The evolution of Artificial Intelligence (AI) has reached a critical point, where agentic AI systems demonstrate strong capabilities in goal formulation and planning but remain difficult to deploy in real-world settings due to their limited grounding in physical environments. These limitations arise from the challenges of partial observability, actuation uncertainty, and strict resource constraints that characterize the physical world. This survey argues that the Artificial Intelligence of Things (AIoT) provides the necessary foundation to embed agentic intelligence into such environments by enabling continuous interaction between sensing, reasoning, and action. We analyze the synergy between goal-driven agentic AI and distributed AIoT infrastructures and present a unified taxonomy of AIoT-enabled agentic architectures, highlighting trade-offs across centralized, edge-native, and hybrid deployment models. The survey further examines key enabling technologies, including edge intelligence, semantic communication, digital twins, and trust mechanisms, and discusses how they integrate into cognitive control loops. Through representative applications in smart cities, industrial automation, healthcare, and energy systems, we show how this convergence moves automation beyond rule-based behavior toward context-aware autonomy. Finally, we identify open challenges related to long-horizon safety, resource-aware intelligence, and ethical governance, and outline research directions toward robust, trustworthy, and socially embedded autonomous systems.

The proliferation of IoT devices has limited the efficiency of heterogeneous data communication in distributed environments and increased security risks. Balancing scalability, efficiency and data privacy in IoT transaction systems becomes critical, and intent-based networks enable optimal configuration with minimal intervention. To optimize the network management environment, we propose a three-stage execution scheme for blockchain cross-shard transactions, which combined with a timeout rollback mechanism ensures atomicity and reduces latency. In addition, we design a fragment-based consensus protocol utilizing a verifiable random function, which improves the consensus efficiency through the randomness of committee member selection. In order to enhance system security, we introduce a reputation evaluation mechanism and a malicious node detection method based on normalized entropy. The mechanism dynamically adjusts the reputation value of a node according to its performance in the consensus process, so that high-reputation nodes can play a greater role in the consensus and detect malicious nodes in the network accordingly. By embedding this mechanism into a network management framework based on users’ intention, it can accurately realize users’ expectations for network performance optimization, security enhancement and efficient operation. Experiments show that our scheme not only improves communication efficiency, but also enhances the security of sharded transactions, effectively matching users’ high-level intentions for network scalability, efficiency, and data privacy.

Eddy current testing (ECT) is a widely adopted electromagnetic non-destructive testing (NDT) technique for detecting defects in conductive materials. In practical deployments, however, ECT systems often suffer from low signal-to-noise ratio, strong sensitivity to lift-off and environmental variations, and complex multi-parameter coupling, which makes robust signal interpretation challenging. Meanwhile, the growing demand for portable and always-on inspection pushes data processing toward resource-constrained embedded hardware. Tiny machine learning (TinyML) provides a promising pathway for enabling on-device intelligence by deploying compact models with low latency and low power consumption. This review summarizes recent progress in integrating TinyML into ECT, covering the ECT signal characteristics and key technical bottlenecks, the TinyML workflow and optimization techniques for embedded deployment, and representative application scenarios including pipeline inspection, corrosion detection, and thickness evaluation. We further analyze the main barriers to adoption, such as limited computing power and memory, data scarcity, calibration overhead, and generalization across materials, probes, and defect types, and we outline future research directions including physics-guided learning, federated learning, and standardized benchmarks for ECT-oriented TinyML evaluation.

Intelligent fault diagnosis of rotating machinery is essential for predictive maintenance, yet conventional deep learning models suffer from limited generalization under noisy and cross-domain conditions. Furthermore, their lack of interpretability restricts industrial trust and deployment. To address these challenges, we propose Conformer-PhyFaultNet, a novel physics-informed spectral attention Conformer that seamlessly integrates domain knowledge with advanced sequence modeling. The method embeds characteristic fault frequencies (BPFO, BPFI, FTF) directly into the spectral attention layer, guiding the network toward physically meaningful patterns rather than spurious features. A set of physics-guided tokens is introduced into the Conformer encoder, which persist across layers and acts as stable descriptors of defect signatures. The hybrid spectral attention + physics tokens mechanism enables the model to simultaneously capture local fault harmonics and long-range dependencies across time–frequency representations. Unlike conventional CNN or Transformers, proposed approach ensures interpretability by aligning attention distributions with analytic harmonics and providing layer-wise token activations as diagnostic evidence. This dual mechanism represents the key novelty, bridging analytic fault modeling with modern deep architectures for the first time in a unified framework. Extensive experiments on CWRU, Paderborn, and HUST datasets demonstrate the superiority of the proposed method: in-domain accuracy reaches 93.75, cross-domain transfer achieves 86.75 (CWRU→Paderborn) and 84.3% (HUST→CWRU), while noise robustness remains above 87% at 10 dB and 81% at 0 dB, outperforming CNN, RNN, Transformer and physics-informed baselines by significant margins. The proposed Conformer-PhyFaultNet therefore offers a technically rigorous, interpretable and noise-robust solution that can substantially enhance the reliability and adoption of intelligent predictive maintenance in industrial environments, while also enabling real-time monitoring and edge deployment in industrial IoT systems through low-latency inference (< 5 ms per segment).

The emergence of social media in the COVID-19 has contributed to the proliferation of explicit materials, which are frequently used by cybercriminals. To overcome this, the federated fusion W-Net (Gabor + PL) model, an intelligence of social things (IoST) enabled cooperative learning model is proposed that can be used to solve the problem of segmentation and moderation of obscene images. It is a hybrid of Gabor filtering to extract texture and power-law transformation to enhance contrast that will extract both a textural and intensity-based feature. Data augmentation methods such as region-of-interest filtering and unsharp masking enhance the clarity of edges and segmentation accuracy. We maximize the image quality using sigman ($\bm{\sigma} = \mathbf{5,10,15}$), and mask weights(k = 1, 4.5). The model exhibits a high level of performance, with a precision, recall, and IoU of 98.85% precision, 97.73% recall, 98.85% IoU, and a Dice Score of 97.70%. It identifies obscene areas with minimal instances of false-positive and false-negative. The reliability of the result is attested by a large Matthews correlation coefficient and the 0.038 s processing time makes it usable in real time. These findings highlight its ability to do low-latency privacy-preserving obscene content detection in socially connected IoT settings. This method exemplifies the strength of IoST-enabled federated intelligence, as it allows cooperation among social devices without centralizing user data, thereby maintaining user privacy while enabling behavioral and cultural analysis.

The heavy use of social media platforms is generating a high volume of affective data over the internet. This data is being used by researchers in various domains for prediction, qualitative, and quantitative analytical problems such as stock market prediction, opinion mining of online reviews on products, events, and many more. This article leverages X data for the political response analysis of users towards the 2019 Indian General election. In this article, a methodology is proposed that analyses X data to know what topics were mostly discussed during the election time under the #LoksabhaElection2019 hashtag. Also, we have tried to find out the sentiments of people towards different political terms (words) in the topics inferred. For this task, the study has used topic modeling and sentiment analysis of Tweets. This research may be useful for political parties or newsgroups to mine main topics and analyze the sentiments of people towards different entities.

Nowadays, object saliency detection has attracted considerable attention due to the vivid description of images. The traditional saliency detection methods are faced with the challenges of sparse boundary, fractured contour and internal non-uniform density. That will result in losing texture and detailed information of images, which makes a bad contribution to the subsequent object detection. Therefore, we propose a new approach based on fuzzy region competition and a Gaussian mixture segment model via a modified line segment detector (FGM-MLSD) for airport saliency detection in remote sensing images. First, we adopt fuzzy region competition, combining a Gaussian mixture model to segment the input images and obtain the airport candidate regions. After segmentation, a modified line segment detector (LSD) is used for extracting line features, which enhances the connection between broken lines and greatly improves the detected line quality. Then we can acquire the saliency map of the airport region. At last, we fuse the above saliency maps with the binarization map obtained by the Otsu method, aiming to eliminate the false alarm. Finally, abundant experiments are conducted, and the testing results reveal that the neoteric method can clearly and accurately extract the airport region in the remote sensing images and effectively improve the accuracy of saliency detection.

Efficient Medium Access Control (MAC) protocols are crucial for time-sensitive transmissions of safety and non-safety messages. The IEEE 802.11p standard requires enhancements for varying channel conditions, including error-prone environments. This paper proposes HVMAC, a hybrid VANET MAC protocol that enhances Quality of Service (QoS) for time-sensitive data traffic applications. It categorizes service channels into contention and scheduled channels. The HVMAC protocol is modeled with Markov chains and evaluated against IEEE 802.11p on offered load, average delay, throughput, reliability, and energy consumption (upto 90%). To improve HVMAC security during safety messages (SM) and service advertisement messages (SAM) transmission, a Post-Quantum Weighted Anonymous Authentication (PQWAA) is proposed. The weighted certificate authority (WCA) assigns priority weights to vehicles, for effective traffic management and resource distribution. PQWAA ensures secure authentication and message integrity using quantum-resistant cryptography and pseudonym-based key derivation. Integrating PQWAA with HVMAC ensures energy efficiency and secure communication for both safety and non-safety applications, offering a comprehensive solution for modern VANET environments. The proposed protocol is analyzed with existing techniques based on the packet delivery ratio, throughput, and average packet delay, values of 99%, (45-50)Mbps, and 50 ms. Also, the HVMAC protocol shows 81.23% lower channel collision than TDMA-MAC.

Deep reinforcement learning (DRL) has shown significant potential in adaptive traffic signal control (ATSC) by adapting to real-time traffic conditions. However, controlling multiple intersections faces challenges, mainly due to the isolated actions of agents and non-stationary caused by other intersections. To address these issues, this paper proposes a novel knowledge collaboration-based actor-critic policy gradient (KCACPG) method to achieve cooperative traffic scheduling across multiple intersections. KCACPG includes a knowledge collaboration learning mechanism that allows heterogeneous agents to exchange knowledge across experience tuples, achieving globally optimal decision-making and coordination. KCACPG also integrates an off-policy prioritized experience replay mechanism to improve knowledge reuse efficiency and reduce the negative impact of knowledge transfer. Simulation results show that KCACPG converges quickly, generalizes to fluctuant traffic and load well, improves the network throughput by up to 17.8%, and reduces the pressure imbalance by up to 11.6% compared with the existing collaborative methods. The proposed method has significant implications for intelligent transportation systems and smart cities.

The meteorological communication networks provide critical data support for agriculture and environmental monitoring. However, covert gradient-based attacks persistently inject subtle perturbations, threatening data integrity and increasing the operational overhead for network operators. To achieve proactive service assurance and security-aware network management, this paper proposes a data integrity monitoring mechanism as a managed network function, named EK-IGNN. Unlike traditional passive detection, EK-IGNN functions as an active security service. It first employs the Empirical Mode Decomposition Kalman Filter (EMD-KF) to extract high-fidelity attack fingerprints, which are then analyzed by an Intrinsic Graph Neural Network (IGNN). The IGNN model captures complex dependencies and adaptively amplifies weak attack features, enabling closed-loop network security management. Experimental results demonstrate that the proposed algorithm achieving an average improvement of 16.07% in accuracy and 15.27% in F1-score over state-of-the-art benchmarks.

