference and the channel noise; and 3) FD-NOMA has a better latency performance compared with other schemes.

A Tactile Internet-based nanonetwork is an emerging field that promises a new range of e-health applications, in which human operators can efficiently operate and control devices at the nanoscale for remote-patient treatment. A haptic feedback is inevitable for establishing a link between the operator and unknown in-body environment. However, haptic communications over the terahertz band may incur significant path loss due to molecular absorption. In this paper, we propose an optimization framework for haptic communications over nanonetworks, in which in-body nanodevices transmit haptic information to an operator via the terahertz band. By considering the properties of the terahertz band, we employ Brownian motion to describe the mobility of the nanodevices and develop a time-variant terahertz channel model. Furthermore, based on the developed channel model, we construct a stochastic optimization problem for improving haptic communications under the constraints of system stability, energy consumption, and latency. To solve the formulated nonconvex stochastic problem, an improved time-varying particle swarm optimization algorithm is presented, which can deal with the constraints of the problem efficiently by reducing the convergence time significantly. The simulation results validate the theoretical analysis of the proposed system.

Multi-Access Edge Computing (MEC) is an emerging technology that leverages computing, storage and network resources deployed at the proximity of users to offload terminal from computational- and delay-sensitive tasks. Various existing facilities including mobile devices with idle resources, vehicles, and MEC servers deployed at base stations or road side units, could act as edges in the network. Since offloading tasks incurs extra transmission energy consumption and transmission latency, two key questions to be addressed in MEC deployments are: (i) offload the workload to the edge or compute it in terminals? (ii) which edge, among the available ones, should the task be offloaded to? Hence, we propose a matching theory based task assignment mechanism which takes into account the devices' and MEC servers' computation capabilities, wireless channel conditions, and delay constraints. The main goal of our task assignment mechanism is to reduce overall energy consumption, while satisfying task owners' heterogeneous delay requirements and supporting good scalability. Simulations are conducted to evaluate the efficiency of our proposed mechanism.

The cognitive network uses cognitive processes to record data transmission rate among nodes and applies self-learning methods to trace data load points for finding optimal transmission path in the distributed computing environment. Several industrial systems, e.g., data centers, smart grids, etc., have adopted this cognitive paradigm and retrieved the least HOP count paths for processing huge datasets with minimum resource consumption. Therefore, this technique works well in transmitting structured data such as `XML', however, if the data is in unstructured format i.e. `RDF', the transmission technique wraps it with the same layout of payload and eventually returns inaccuracy in calculating traces of data load points due to the abnormal payload layout. In this paper, we propose a knowledge-based optimal routing path analyzer (RORP) that resolves the transmission wrapping issue of the payload by introducing a novel RDF-aware payload-layout. The proposed analyzer uses the enhanced payload layout to transmit unstructured RDF triples with an append pheromone (footsteps) value through cognitive nodes towards the semantic reservoir. The grid performs analytics and returns least HOP count path for processing huge RDF datasets in the cognitive network. The simulation results show that the proposed approach effectively returns the least HOP count path, enhances network performance by minimizing the resource consumption at each of the cognitive nodes and reduces traffic congestion through knowledge-based HOP count analytics technique in the cognitive environment of the smart grid.

Growing popularity of multimedia applications, pervasive connectivity, higher bandwidth, and euphoric technology penetration among bulk of the human race that happens to be cellular technology users, has fueled the adaptation to long-term evolution (LTE)/system architecture evolution. The LTE fulfills the resource demands of the next generation applications for now. We identify security issues in authentication mechanism used in LTE that without countermeasures might give super user rights to unauthorized users. The LTE uses static LTE key to derive the entire key hierarchy, i.e., LTE follows Evolved Packet System-Authentication and Key Agreement based authentication, which discloses user identity, location, and other personally identifiable information. To counter this, we propose a public key cryptosystem named “International mobile subscriber identity Protected Console Grid based Authentication and Key Agreement (IPG-AKA) protocol” to address the vulnerabilities related to weak key management. From the data obtained from threat modeling and simulation results, we claim that the IPG-AKA scheme not only improves security of authentication procedures, but also shows improvements in authentication loads and reduction in key generation time. The empirical results and qualitative analysis presented in this paper prove that IPG-AKA improves security in authentication procedure and performance in the LTE.