Fraud detection in Internet-of-Things (IoT) applications remains a pressing challenge. Adversaries exploit injection, eavesdropping, and man-in-the-middle attacks that often evade conventional detection pipelines. Existing blockchain and Machine Learning (ML) based solutions improve accuracy but lack verifiability, auditability, and resilience against quantum-era threats. We proposeQuanFraud, a protocol that integrates Greenberger–Horne–Zeilinger (GHZ)–$\theta$quantum state verification, Decentralized Identifiers (DID), and a Quantum Support Vector Classifier (QSVC) within an auditable blockchain framework. The scheme ensures that fraud detection outcomes are not only data-driven but also cryptographically verifiable and resistant to identity-correlation and replay attacks. We evaluateQuanFraudon a financial dataset of 20,000 records (117 features), using Principal Component Analysis (PCA) and the Synthetic Minority Oversampling Technique (SMOTE) under 10- fold cross-validation. Results show that classical baselines such as Random Forest and XGBoost achieve balanced accuracy above 77%, while QSVC alone yields 42.1$\pm$2.8%. This gap indicates that the contribution ofQuanFraudis not accuracy leadership but a verifiable, auditable fraud-detection protocol under Noisy Intermediate-Scale Quantum (NISQ) constraints, where QSVC provides kernel-level privacy, quantum state verification, and on-chain checks that classical models do not offer. We further discuss complexity and scalability, highlighting the scheme's suitability for deployment in resource-constrained IoT environments.

In the era of smart cities, securing sensitive data transmitted through Internet of Things (IoT) devices has become a critical challenge. This paper presents a novel Fuzzy-Tuned Intelligent Edge-based Image Steganography framework designed to enhance IoT communication security. The proposed method employs a weighted fuzzy logic system to detect meaningful edge regions in a cover image, guided by gradient magnitude and local entropy to assign edge strength, enabling the selection of fine, imperceptible edge pixels in a 4-MSB image. To ensure optimal embedding locations, a Particle Swarm Optimization (PSO) algorithm is applied to intelligently select high-entropy edge pixels, maximizing both imperceptibility and embedding capacity. The secret data is then embedded within these optimized edge regions, preserving visual fidelity while ensuring robust concealment. Comprehensive testing was carried out on widely used benchmark datasets, with evaluation based on indicators like visual analysis of cover-stego image and their corresponding histogram plots. In addition, Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM), and entropy are evaluated for further analysis. The findings reveal that the introduced approach provides enhanced data protection, robustness, and image quality when compared with conventional edge-detection and random embedding techniques. This model proves highly effective for secure information exchange in low-resource IoT systems integrated into smart city networks.

The increasing growth of digital images has become significant in the areas of healthcare, real-time governance, and social media activities to validate identity to offer services without any inconvenience. However, the rapid advancement of artificial intelligence and security-related concepts has led to an increase in real-time security attacks, such as deepfakes on digital images. Advanced technologies have been used by attackers to exploit sensitive data, necessitating the proposal of novel approaches to counter them. Numerous studies have evaluated tamper detection using watermarking techniques such as LSB, DCT, DWT, correlation-based methods, and hybrid approaches. The drawbacks of these existing techniques include low embedding density, memory inefficiency, and insufficient integrity checks, which impact tamper detection efficiency. To address these limitations, a novel watermarking technique is proposed that uses a Multi-task Cascaded Convolutional Neural Network (MTCNN) and a Penultimate Least Significant Bit (PLSB) approach to secure digital human images against unlawful activities such as deep fakes and tampering. The proposed framework outperforms existing methodologies in key performance metrics, including SVD-DWT, DCT, DNN, PB-DMFB, and PCA-DCT, achieving a 2 % increase in SSIM, a 12 % enhancement in PSNR, and a 4 % reduction in MSE, indicating superior quality of the watermarked image and enhanced resistance to manipulation and tampering.

The combination of artificial intelligence and Internet of Things (AIoT) technologies is changing precision agriculture by making it possible to automatically check the health of crops. Early detection of leaf diseases is still important for stopping yield losses, but regular convolutional neural networks (CNNs) often don't work as well when they have to deal with different textures, lighting changes, and noise on the field level. To address these constraints, this study presents HRL-ViT, a Human–Robot Collaborative Learning framework that utilizes Vision Transformers for leaf disease identification. The frame-work merges the global attention feature of Vision Transformers with a human-in-the-loop approach, wherein predictions with low confidence are validated by experts and used to improve the model over time. The system is also made for edge-based AIoT deployment, which lets you analyze data in real time in agricultural settings. Experimental research utilizing both benchmark datasets and field-acquired images demonstrates that HRL-ViT consistently surpasses baseline CNN and Transformer models, attaining superior accuracy, precision, and recall while minimizing false detections. Transformers' attention maps can be visualized to make them even easier to understand, which helps users trust them and make decisions. In general, HRL-ViT shows a lot of promise for use in autonomous robotic platforms. It offers an explainable and scalable way to find diseases in precision agriculture.

Artificial Intelligence of Things (AIoT) systems are increasingly deployed in smart cities to enable automation, resource optimization, and real-time decision-making. How-ever, large-scale deployments face significant challenges, in-cluding device-level resource limitations, communication over-head, synchronization inefficiencies, and security threats such as data and model poisoning. To address these issues, a digi-tal twin-assisted collaborative learning framework is proposed. Resource-constrained devices are virtualized at home edge servers to offload computationally intensive training, while Multi- access Edge Computing (MEC) nodes equipped with Zero-Touch Networking (ZTN) autonomously orchestrate training policies. Snake learning is adopted to reduce synchronization delays and communication costs compared with federated and split learning, and Harris Hawks Optimization is applied to select participants based on trust, resources, and latency. Robustness against ad-versarial updates is ensured through a trust-weighted Adaptive Multi-Krum aggregation mechanism, while a permissioned blockchain provides tamper-proof auditability and accountability. Experimental results on a smart home intrusion detection dataset demonstrate a 50-65% reduction in communication, 30-45% reduction in computation and energy consumption, and Fl- scores above 95 % even under 40 % adversarial participation.

Emerging sixth-generation (6G) edge networks demand intelligent, scalable, and privacy-preserving learning systems that support real-time decision-making and natural language-driven control. In addition to training, these systems must also support federated unlearning (FU), the ability to selectively remove user data without full model retraining. However, existing federated learning (FL) and FU frameworks lack adaptability, require manual hyperparameter tuning, and are ill-suited for dynamic, resource-constrained environments. To address these challenges, we propose SLM-FARL, a hierarchical multi-agent deep reinforcement learning (MARL) framework that integrates small language models (SLMs) with FL and FU processes for autonomous, privacy-compliant learning aligned with user-level data removal demands. We implement a customized MAPPO algorithm to enable stable and adaptive policy updates across distributed SLM agents, orchestrated by a central LLM controller that supports human-in-the-loop interaction. To ensure real-time responsiveness and deployment efficiency, we incorporate SLM optimization techniques such as quantization and knowledge distillation, reducing model size and latency while maintaining performance. The proposed framework is evaluated on the UCI Adult dataset using 120 clients and demonstrates up to 15.78% higher FL-FU accuracy compared to baseline methods. The MAPPO Loss decreased by 90.12% indicates highly effective MARL convergence and Policy Entropy drop by 84.31% shows it confident policy decisions. The KD demonstrated an overall 17.56% improved performance over other model compression techniques. Thus, these metrics affirms the robustness and adapt-ability of our proposed SLM-FARL framework.

Two nascent technologies, rate-splitting multiple access (RSMA) and reconfigurable intelligent surfaces (RIS), present promising avenues to enhance spectral and energy efficiencies within multi-antenna frameworks. However, passive RIS may encounter challenges in delivering substantial capacity gains due to the cumulative path loss effect. Active RIS (ARIS) equipped with low-cost amplifiers in the reflective elements emerges as a solution to mitigate the limitation. This paper investigates a multi-user multiple-input single-output (MISO) simultaneous wireless information and power transfer (SWIPT) framework, augmented by an ARIS and leveraging RSMA. The primary objective is to maximize the system's SE, subject to constraints imposed by the design of BS beamforming vectors, PS ratios, and RIS phase shifts. To address the inherent nonconvexity of this optimization problem, we propose an innovative approach that combines alternating optimization (AO) and semidefinite relaxation (SDR) algorithms. Simulations results demonstrate the significant advantages of our proposed design over established benchmarks.

Underwater communication systems are vital for applications such as environmental monitoring, military surveillance, and offshore exploration. However, existing authentication protocols for underwater networks are often inefficient, vulnerable to replay and impersonation attacks, and lack resilience to node failures, a gap not fully addressed by current standards. The proposed study presents the design and implementation of a novel authentication protocol tailored for underwater communication systems. The approach leverages pentatope elliptic curve cryptography for efficient key generation and secure data exchange, ensuring robust protection against common cyber threats. Formal security analysis using BAN logic and the Scyther tool verifies resistance to replay, impersonation, and eavesdropping attacks, with no successful attacks detected in over 60 test cases. The resulting design demonstrates significant improvements in computational efficiency and resilience to adversarial attacks, ensuring scalable and reliable underwater communications. Thus, it represents a critical advancement in securing underwater networks, paving the way for practical deployment in mission-critical applications. The proposed protocol reduces total communication overhead to 2,112 bits (a 30–34% reduction) and lowers computational cost to 0.4 ms per entity, significantly improving efficiency compared to existing schemes. Furthermore, the protocol incorporates fallback authentication peers to ensure resilience under partial node outages.

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 use of SCADA and AMI systems in smart grid-based Industrial Internet-of-Things (SG-IIoT) networks for proper energy supply are noteworthy. Inaccurate energy load forecasts, cyber-threats, and energy load-based sustainability issues in smart grids hinder SG-IIoT operations. To mitigate these challenges, a federated-learning approach is developed by integrating LSTM (Long-Short-Term-Memory), Transformer-LLM (Larger Language Model) based Foundation-Model, and AES (Advanced-Encryption-Standard) cryptography. The proposed approach is named Responsible-Federated-Foundation-Model (ResFedFM). To ensure secure federated learning computation as well as data security at the edge (smart meter), fog (SCADA-based substation grid) and cloud (grid cloud server) layers of the SG-IIoT, a self-parent keys-based cryptography method has been developed by combining AES with HMAC (Hash-based-Message-Authentication-Code). A load forecasting algorithm called LSTM-LLM-GenResAI-Forecasting has been developed for computation at each end node of the federated learning process. The edge node forecast outputs are encrypted and aggregated at the fog node. At the fog node, the data are decrypted, and aggregation algorithm of federated-learning process are used to generate overall load forecasting of each sub-station grid. Again, the forecast data from these fog nodes are aggregated in an encrypted state at the cloud level and overall load forecasts are generated for multiple fog nodes. The result of proposed approach provides responsible forecasting (High accuracy, green computing-based energy demand, optimization of AI-hallucination, and grid data security), demonstrating enhanced performance over seven significant models.

Carbon Intelligent Industrial Internet of Things (IIoT) systems are critical for achieving sustainable industrial automation but face challenges such as scalability, operational complexity, and security vulnerabilities. Zero-Touch Networks (ZTN), with their autonomous management capabilities, offer solutions to operational challenges but remain vulnerable to sophisticated cyber intrusions due to their high level of autonomy and interconnectedness. While Artificial Intelligence (AI), especially Deep Learning (DL), shows potential in intrusion detection, current approaches often encounter obstacles such as insufficient datasets, challenges in automated data preprocessing, and a lack of transparency. This paper introduces an AutoML-enabled Meta Learning-based Intrusion Prevention Scheme designed specifically for ZTN within Carbon Intelligent IIoT. The proposed framework integrates AutoML and meta-learning to streamline data preprocessing and improve model adaptability in dynamic and evolving threat environments. To ensure transparency, an Integrated Gradient-based Explainable AI (XAI) mechanism is employed, offering insights into the impact of individual features on model predictions, thereby addressing concerns related to trust and accountability in industrial applications. Experimental evaluations demonstrate the framework’s effectiveness in enhancing intrusion prevention, bolstering security, and improving transparency for ZTN in carbon intelligent IIoT, providing a comprehensive solution to prevailing challenges.

As a key economic crop, jujube’s external morphology directly affects quality grading and market value. However, traditional inspection methods relying on manual sampling or 2D image analysis suffer from inefficiency and limited feature characterization, particularly in quantifying complex geometric traits such as irregular wrinkles and localized depressions on jujube surfaces. Existing 3D reconstruction techniques have been applied in agricultural product inspection but face challenges in widespread adoption due to high costs and low resolution. This study proposes a single-view high-resolution RGB 3D reconstruction method for jujube based on generative artificial intelligence. Specifically, we designed a two-stage single-view 3D reconstruction framework and modified the cross-attention layers in the U-shaped network architecture of a stable video diffusion mode to meet the requirements of high-resolution and clear texture reconstruction for jujube. Additionally, we improved training and inference efficiency through parallel computing and achieved automation integration with Unmanned Agents. The proposed method successfully reconstructed 3D models from single-view 1,024 1,024 RGB images of jujube. Our model achieves a PSNR of 23.52 and an SSIM of 0.86 on the public dataset.This approach provides a low-cost, high-precision 3D digital solution for non-destructive phenotyping of jujube, offering practical value for advancing intelligent sorting and quality evaluation in agricultural production.

With the deepening integration of the Internet of Things (IoT) and Artificial Intelligence (AI), intelligent warehousing systems are increasingly confronted with the challenges of achieving high-precision navigation and task scheduling in dynamic environments. Although existing research has made notable strides in simultaneous localization and mapping (SLAM) and task scheduling, persistent issues–such as point cloud noise interference in dynamic scenes, inefficiencies in computational resource allocation, and insufficient multi-sensor collaboration–continue to constrain system performance. To address these challenges, this study proposes an AI-driven task scheduling SLAM framework named KORS designed to enhance navigational robustness and scheduling efficiency in dynamic warehousing environments. This study proposes the KCPoint model to achieve precise segmentation and elimination of dynamic point clouds. Building upon the PointNet++ architecture, KCPoint integrates K-Nearest Neighbors Enhanced Farthest Point Sampling (KFPS) and a Convolutional Block Attention Module (CBAM) to enhance feature extraction. In addition, a task scheduling mechanism is introduced to address the dynamic allocation of computational resources within vehicular networks. Relative to FAST-LIO2, the KORS system reduces absolute pose error (APE) by 31.32% and improves computational efficiency by 17.88% on the NCD and NCLT datasets. Furthermore, compared to conventional methods based on particle swarm optimization and genetic algorithms, the task scheduling algorithm achieves comparable decision-making benefits while reducing single-decision latency by over 42

The advent of 6G-enabled Internet of Everything(IoE) technologies is set to revolutionize urban infrastructures by providing fast, consistent, and low-delay capabilities for communication. 6G connectivity will integrate traffic and power grids for adaptive urban management. However, current traffic networks and power grids face critical challenges such as fragmented data processing, delayed responses, and outdated resource management leading to inefficiencies like traffic congestion and power outages. In 6G-enabled smart grid cities, system complexity and interdependence demand dynamic, real-time solutions, further exacerbating inefficiencies. To address these issues, this study introduces Digital Twin-enabled Real-time Optimization System (DT-ROS), a dynamic framework designed to optimize urban traffic and power grid systems. DT-ROS integrates a dual-tier Digital Twin (DT) and an advanced scheduling framework based on Priority Age of Information Deep Q Scheduler (PAoI-QS). The dual-tier framework builds an elementary and Integrated Digital Twin (IDT) with Auto-Regressive Integrated Moving Average (ARIMA)-based forecasting for accurate real-time traffic and energy demand predictions. The advanced scheduling framework minimizes the Age of Information (AoI), ensuring decision-making relies on the most current and relevant data. By continuously monitoring and processing real-time data, DT-ROS creates virtual models to simulate system behavior and dynamically allocate resources. Simulation results demonstrate the effectiveness of DT-ROS, achieving a 30% reduction in traffic congestion and a 25% improvement in power grid stability compared to existing methods. To create effective, robust, and sustainable urban systems for future smart cities, DT-ROS addresses traffic and electricity problems.

Underwater communication systems face challenges, including limited bandwidth, high latency, and void areas. This article introduces synergy optimization routing protocol (SORP) for Internet of Underwater (IoU) sensor networks, emphasizing link scheduling to address localization, energy consumption, latency, network longevity, and void regions. Leveraging belief-desire-intention (BDI) and fuzzy logic, SORP offers adaptive responses to varying network conditions. Theoretical modeling using NetLogo enhances the understanding of SORP’s behavior. In evaluation, SORP consistently outperforms others. Demonstrating superior energy efficiency (3.0–3.9) compared to PPWURC, state prediction-based data collection (SPDC), balanced routing protocol based on machine learning (BRP-ML) (40–120), and energy efficient clustering routing protocol based on arithmetic progression (5–6.5), SORP proves its efficacy. Latency analysis reveals SORP consistently displaying the lowest values (2.0–2.8), surpassing packet hierarchy and void processing, SPDC, and BRP-ML (8.3–30.0). With a perfect packet delivery ratio (PDR) of 98%, SORP showcases exceptional reliability. Network lifetime analysis positions SORP as a durable option, lasting from 3985 to 4010 rounds. Validation through an underwater communication system demonstrates speeds of 5 Mb/s and above. Simulation testing reveals a transmission speed of 80 bps with latency of less than 4 s and 98% PDR. Theoretical predictions indicate significant improvements in real-time transmission, reducing latency to less than 1 s with a speed of 5 Mb/s. This research presents an innovative and practical approach to address underwater communication challenges, highlighting the efficiency and reliability of SORP in routing protocols for underwater sensor networks. The combination of theoretical modeling and real-time testing offers a comprehensive understanding, emphasizing the potential real-world impact of SORP.

The rapid advancement of big data and artificial intelligence (AI) in healthcare heightens the urgency for accurate medical text sentiment analysis. The privacy protection of medical data has been a crucial concern due to its sensitivity. The Internet of Medical Things (IoMT) facilitates large-scale data collection at lower cost, enabling precision medicine. However, decentralized IoMT poses novel challenges to centralized standard encryption schemes. In this article, we propose a novel approach to building privacy-preserving sentiment models with a generative pretrained transformer (GPT). We first convert sensitive medical text data into noise-like and distributed one-hot images. Then, we introduce visual cryptography (VC) for lightweight and secure transmission of medical text across public networks in resource-limited IoMT devices. We adopt a cross-domain sentiment analysis framework that finetunes transformer-based language models for accurate sentiment analysis instead of training GPT in sentiment analysis from scratch. Experimental results show that the proposed approach improves the accuracy and effectiveness of sentiment analysis while maintaining privacy, thereby addressing a significant gap in biomedical text analysis.

This research proposes a solution integrating AIGC technology with optimized object detection networks to address challenges in brain tumor identification under the context of Medical Industry 5.0. First, to mitigate data scarcity, DCGAN is employed to augment the Br35H dataset by generating high-quality synthetic samples, enhancing model generalization. Second, a hierarchical feature-enhanced EfficientDet (EfficientDet-HFE) model is developed by combining FPN and EfficientDet architectures, fusing high-level semantic information with low-level spatial details to optimize feature transmission pathways. Additionally, the SimAM is introduced, integrated with a global-local feature optimization strategy to construct a recursive attention module. As BiFPN iterates progressively, the capacity for key region feature expression and the efficiency of multi-scale feature extraction are significantly enhanced. In response to the computational resource constraints of medical devices, LAMP techniques are applied to compress the network structure. With the assistance of fine-tuning strategies, the model parameters are reduced to 32.20 MB while preserving detection performance. Experimental results demonstrate that this method achieves 92.25% recall, 93.36% precision, 92.80% F1 Score, and 94.99% mAP on the augmented dataset, validating its efficacy in tumor detection. This research offers a lightweight, IoT-compatible solution for brain tumor detection, promoting the integration of AI-driven diagnostics into Healthcare Industry 5.0 ecosystems.

Maritime data security plays a crucial role in in Navy and Coastal Areas, where the detection of vessels is sensitive as well as boundless and demands privacy preservation and accurate identification. While manual identification of vessels can be challenging, advancements in Cryptographic hash functions, Deep Learning technology, and image processing have simplified the task. However, existing techniques like YOLOv3, with its struggles in handling unusual aspect ratios, YOLOv5’s low mean average precision, and R-CNN’s increased complexity and lack of privacy preservation, motivate the need for an improved approach. In lieu of this, we propose an Extended-YOLOv7 model as a more effective detection solution due to its favorable characteristics like CSPNet, Feature Fusion Module (FFM), Spatial Pyramid Pooling (SPP), and Non-Maximum Suppression (NMS). Additionally, utilization of the gradient descent algorithm aims to optimize system performance. To ensure privacy preservation, our work employs the widely recognized and secure hashing algorithm SHA-256, which is extensively used for data security. The proposed system facilitates detecting vessel traffic in designated areas such as ports and harbours as well as enables real-time vessel detection and tracking for enhanced security and safety purposes. In addition to safeguarding sensitive data, our research addresses compliance with privacy regulations, mitigates the risks of data breaches, and upholds ethical considerations. With the integration of these driving factors, this work strives to elevate the security analysis of detected maritime vessels, foster a sense of trust and assurance, and promote the use of ethical data management techniques. The proposed model provides better performance than other state-of-the-art methods. Specifically, this is accomplished by achieving a 9.3% increase in Precision over YOLOv7.

The interactive attention graph convolution network (IAGCN), a novel model proposed in this article, will revolutionize aspect-level sentiment analysis (SA). IAGCN effectively addresses these key features, in contrast to prior research that ignored the meaning of aspect terms and their relationship with context. The model combines a modified dynamic weighting layer with bidirectional long short-term memory (BiLSTM) to accurately acquire context. It takes use of graph convolutional networks (GCNs) to encrypt syntactic information from the syntactic dependency tree. Furthermore, a method for interactive attention is employed to discover the intricate relationships between context and aspect terms, which results in the reconstruction of those terms’ representations. Comparing the proposed IAGCN model to baseline models, impressive gains are made. Across five datasets, the model beats previous methods with an amazing improvement in F1 scores that ranges from 1.34% to 4.04% and an impressive improvement in accuracy that ranges from 0.56% to 1.75%. Additionally, the IAGCN model outperforms the global vectors (GloVe)-based strategy when the potent pretrained model bidirectional encoder representations from transformers (BERT) is included in the challenge, resulting in even greater improvements. The F1 score considerably increases from 2.59% to 7.55%, and accuracy increases from 1.47% to 3.95%, making the IAGCN model a standout performer in aspect-level SA.

Wireless sensor networks (WSNs) can be conceptualized as large-scale, dynamic social systems where nodes interact to achieve collective objectives. These networks generate extensive data through interactions, offering opportunities for large-scale knowledge discovery to optimize operations and enhance resilience. However, challenges such as limited resources and susceptibility to distributed denial-of-service (DDoS) attacks necessitate efficient and secure mechanisms for managing these “social” interactions. This article proposes a lightweight trusted framework that applies computational modeling principles to clustering in WSNs. The framework employs bi-directional long short-term memory (Bi-LSTM) networks for malicious node detection, mirroring the role of anomaly detection in social systems, and uses the walrus optimization algorithm (WOA) for optimized cluster head (CH) selection. By considering parameters such as residual energy, proximity to base stations, node density, and trust value, WOA ensures effective “role assignment” within the network, similar to optimizing functional roles in human social systems. The Bi-LSTM model analyzes node behavior to exclude malicious actors, fostering trusted, and efficient clustering. Evaluated in simulated DDoS attack scenarios, the framework significantly reduces the impact of attacks by isolating malicious nodes while improving network performance and resilience. Metrics such as stability period, throughput, network lifetime, energy efficiency, and attack mitigation are analyzed, demonstrating the framework’s effectiveness. This research bridges the domains of social system modeling and WSN operations, providing an energy-efficient and secure solution for managing large-scale dynamic networks.

Histopathological whole-slide images (WSIs) segmentation is essential for precise tissue characterization in medical diagnostics. However, traditional approaches require labor-intensive pixel-level annotations. To this end, we study weakly supervised semantic segmentation (WSSS) which uses patch-level classification labels, reducing annotation efforts significantly. However, the complexity of WSIs and the challenge of sparse classification labels hinder effective dense pixel predictions. Moreover, due to the multi-label nature of WSI, existing approaches of single-label contrastive learning designed for the representation of single-category, neglecting the presence of other relevant categories and thus fail to adapt to WSI tasks. This paper presents a novel multi-label contrastive learning method for WSSS by incorporating class-specific embedding extraction with LLM features guidance. Specifically, we propose to obtain class-specific embeddings by utilizing classifier weights, followed by a dot-product-based attention fusion method that leverages LLM features to enrich their semantics, facilitating contrastive learning between different classes from single image. Besides, we propose a Robust Learning approach that leverages multi-layer features to evaluate the uncertainty of pseudo-labels, thereby mitigating the impact of noisy pseudo-labels on the learning process of segmentation. Extensive experiments have been conducted on two histopathological image segmentation datasets, i.e. LUAD dataset and BCSS dataset, demonstrating the effectiveness of our methods with leading performance.

In the Internet of Medical Things (IoMT), de novo peptide sequencing prediction is one of the most important techniques for the fields of disease prediction, diagnosis, and treatment. Recently, deep-learning-based peptide sequencing prediction has been a new trend. However, most popular deep learning models for peptide sequencing prediction suffer from poor interpretability and poor ability to capture long-range dependencies. To solve these issues, we propose a model named SeqNovo, which has the encoding-decoding structure of sequence to sequence (Seq2Seq), the highly nonlinear properties of multilayer perceptron (MLP), and the ability of the attention mechanism to capture long-range dependencies. SeqNovo use MLP to improve the feature extraction and utilize the attention mechanism to discover key information. A series of experiments have been conducted to show that the SeqNovo is superior to the Seq2Seq benchmark model, DeepNovo. SeqNovo improves both the accuracy and interpretability of the predictions, which will be expected to support more related research.

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.

The rapid improvement in 6G-enabled Autonomous Transport Systems (ATS) has enhanced operational efficiency in terms of communication speed, data processing, and vehicle coordination. However, it presents a critical challenge in enabling vehicles to handle unforeseen, real-time adverse conditions. Despite these advancements, the challenge of adapting to unpredictable traffic scenarios and operational anomalies persists, and there is still room for improvement in managing these situations without compromising decision-making or resource management. We propose the Distributed Intelligence Framework (DIF), which leverages Federated Learning (FL) and Digital Twins (DTs) to enhance decision-making and network resilience. FL enables collaborative learning among vehicles while ensuring sensitive data remains localized, and DTs simulate adverse traffic scenarios in real time, allowing proactive adjustments to resource allocation and traffic management. The DIF framework enables vehicles to learn from the experiences of others, allowing them to handle unique or adverse conditions that individual vehicles may not have encountered before. This collaborative approach strengthens the system’s ability to adapt to new challenges while safeguarding data integrity and ensuring operational efficiency. Experimental results show that DIF achieves a 65% reduction in convergence error within just five epochs, demonstrating significant improvements in both network resilience and decision-making, making it a critical advancement for the future of 6G-enabled ATS networks.

Vehicular Ad Hoc Networks (VANETs) facilitate real-time information exchange through Vehicle-to-Vehicle (V2V) and Vehicle-to-Roadside (V2R) communications. While V2R communication plays a crucial role, it faces significant security challenges due to the transmission of sensitive data, leaving the system vulnerable to man-in-the-middle, replay, and impersonation attacks. Previous attempts to enhance security, such as dynamic anonymization and trusted key management, have introduced new challenges, including complex authentication processes, high resource demands, and inadequate privacy protection. To overcome these issues, we propose a lightweight and efficient authentication scheme that enhances vehicle privacy and security through a combination of signatures, pseudonyms, batch verification, and flexible certificate management. Our approach also employs Bloom filters to improve authentication efficiency, addressing the limitations of traditional certificate management systems that suffer from large lists and slow query times. The evaluation results demonstrate that the proposed scheme ensures comprehensive security by providing two-way authentication and guaranteeing anonymity. It effectively prevents replay attacks, DoS attacks, and other potential threats. Moreover, the scheme significantly reduces both communication and computational overhead, offering an efficient and secure solution for V2R communication in VANET.

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.

This paper investigates how to improve the energy efficiency of unmanned aerial vehicle (UAV)-enabled simultane-ous wireless information and power transfer (SWIPT) systems with multiple outdoor energy receivers (ERs) and multiple indoor wired-charging information receivers (IRs) by utilizing simul-taneously transmitting and reflecting reconfigurable intelligence (STAR-RIS), in which the UAV avoids flying over the indoor no-fly zone. Specifically, the total UAV energy consumption is minimized, while ensuring that the energy harvesting require-ment (EHR) of each ER and the communication throughput requirement (CTR) of each IR are met. To achieve this, the total UAV energy consumption is minimized by optimizing the STAR-RIS phase-shifts, the UAV trajectory, and hovering time using an iterative technique based on the fly-hover-broadcast (FHB) protocol. The technique allows the UAV to radiate energy-carrying information signals for the ERs and IRs at a limited number of hover positions. Simulation results demonstrate that the proposed design significantly outperforms other benchmark schemes, demonstrating its potential for improving the energy efficiency of UAV-enabled SWIPT systems while meeting the EHRs of each ER and the CTR of each IR.

ABSTRACT Optimizing crop production is essential for sustainable agriculture and food security. This study presents the AgriFusion Model, an advanced ensemble‐based machine learning framework designed to enhance precision agriculture by offering highly accurate and low‐carbon crop recommendations. By integrating Random Forest, Gradient Boosting, and LightGBM, the model combines their strengths to boost predictive accuracy, robustness, and energy efficiency. Trained on a comprehensive dataset of 2200 instances covering key parameters like nitrogen, phosphorus, potassium, temperature, humidity, pH, rainfall, and crop type, the model underwent rigorous preprocessing for data integrity. The RandomizedSearchCV method was employed to do hyperparameter tuning, namely improving the number of trees in the Random Forest algorithm and the learning rates in the Gradient Boosting algorithm. This ensemble approach achieves a remarkable accuracy rate of 99.48%, optimizes computer resources, lowers carbon footprint, and responds efficiently to a variety of agricultural situations. The model's performance is confirmed using metrics including cross‐validation, accuracy, precision, recall, and F1 score. This demonstrates how the model might improve agricultural decision‐making, make the most use of available resources, and promote ecologically responsible farming practices.

Internet of Things (IoT) devices like wearable devices have enabled quick monitoring of electrocardiogram (ECG) signals with lower resources than multielectrode ECG devices, opening up development opportunities for sustainable ECG-based emotion recognition. However, existing methods that rely on predesigned features extracted from single-lead ECG signals cannot automatically extract effective features from the original ECG signal collected by IoT devices. To address this limitation, we propose a novel approach leveraging signal transformation and graph representation learning for ECG-based emotion recognition. The signal graph learning process can be divided into local subgraph learning for ECG representation learning and signal enhancement graph to derive the graph-enhanced representation. We employ a designed loss function by calculating cosine similarity to extract an effective representation of the original signal from the transformed signal in the local subgraph learning. Additionally, we utilize a graph convolution model based on the signal enhancement graph to obtain a graph-enhanced representation of the ECG signal. The method incorporates six signal transformations and constructs a self-signal transformation graph. For emotion recognition, we design a classification network comprising convolutional neural networks (CNNs) and long short-term memory (LSTM) networks. Experiments on public data sets show the superiority of our method among other baselines. Ablation studies are conducted to verify the performance.

Internet of Things (IoT) in extreme environments inevitably produces incomplete multi-view data, presenting challenges to the existing data analysis methods. Although incomplete multi-view clustering methods have the potential to mine patterns of incomplete IoT data, they are still confronted with two challenges. 1) They ignore shifts of semantics caused by missing data in aggregating consistent and complementary information of incomplete data, degrading the robustness of models in pattern mining. 2) Most of them rely on the instances with complete views as pairwise supervision to capture correlations among views, failing to mine inherent patterns of data in the extreme view missing scenario where multi-view instances are only with an available view. To this end, a deep incomplete multi-view clustering network (DIMC) is proposed via defining dual consistencies within the information bottleneck framework to mine accurate patterns of incomplete data. Specifically, an unsupervised multi-view information bottleneck (MIB) is formulated to model dependencies of data, which remedies shifts of semantics via within-view intrinsic knowledge learning, consistent semantics sharing, and consistent structure aligning. Meanwhile, dual consistencies are designed to implement MIB, which builds invariant transformations to mine correlations between views without the help of complete instances. Finally, extensive experiments on four benchmark incomplete datasets demonstrate the superiority of DIMC. Especially, DIMC surpasses the state-of-the-art methods by 0.2048 in accuracy under extreme view missing scenarios.

With the rapid growth of the Internet of Things, sensors have become integral components of smart homes, enabling real-time monitoring and control of various aspects ranging from energy consumption to security. In this context, we cannot underestimate the importance of sensor-based data in ensuring the safety and well-being of occupants, particularly in scenarios involving early detection of fire outbreaks. We propose a novel federated learning (FL) Framework in this study to address the crucial issue of rapid fire smoke detection at the edge of smart home environments. The proposed framework employs three distinct FL algorithms, namely, federated averaging, federated adaptive moment estimation, and federated proximal, for global aggregation of machine learning predictions based on data from various IoT sensors. This framework allows for early prediction by utilizing the computational capabilities at the edge, thereby improving the responsiveness and efficiency of fire safety systems. Furthermore, to improve trust and transparency in the FL framework, explainable artificial intelligence techniques, such as local interpretable model-agnostic explanations (LIMEs) and Shapley additive explanations (SHAP), are integrated. We unveil pivotal features driving predictive outcomes through LIME and SHAP analyses, offering users valuable insights into model decision-making processes.

With the rapid increase of data from unmanned aerial vehicles (UAVs), the security and privacy of data presents a severe challenge for UAV-based applications. Moreover, UAVs with constrained resources cannot be equipped with strong but complicated cryptographic primitives for authentication protocol design. Although some attempts have been made to deal with security and privacy issues for UAVs, most of the existing studies have been found numerous security vulnerabilities or own extreme communication/computation overheads. This article offers a lightweight and practical mutual authentication protocol solely comprised of bitwise XOR operations and one-way hash functions. Moreover, blockchain technology is utilized to alleviate the centralized trusted party (TA) issue. Then, security of our proposed authentication protocol is proved by widely adopted formal security proof—Real-or-Random model and informal security proof. The experimental results prove that the proposed protocol can achieve better security requirements (e.g., decentralized TA, replay attack defense, and session key security) with less communication cost (i.e., reduced by around 58.7% at most) and computation cost (i.e., reduced by around 98.9% at most) than related UAV authentication schemes.

In recent years, driven by the continuous development of mobile Internet technology and artificial intelligence technology, the improvement of the manufacturing level of 6G Internet-of-Everything (IoE) products and the increase in residents’ income level, the 6G IoE industry has shown a sustained and stable development trend. However, 6G IoE has great security risks. Network anomaly detection is very important for 6G IoE. The anomaly detection method based on traditional deep auto-encoder uses the reconstruction error to determine whether the sample to be measured is normal data or abnormal data. However, the reconstruction errors generated by the above method on normal data and abnormal data are very close, which leads to some abnormal data being easily misclassified as normal data. Therefore, an anomaly detection method based on deep auto-encoder and capsule graph convolution via sparrow search algorithm in 6G IoE is proposed. Firstly, the capsule graph network uses the bottleneck feature of the input sample to generate the bottleneck feature of the pseudo-abnormal data, so as to increase the abnormal data information in the training set. The capsule dynamic fusion strategy aggregates different factors to obtain new item embedding. Secondly, deep auto-encoder reconstructs the bottleneck characteristics with abnormal data information into normal data as much as possible, and increases the difference of reconstruction error between abnormal data and normal data. In the process of network classification, we use the sparrow search algorithm to find the optimal value of the function. And at the same time, it prevents the algorithm from prematurity and improves the classification effect. Finally, we conduct experiments on public data sets to compare with other advanced methods. Experimental results show that the proposed method can effectively enlarge the difference between normal data and abnormal data in reconstruction error.

The Augmented Intelligence of Things (AIoT) is an emerging technology that combines augmented intelligence with the Internet of Things (IoT) to facilitate advanced decision-making processes. In this paper, we focus on the detection of vehicle trajectory anomalies in a vehicle-road collaboration system by AIoT, aiming to improve the traffic safety and road operation efficiency. We transmit collaboration data collected by sensors to an IoT server, which enables the effective data analysis for vehicle trajectory information. We propose a self-supervised learning augmented intelligence algorithm to achieve precise and efficient detection of trajectory anomalies. First, we models the traffic road network as a topology graph. Subsequently, we sample the relevant subgraph contexts for each target node through a random walk algorithm. And the subgraphs with higher intimacy scores are selected as the contextual background to be input along with the target node. After that, the anomaly score of each target node is computed through the generative learning module and the contrastive learning module. To evaluate the effectiveness of our anomaly detection approach, we initially conduct pre-training of the model using four widely utilized graph machine learning datasets. The experimental results reveal that our approach surpasses previous methods in the accuracy of identifying graph anomaly nodes. In addition, we carry out our approach on two real traffic datasets with high accuracies of 86.47% and 85.2%, respectively. This result demonstrates the effectiveness of our proposed approach in detecting trajectory anomalies in real traffic scenarios.

The recent advancement of the Internet of Things (IoT) and information technology has led to the rapid expansion of interconnectivity among a billion devices across various applications. The advent of massive data has resulted in greater computational dependence, posing obstacles to applying security policies in energy-sensitive devices. However, public-key-based encryption algorithms are impractical or impossible to execute on these resource-limited terminals. In this paper, we propose a lightweight framework called STBCIoT based on a visual cryptography (VC) scheme to achieve low-latency encryption for large-scale data like biometric images. To reduce noise in encryption, we utilize central recognition and gray-level features of QR codes to integrate the visually friendly feature of QR into VC. we further propose a high-quality image generation model with the halftoning effect of VC to improve the quality of decrypted images. The experimental results demonstrate that our proposed method achieves high recognition performance on lossy decrypted images, effectively overcoming the performance limitations of traditional public key encryption methods for largescale images.

Multimodal hateful social media meme detection is an important and challenging problem in the vision-language domain. Recent studies show high accuracy for such multimodal tasks due to datasets that provide better joint multimodal embedding to narrow the semantic gap. Religiously hateful meme detection is not extensively explored among published datasets. While there is a need for higher accuracy on religiously hateful memes, deep learning–based models often suffer from inductive bias. This issue is addressed in this work with the following contributions. First, a religiously hateful memes dataset is created and published publicly to advance hateful religious memes detection research. Over 2000 meme images are collected with their corresponding text. The proposed approach compares and fine-tunes VisualBERT pre-trained on the Conceptual Caption (CC) dataset for the downstream classification task. We also extend the dataset with the Facebook hateful memes dataset. We extract visual features using ResNeXT-152 Aggregated Residual Transformations–based Masked Regions with Convolutional Neural Networks (R-CNN) and Bidirectional Encoder Representations from Transformers (BERT) uncased for textual encoding for the early fusion model. We use the primary evaluation metric of an Area Under the Operator Characters Curve (AUROC) to measure model separability. Results show that the proposed approach has a higher AUROC score of 78%, proving the model’s higher separability performance and an accuracy of 70%. It shows comparatively superior performance considering dataset size and against ensemble-based machine learning approaches.

Traffic sign recognition is a crucial aspect of autonomous vehicle research, and deep learning techniques have significantly contributed to its progress. Nevertheless, the distribution of traffic sign information in natural complex road conditions is long-tailed, and traffic sign identification in complex road conditions has become a significant barrier to autonomous vehicle applications. The imbalanced distribution of information on the dataset migrates to the feature space during training, resulting in imbalanced classifier prediction. In this paper, we propose the gradient rebalanced traffic sign recognition (GRTR) method to address this problem for the first time. GRTR first evaluates the prediction and classification bias of the classifier using the fitted deviation between the model’s output probability and the ground-truth distributions. Then, GRTR dynamically adjusts the correction and compensation factors following the classifier’s prediction and classification biases. GRTR rebalances the positive and negative sample gradients for each category based on the synergistic effect of the correction and compensation factors to prevent the transfer of distribution imbalance and to significantly enhance the performance of the traffic sign classifier under difficult road conditions. Experimental results demonstrate that our GRTR achieves state-of-the-art performance on long-tailed traffic sign and multilabel datasets.Note to Practitioners—Most traffic sign recognition algorithms are still designed based on the assumption of a balanced distribution of traffic signs in the dataset. Real-world autonomous vehicles require traffic sign recognition on datasets with severely imbalanced distributions. This paper proposes a general approach to solving the long-tailed traffic sign recognition problem.

In the undertaken study, we have used a customized dataset termed ``Cardiac-200'' and the benchmark dataset ``PhysioNet.'' which contains 1500 heartbeat acoustic event samples (without augmentation) and 1950 samples (with augmentation) heartbeat acoustic events such as normal, murmur, extrasystole, artifact, and other unlabeled heartbeat acoustic events. The primary reason for designing a customized dataset, ``cardiac-200,'' is to balance the total number of samples into categories such as normal and abnormal heartbeat acoustic events. The average duration of the recorded heartbeat acoustic events is 10-12 s. In the undertaken study, we have analyzed and evaluated various heartbeat acoustic events using audio processing libraries such as Chromagram, Chroma-cq, Chroma-short-time Fourier transform (STFT), Chroma-cqt, and Chroma-cens to extract more information from the recorded heartbeat sound signals. The noise removal process has been carried out using local binary pattern (LBP) methodology. The noise-robust heartbeat acoustic images are classified using long short-term memory (LSTM)-convolutional neural network (CNN), recurrent neural network (RNN), LSTM, Bi-LSTM, CNN, K-means Clustering, and support vector machine (SVM) methods. The obtained results have shown that the proposed InfusedHeart Framework had outclassed all the other customized machine learning and deep learning approaches such as RNN, LSTM, Bi-LSTM, CNN, K-means Clustering, and SVM-based classification methodologies. The proposed Knowledge-infused Learning Framework has achieved an accuracy of 89.36% (without augmentation), 93.38% (with augmentation), and a standard deviation of 10.64 (without augmentation), and 6.62 (with augmentation). Furthermore, the proposed framework has been tested for various signal-to-noise ratio conditions such as SignaltoNoiseRatio0, SignaltoNoiseRatio3, SignaltoNoiseRatio6, SignaltoNoiseRatio9, SignaltoNoiseRatio12, SignaltoNoiseRatio15, and SignaltoNoiseRatio18. In the end, we have shown a detailed comparison of texture and without texture approaches and have discussed future enhancements and prospective ways for future directions.

The abnormal growth of malignant or nonmalignant tissues in the brain causes long-term damage to the brain. Magnetic resonance imaging (MRI) is one of the most common methods of detecting brain tumors. To determine whether a patient has a brain tumor, MRI filters are physically examined by experts after they are received. It is possible for MRI images examined by different specialists to produce inconsistent results since professionals formulate evaluations differently. Furthermore, merely identifying a tumor is not enough. To begin treatment as soon as possible, it is equally important to determine the type of tumor the patient has. In this paper, we consider the multiclass classification of brain tumors since significant work has been done on binary classification. In order to detect tumors faster, more unbiased, and reliably, we investigated the performance of several deep learning (DL) architectures including Visual Geometry Group 16 (VGG16), InceptionV3, VGG19, ResNet50, InceptionResNetV2, and Xception. Following this, we propose a transfer learning(TL) based multiclass classification model called IVX16 based on the three best-performing TL models. We use a dataset consisting of a total of 3264 images. Through extensive experiments, we achieve peak accuracy of 95.11%, 93.88%, 94.19%, 93.88%, 93.58%, 94.5%, and 96.94% for VGG16, InceptionV3, VGG19, ResNet50, InceptionResNetV2, Xception, and IVX16, respectively. Furthermore, we use Explainable AI to evaluate the performance and validity of each DL model and implement recently introduced Vison Transformer (ViT) models and compare their obtained output with the TL and ensemble model.

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

Intrusion detection and prevention has been an area of active research in the use of machine learning for cyber security practices. Artificial Neural Networks (ANN) are one of the best-known models when it comes to accurately classifying intrusions into attack classes or benign profiles but they are resource-intensive. A server is typically associated with large a amount of high-frequency data. In such a condition, deploying ANN for this purpose can cause significant overhead and delays in the delivery of packets to their intended destination. Furthermore, existing deep learning approaches do not address the similarity between different attack classes, the information regarding which can be used to select the defence strategies. We propose a lightweight architecture called DAIDNet that utilizes the information contained by the domain of classes extracted from packet distributions to make better predictions. Results show that DAIDNet achieves better accuracy while being significantly smaller in size than a baseline ANN model. DAIDNet achieves validation accuracy of 99.66% and 99.98% on the NSL-KDD and CICIDS-2018 datasets, respectively.

With the wide deployment of the Internet of Things (IoT), large volumes of incomplete multiview data that violates data integrity is generated by various applications, which inevitably produces negative impacts on the quality of service of IoT systems. Incomplete multiview clustering (IMC), as an essential technique of data processing, has the potential for mining patterns of incomplete IoT data. However, previous methods utilize notion-strong distances that can only measure differences between distributions at the overlap of data manifolds in fusing complementary information of data for pattern mining. They may suffer from biased estimation and information loss in capturing intrinsic structures of incomplete multiview data. To address these challenges, a semidiscrete multiview optimal transport (SD-MOT) is defined for IMC, which utilizes distances with weak notions to capture intrinsic structures of incomplete multiview data. Specifically, IMC is recast as an equivalent optimal transport between continuous incomplete multiview data and discrete clustering centroids, to avoid the strict assumption on overlap between manifolds in pattern mining. Then, SD-MOT is instantiated as a deep incomplete contrastive clustering network to remedy biased estimation and information loss on intrinsic structures of incomplete multiview data. Afterwards, a variational solution to SD-MOT is derived to effectively train the network parameters for pattern mining. Finally, extensive experiments on four representative incomplete multiview datasets verify the superiority of SD-MOT in comparison with nine baseline methods.

In this paper, we investigate the physical layer security for multi-beam satellite communications in the presence of multiple eavesdroppers (Eves). In particular, a worst-case eavesdropping scheme is considered. To achieve a positive secrecy rate, we consider a non-orthogonal multiple access (NOMA) scheme with imperfect channel state information on Eves. Fur-thermore, we design a robust precoding algorithm to maximize the achievable secrecy rate of legitimate ground user equipments, which satisfies the quality of service for each user, secure outage probability constraint and the NOMA decoding order between legitimate users. In contrast to the conventional total transmit power constraint, the algorithm is designed under joint total and per-beam transmit power constraints. We first combine the decomposition-based large deviation inequality, the arithmetic-geometric mean inequality with a penalty function iterative algorithm to solve the non-convex precoding problem, and further analyze the computational complexity of the algorithm. Simulation results verify the robustness and superiority of the proposed algorithm.

Detection and monitoring of ships in the images captured from satellites or aerial vehicles is a pivotal task in maritime security applications. Recent advancements in aerial communication and computer vision has enabled real-time collection of such images as well as development of robust and precise models for ship detection. However, conventional machine learning (ML) based models are prone to security and privacy issues as the real-time data captured through aerial imagery may be exposed during transfer or after storage in the cloud server. Furthermore, real-time decision making is a challenging task with conventional ML models due to the latency incurred while transmitting large amount of data from maritime aerial network to the cloud. To address the privacy and latency challenges, we propose a privacy-preserving game-theory based federated learning approach for ship detection in aerial images from maritime network. FL improves privacy by allowing raw data to reside at the edges/clients, and game theory helps in optimizing the parameter updates that are sent to the centralized server. Evaluation results prove the efficacy of the proposed model with a prediction accuracy of 96.01%, 92.96% reduction in time complexity and also 8.28% reduction in communication overhead.

The volume of multimedia data produced by various smart devices has increased dramatically with the advent of new digital technologies, including in the Internet of Vehicles (IoV). It has become more difficult to extract valuable insights from multimedia data due to several challenges during data analysis. The main problem is the need to quickly and precisely identify abnormalities in multimedia data. This research presents an unusual occurrence of the audio forensics database named UOAFDB and a practical method for identifying and categorizing unusual occurrences in audio files. To study the detection of abnormal audio and the classification of rare sound (e.g., car crash—machine gun, explosion) events for audio forensics, we construct a large audio dataset containing ten rare special events (anomalies) with 15 different background environmental settings (e.g., beach, restaurant, and train). The suggested method determines the optimal amount of features using the best feature extraction methodology available by extracting Mel-frequency cepstral coefficients (MFCCs) features from the audio signals of the newly formed dataset. Modern deep learning algorithms use these features as input to assess performance. Additionally, we apply deep learning methods to the most recent and best available dataset and obtain promising outcomes. The experimental findings demonstrate promising results on the UOAFDB dataset.

Abstract The rampant spread of explicit content across social media can leave a damaging mark on our society. Hence, the need to be vigilant in detecting and curtailing sexually explicit content cannot be overstated. As such, it becomes paramount to discern and manage sexually explicit material to curb its dissemination and safeguard our digital communities from its harmful effects. In this article, we propose a unique technique entitled attention‐enabled pooling (ABP) embedded Swin transformer‐based YOLOv3 (ASYv3) for the detection of obscene areas present in the images with a bounding box around the offensive regions. ASYv3 employs a unique two‐step approach for enhanced performance in obscene detection. In the first step, a scalable and efficient Swin transformer block is integrated, utilizing self‐attention and model parallelism to train massive models effectively. In the second phase, the embedding layer of the Swin transformer is replaced with ABP, mitigating disruption of feature context. ABP allows for the projection of raw‐valued features into linear form with proper attention to feature context information at specified locations, resulting in optimized feature extraction. The proposed ABP embedded Swin transformer‐based YOLOv3 (ASYv3) was trained with annotated obscene images (AOI) dataset. The proposed ASYv3 model surpassed the state‐of‐the‐art methods by achieving 97% testing accuracy, 96.62% precision, 97.40% sensitivity, 3.48% FPR rate, 97.37% NPV values, and 95.59% mAP values, respectively.

Abstract Countless cybercrime instances have shown the need for detecting and blocking obscene material from social media sites. Deep learning methods (DLMs) outperformed in recognizing obscene content flooded on many online platforms. However, these contemporary DLMs primarily treat the recognition of obscene content as a simple task of binary classification, rather than focusing on the labelling of obscene areas. Hence, many of these methods could not pay attention to the fact that misclassification samples are so diverse. Therefore, this paper focuses on two aspects (i) developing a deep learning model that could classify and label the obscene portion, and (ii) generating a labelled obscene image dataset with a wide variety of obscene samples to minimize the risks of inaccurate recognition. We have proposed a method named S3Pooling based bottleneck attention module (BAM) embedded MobileNetV2‐YOLOv3 (SBMYv3) for automatic detection of obscene content using an attention mechanism and a suitable pooling strategy. The key contributions of our article are: (i) generation of a well‐labelled obscene image dataset with a variety of augmentation strategies using Pix‐2‐Pix GAN (ii) modifications to the backend architecture of YOLOv3 using MobileNetV2 and BAM to ensure focused and accurate feature extraction, and (iii) selection of an optimal pooling strategy, that is, S3Pooling strategy, while taking the design of the feature extractor into account. The proposed SBMYv3 model outperformed other state‐of‐the‐art models with 99.26% testing accuracy, 99.39% recall, 99.13% precision, and 99.13% IoU values respectively.

Abstract The software is changing rapidly with the invention of advanced technologies and methodologies. The ability to rapidly and successfully upgrade software in response to changing business requirements is more vital than ever. For the long‐term management of software products, measuring software maintainability is crucial. The use of soft computing techniques for software maintainability prediction has shown immense promise in software maintenance process by providing accurate prediction of software maintainability. To better understand the role of soft computing techniques for software maintainability prediction, we aim to provide a systematic literature review of soft computing techniques for predicting software maintainability. Firstly, we provide a detailed overview of software maintainability. Following this, we explore the fundamentals of software maintainability and the reasons for adopting soft computing methodologies for predicting software maintainability. Later, we examine the soft computing approaches employed in the process of software maintainability prediction. Furthermore, we discuss the difficulties and potential solutions associated with the use of soft computing techniques in predicting maintainability of software. Finally, we conclude the review with some promising future directions to drive further research innovations and developments in this promising area. This systematic literature review provides a comprehensive overview of the soft computing strategies utilized for software maintainability for future researchers.

Since Facebook officially changed its name to Meta in Oct. 2021, the metaverse has become a new norm of social networks and three-dimensional (3D) virtual worlds. The metaverse aims to bring 3D immersive and personalized experiences to users by leveraging many pertinent technologies. Despite great attention and benefits, a natural question in the metaverse is how to secure its users' digital content and data. In this regard, blockchain is a promising solution owing to its distinct features of decentralization, immutability, and transparency. To better understand the role of blockchain in the metaverse, we aim to provide an extensive survey on the applications of blockchain for the metaverse. We first present a preliminary to blockchain and the metaverse and highlight the motivations behind the use of blockchain for the metaverse. Next, we extensively discuss blockchain-based methods for the metaverse from technical perspectives, such as data acquisition, data storage, data sharing, data interoperability, and data privacy preservation. For each perspective, we first discuss the technical challenges of the metaverse and then highlight how blockchain can help. Moreover, we investigate the impact of blockchain on key-enabling technologies in the metaverse, including Internet-of-Things, digital twins, multi-sensory and immersive applications, artificial intelligence, and big data. We also present some major projects to showcase the role of blockchain in metaverse applications and services. Finally, we present some promising directions to drive further research innovations and developments toward the use of blockchain in the metaverse in the future.

Abstract The proliferation of IoT devices has influenced end users in several aspects. Yottabytes (YB) of information are being produced in the IoT environs because of the ever-increasing utilization capacity of the Internet. Since sensitive information, as well as privacy problems, always seem to be an unsolved problem, even with best-in-class in-formation governance standards, it is difficult to bolster defensive security capabilities. Secure data sharing across disparate systems is made possible by blockchain technology, which operates on a decentralized computing paradigm. In the ever-changing IoT environments, blockchain technology provides irreversibility (immutability) usage across a wide range of services and use cases. Therefore, blockchain technology can be leveraged to securely hold private information, even in the dynamicity context of the IoT. However, as the rate of change in IoT networks accelerates, every potential weak point in the system is exposed, making it more challenging to keep sensitive data se-cure. In this study, we adopted a Multi-level Blockchain-based Secured Framework (M-BSF) to provide multi-level protection for sensitive data in the face of threats to IoT-based networking systems. The envisioned M-BSF framework incorporates edge-level, fog-level, and cloud-level security. At edge- and fog-level security, baby kyber and scaling kyber cryptosystems are applied to ensure data preservation. Kyber is a cryptosystem scheme that adopts public-key encryption and private-key decryption processes. Each block of the blockchain uses the cloud-based Argon-2di hashing method for cloud-level data storage, providing the highest level of confidentiality. Argon-2di is a stable hashing algorithm that uses a hybrid approach to access the memory that relied on dependent and independent memory features. Based on the attack-resistant rate (> 96%), computational cost (in time), and other main metrics, the proposed M-BSF security architecture appears to be an acceptable alternative to the current methodologies.

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.

In the current pandemic, global issues have caused health issues as well as economic downturns. At the beginning of every novel virus outbreak, lockdown is the best possible weapon to reduce the virus spread and save human life as the medical diagnosis followed by treatment and clinical approval takes significant time. The proposed COUNTERSAVIOR system aims at an Artificial Intelligence of Medical Things (AIoMT), and an edge line computing enabled and Big data analytics supported tracing and tracking approach that consumes global positioning system (GPS) spatiotemporal data. COUNTERSAVIOR will be a better scientific tool to handle any virus outbreak. The proposed research discovers the prospect of applying an individual’s mobility to label mobility streams and forecast a virus such as COVID-19 pandemic transmission. The proposed system is the extension of the previously proposed COUNTERACT system. The proposed system can also identify the alternative saviour path concerning the confirmed subject’s cross-path using GPS data to avoid the possibility of infections. In the undertaken study, dynamic meta direct and indirect transmission, meta behavior, and meta transmission saviour models are presented. In conducted experiments, the machine learning and deep learning methodologies have been used with the recorded historical location data for forecasting the behavior patterns of confirmed and suspected individuals and a robust comparative analysis is also presented. The proposed system produces a report specifying people that have been exposed to the virus and notifying users about available pandemic saviour paths. In the end, we have represented 3-D tracker movements of individuals, 3-D contact analysis of COVID-19 and suspected individuals for 24 h, forecasting and risk classification of COVID-19, suspected and safe individuals.

Presently, trillions of Internet of Things (IoT) devices are in use, with many more projected to join IoT networks in the future. These IoT devices create a massive volume of data, which cannot be transmitted over the network without proper security and privacy. Furthermore, as the amount of information and variety of interconnected devices grows, problems, including excessive response time, bandwidth constraints, and scalability, emerge in proper network design. To solve the constraints of today’s smart cities for next-generation networks, an effective, secure, and scalable distributed framework must be designed bringing computing and storage resources nearer to endpoints. In this article, combining the strengths of software-defined networks (SDNs) and blockchain technology, an innovative adaptable network infrastructure for smart cities is developed. The network is divided into different domains in which SDN will detect potential attacks and transmit the secured data to the blockchain. Our in-depth experimental analysis on performance evaluation show that the proposed framework achieves 12.75% improvement over baseline methodologies.

Emotion detection (ED) plays a vital role in determining individual interest in any field. Humans use gestures, facial expressions, and voice pitch and choose words to describe their emotions. Significant work has been done to detect emotions from the textual data in English, French, Chinese, and other high-resource languages. However, emotion classification has not been well studied in low-resource languages (i.e., Urdu) due to the lack of labeled corpora. This article presents a publicly available Urdu Nastalique Emotions Dataset (UNED) of sentences and paragraphs annotated with different emotions and proposes a deep learning (DL)-based technique for classifying emotions in theUNEDcorpus. Our annotatedUNEDcorpus has six emotions for both paragraphs and sentences. We perform extensive experimentation to evaluate the quality of the corpus and further classify it using machine learning and DL approaches. Experimental results show that the developed DL-based model performs better than generic machine learning approaches with an F1 score of 85% on the UNED sentence-based corpus and 50% on the UNED paragraph-based corpus.

The Internet of Medical Things (IoMT) has a bright future with the development of smart mobile devices. Information technology is also leading changes in the healthcare industry. IoMT devices can detect patient signs and provide treatment guidance and even instant diagnoses through technologies, such as artificial intelligence (AI) and wireless communication. However, conventional centralized machine learning approaches are often difficult to apply within IoMT devices because of the difficulty of large-scale collection of patient data and the potential risk of privacy breaches. Therefore, we propose a blockchain-based two-stage federated learning approach that allows IoMT devices to train a global model collaboratively without gathering the data to a central server. Specifically, to address the problem of poor training performance on non-independent identically distributed (non-IID) data, we design a blockchain-based data-sharing scheme that can significantly improve the model’s accuracy without threatening user privacy. We also design a client selection mechanism to further improve the system’s efficiency. Finally, we validate the feasibility and effectiveness of our system through simulation experiments on three popular datasets (i.e., MNIST, Fashion-MNIST, and CIFAR-10).

Nowadays, much research leverages the clustering to mine commercial patterns from data in enterprise systems. However, previous methods cannot fully consider local structures and global topology of data, which may cause the degradation of clustering performance. To address the challenges, a deep multimodal adversarial cycle-consistent network (DMACCN) is proposed to mine intrinsic patterns of data, which can capture the local structures from instance reconstructions and the global topology from adversarial games. Specifically, DMACCN is designed as an adversarial encoding-decoding architecture composed of the modality specific-encoder, the modality-common fusion network, the cycle-consistent modality-specific generator, and the modality-fusion discriminator, which can fully fuse complementary information of data. Then, an adversarial cycle-consistent loss is devised to guide the clustering pattern mining from complementary information of data, which can align semantics between modalities and capture clustering structures of instances. The two components collaborate in a seamless manner to capture accurate commercial patterns. Finally, extensive experimental results on four datasets show DMACCN greatly outperforms the comparison methods.

The papers in this special section focus on federal learning applications for the Internet of Medical Things. Due to to the advancements in Internet of Medical Things (IoMT), wearable devices, remote monitoring of patients is possible like never before. Machine learning and deep learning techniques help the doctors immensely in remotely diagnosing the patients by learning the patterns from the data generated through these devices [1]. The main problem with traditional machine learning (ML)/deep learning (DL) models is that the data from the individual devices, sensors, wearables of patients have to be transferred to the central servers to train the data using the ML/DL models. Due to the sensitive nature of the healthcare data, the aforementioned approach of transferring the patients’ data to the central servers may create serious security and privacy issues.

Telemedicine and online consultations with doctors has become very popular during the pandemic and involves the transmission of medical data through the internet. Thus this raises concern about the security of the medical data of the patient as the records to contain sensitive and confidential information. A Secure multimedia transformation approach is proposed in this paper using a deep learning-based chaotic logistic map. The proposed work achieves novelty by the integration of a lightweight encryption function using a chaotic logistic map. It also uses the ResNet model to perform classification for identifying the fake medical multimedia data. A linear feedback shift register operations and an interactive user interface facilitate ease of usage to secure the medical multimedia data. The chaotic map provides the security properties such as confusion and diffusion necessary for the encryption ciphers. At the same time, they are highly sensitive to input conditions, thus making the proposed encryption algorithm more secure and robust. The proposed encryption mechanism helps in securing the medical image and video data. On the receiver side, Multilayer perceptions (MLP) of the deep learning approach are used to classify the medical data according to the features required to make other processes. When tested, the proposed work proves efficient in securing medical data against various cyber-attacks and exhibits high entropy levels.

Trajectory design is of great significance for the intelligent Unmanned Ground Vehicle (UGV) when performing various ground tasks. Though obstacle avoidance, speed control and other movement issues in the UGV navigation have been considered by the current research, the UGV path planning against malicious radio source is off the beaten path. To address such a research gap, we propose a reinforcement learning-based scheme to design UGV trajectory against malicious radio source as well as minimize the movement cost. Firstly, the malicious radio source detection and localization models are introduced after the Received Signal Strength Indicator (RSSI) map establishment. Then, the RSSI Map-based UGV trajectory design problem is formulated, where the movement cost and security risk are both concerned. To solve the formed problem, we propose a reinforcement learning-based trajectory design scheme, whose complexities are analyzed in detail. Finally, experiments are conducted under various parameter settings, where the simulation results evaluate the correctness and effectiveness of the proposed algorithm.

With the rapid development of mobile technology, it is very convenient to share people’s current locations by checking-in on Location-Based Social Networks (LBSNs). Using users’ check-in histories to study mobility preferences and recommend new locations is a typical application to LBSNs. Most existing models explore reasonable representations for users and locations. However, a lack of behavioral mobility modeling would hamper a better understanding of users’ mobility patterns. This paper proposes a location recommendation model to serve the personalized LBSNs application, called Spatio-temporal Individual mobility graph encoding network with Group Mobility Assistance (SIGMA). We design a spatio-temporal interaction enhanced graph neural network to encode the mobility graphs to represent individual mobility behaviors. Furthermore, we provide a novel stacked scoring approach to generate the recommendation score by combining the stacked individual mobility graphs with the group influences. We conduct extensive experiments on two real-world LBSNs data, Foursquare and Gowalla. The result demonstrates SIGMA outperforms ten state-of-the-art models and further confirms that both the individual and the group mobility behaviors play essential roles in the practical scenario of location recommendation.

Traffic problems continue to deteriorate because of increasing population in urban areas that rely on many modes of transportation, the transportation infrastructure has achieved considerable strides in the last several decades. This has led to an increase in congestion control difficulties, which directly affect citizens through air pollution, fuel consumption, traffic law breaches, noise pollution, accidents, and loss of time. Traffic prediction is an essential aspect of an intelligent transportation system in smart cities because it helps reduce overall traffic congestion. This article aims to design and enforce a traffic prediction scheme that is efficient and accurate in forecasting traffic flow. Available traffic flow prediction methods are still unsuitable for real-world applications. This fact motivated us to work on a traffic flow forecasting issue using Vision Transformers (VTs). In this work, VTs were used in conjunction with Convolutional neural networks (CNN) to predict traffic congestion in urban spaces on a city-wide scale. In our proposed architecture, a traffic image is fed to a CNN, which generates feature maps. These feature maps are then fed to the VT, which employs the dual techniques of tokenization and projection. Tokenization is used to convert features into tokens containing Vision information, which are then sent to projection, where they are transformed into feature maps and ultimately delivered to LSTM. The experimental results demonstrate that the vision transformer prediction method based on Spatio-temporal characteristics is an excellent way of predicting traffic flow, particularly during anomalous traffic situations. The proposed technology surpasses traditional methods in terms of precision, accuracy and recall and aids in energy conservation. Through rerouting, the proposed work will benefit travellers and reduce fuel use.

As a promising enabler for edge intelligence, Unmanned Aerial Vehicles (UAV) have become more and more important in Mobile Edge Computing Networks (MECN), such as communication, computation, collection and control service supply. Although Age of Information (AoI) minimization is indispensable for fresh information collection and computation in the UAV-aided MECN, some attackers can launch attacks to deteriorate the availability of precious channel resources, such as revealed channel access attacks (CAAs). Moreover, recent research has not considered the system’s active probability and security issues concurrently, e.g., CAA, in the average AoI minimization process. In this paper, to deal with this problem, we consider an AoI-oriented channel access problem under CAA with a game theory viewpoint. Firstly, to obtain a MECN-based AoI indicator under CAA, the system model with active probability consideration is established. Next, the channel access-based AoI minimization problem is formulated from the viewpoint of the Ordinary Potential Game (OPG). Furthermore, two algorithms called AACSD and DCASD are proposed to determine channel access strategies, by which the Nash Equilibrium (NE) solution of the OPG could be reached. Finally, experiments are conducted under homogeneous and heterogeneous parameter settings, and the simulation results evaluate the correctness and effectiveness of our proposals.

Federated learning can effectively ensure data security and improve the problem of data islanding. However, the performance of federated learning-based schemes could be better due to the imbalance of image data. Therefore, this paper proposes a federated learning approach based on priori knowledge and a bilateral segmentation network for image edge extraction. First, federated learning can distribute training images for some special complex images due to the small sample and unshared data. Then, the image with similar edge information to the original image is learned to obtain prior knowledge, and the local uniform sparsity method is used to strengthen the detail features and weaken the background features. Based on the bilateral segmentation network, we introduce a dilated pyramid pooling layer and multi-scale feature fusion module to fuse the shallow detailed features in the context path with the deep abstract features obtained through the dilated pyramid pooling. The final result is obtained by fusing the result with prior knowledge and the result with the context path. Finally, we conduct experiments on some public datasets, and the results show that the proposed method greatly improves extraction accuracy compared with the traditional and the most advanced methods.

The Internet of Things (IoT), with the ease of access of Automated Vehicles, is the most reliable technology in the 21stcentury making every possible thing within seconds. The people in this era are blessed with all the new technology, and new gadgets, due to which many things which used to take longer are done within nanoseconds. IoT combines computing devices, mechanical devices, digital machines, objects, and people which possess the ability to transfer data over the network with Unique identifiers (UIDs) without human intervention. Such IoT-enabled Automated Guided Vehicles (AGV) are more reliable on networks for every action. Deep learning and machine learning techniques are pivotal for the successful implementation of IoT-based applications including AGVs. A botnet refers to the attacks which come from robot Network attacks. Recently, many organizations have been compromised using this attack. Most affected devices are connected to IoT as it uses automatically generated data. The ideology of this study is to propose an intrusion prediction system which can predict botnet attacks in AGVs. In this study, N – Balo dataset is used for classification, clustering and prediction. The technique implemented in this paper may provide some roots to develop the most reliable and highly secured AGV network.

As a promising enabler for edge intelligence, Unmanned Aerial Vehicles (UAVs) are playing a more and more important role in Mobile Edge Computing Networks (MECN), such as ground sensor communication assistance, user data collection, edge computation offloading and remote control services. In UAV-aided MECN, the timeliness of exchange data is a key factor that influences the real-time data-driven decisions at the server-side. Simultaneously, the Age of information (AoI) is also an indicator that reflects the freshness of data in terms of the destination during the communication process. Hence, AoI minimization is a vital goal in the MECN. The most recent work overlooks the possible security issues in the AoI minimization process, especially the revealed channel access attacks (CAAs), which aim to deteriorate network performance from ground to air channels. To overcome this research gap, in this paper, we improve the AoI-oriented channel access problem under CAA from the perspective of game theory. Firstly, a system model with active probability consideration is established to obtain a MECN-based AoI indicator under CAA. Subsequently, by utilizing Ordinary Potential Game (OPG), we formulate the AoI-based channel access optimization problem. Then, to reach the Nash Equilibrium (NE) of the OPG, a learning algorithm called Distributed Channel Access Strategy Determination (DCASD) is proposed to determine the channel access strategies. Finally, we conduct experiments under different parameters to present the better performance of our algorithm as compared with related work.

In the process of drone development, most of the current state systems’ design is based on high-weight functionalities. Due to high-weight functionalities, it is observed that if the drone drops at a particular point, the entire design is fragmented. Also, well-defined functionalities of drones for a specific application can only be designed if radial functionalities are defined at proper angles. Therefore, this article addresses the issues present in the existing method using the CRA algorithm, where radial functions, represented in terms of input and hidden weighting functions, are explored utterly. Additionally, a novel analytical procedure that establishes the coverage area for the data transfer approach has been incorporated into the drones’ architecture. Additionally, employing motion signatures and a special identification system, the developed drone system can function along various paths. To evaluate the effectiveness of the suggested system, three scenarios are organized as a basic functionality model. With the right scattering ratio, the comparison inscriptions show that the proposed approach can achieve an 82% success rate.

Abstract Human faces contain useful information that can be used in the identification of age, gender, weight etc. Among these biometrics, body mass index (BMI) and body weight are good indicators of a healthy person. Motivated by the recent health science studies, this work investigates ways to identify malnutrition affected people and obese people by analyzing body weight and BMI from facial images by proposing a regression method based on the 50‐layers Residual network architecture. For face detection, Multi‐task Cascaded Convolutional Neural Networks have been employed. A system is created to evaluate BMI along with age and gender from human facial real‐time images. Malnutrition and obesity are commonly determined with the help of BMI. In the previous works, height, weight, and BMI estimation through automatic means have predominantly focused on full‐body images and videos of humans. The usage of facial images for estimating such traits have been given less importance. In order to facilitate the analysis, the dataset is cleaned along with metadata containing information about the persons height, weight, age, and gender. Gender‐based analysis is performed for the prediction of BMI. Finally, an email containing the persons picture along with their details is sent to the concerned health officer.

In recent years, blockchain networks have attracted significant attention in many research areas beyond cryptocurrency, one of them being the Edge of Things (EoT) that is enabled by the combination of edge computing and the Internet of Things (IoT). In this context, blockchain networks enabled with unique features, such as decentralization, immutability, and traceability, have the potential to reshape and transform the conventional EoT systems with higher security levels. Particularly, the convergence of blockchain and EoT leads to a new paradigm, calledBEoTthat has been regarded as a promising enabler for future services and applications. In this article, we present a state-of-the-art review of recent developments in the BEoT technology and discover its great opportunities in many application domains. We start our survey by providing an updated introduction to blockchain and EoT along with their recent advances. Subsequently, we discuss the use of BEoT in a wide range of industrial applications, from smart transportation, smart city, smart healthcare to smart home, and smart grid. Security challenges in the BEoT paradigm are also discussed and analyzed, with some key services, such as access authentication, data privacy preservation, attack detection, and trust management. Finally, some key research challenges and future directions are also highlighted to instigate further research in this promising area.

Due to the emergence of heterogeneous Internet of Medical Things (IoMT) (e.g., wearable health devices, smartwatch monitoring, and automated insulin delivery systems), large volumes of patient data are dispatched to central cloud servers for disease analysis and diagnosis. Although this direct mode brings a lot of convenience for both patients and medical professionals (MPs), the open communication channel between them also incurs several security and privacy issues, such as man-in-the-middle attacks, eavesdropping attacks, and tracking attacks. Based on the unsolved challenges in wireless medical sensor networks (WMSNs), several researchers have proposed various authentication and key agreement (AKA) protocols for this type of healthcare system recently. However, most of these protocols do not perceive physical-layer security and over-centralized server problem in WMSN. In this article, to address these two open problems, we propose a lightweight and reliable authentication protocol for WMSN, which is composed of cutting-edge blockchain technology and physically unclonable functions (PUFs). In addition, a fuzzy extractor scheme is introduced to deal with biometric information. Subsequently, two security evaluation methods are used to prove the high reliability of our proposed scheme. Finally, performance evaluation experiments illustrate that the proposed mutual authentication protocol requires the least computation and communication cost among the compared schemes.

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

Since the outbreak of COVID-19 pandemic in 2020, a dramatic loss of human life has occurred and this trend presents an unprecedented challenge to public health, economic systems and social operations. Hence, it is urgent for us to take some countermeasures to restrain and dispel epidemic diffusion to the uttermost. Data freshness plays an inevitable role in timely infestor determination during this process. However, existing works pay little attention to optimizing this indicator in health monitoring. To make up this research gap, in this paper, we propose a mixed game-based Age of Information (AoI) optimization scheme, where the edge-based wireless technologies and AI-empowered diagnostic bots are adopted. Firstly, we establish the system model for Epidemic Prevention and Control Center (EPCC)-based health state monitoring network, where ultimate biosensing data is transmitted from AI bots via edge servers. Then, upon deriving AoI expression with a closed form, the minimization goal between edge servers and bots is specified. Simultaneously, we reformulate the AoI optimization problem from the mixed game viewpoint (i.e., coalition formation game and ordinary potential game), and then propose two algorithms for cooperative order-based bot deployment and stochastic learning-based channel selection. Finally, compared with the typical baselines, the experiment result shows our scheme can reach the lower AoI value for biosensing data transmission under different parameter settings.

The papers in this special section focus on security and privacy issues associated with Industry 4.0. In 2011, a group of delegates from business and academia, and politics in German initially proposed the conception of the Fourth Industrial Revolution (or Industry 4.0), which aims to improve the competitive ability in the manufacturing industry of their country. Along with the emergence of the Industry 4.0 term, people started introspecting the existing shortcomings in contemporary industrial society. Especially, the technologies of the past generations cannot maintain data explosive requirements in the Internet and telecommunication industry and fuse real-time data, which would increase waste and reduce productivity and overall equipment effectiveness. Industry 4.0 recognizes the importance of this issue and makes full use of large-scale machine-to-machine communication and the Internet of things (IoT) to increase automation, improve communication, and self-monitoring and diagnose issues without human intervention, finally transforming traditional manufacturing and industrial practices into a modern smart organization. However, with the rapid growth of devices, security and privacy issues rise to the surface. A mass amount of data frequently exchanged in the public channel will draw the attention of some people with evil intentions. Moreover, the resource-limited devices without strong cryptographic assurance would be compromised and hacked by adversaries. Hence, assuring the authenticity, integrity, and nonrepudiation of these industrial IoT data is a hot issue for industry 4.0 at present.

Federated learning (FL) is a recent development in artificial intelligence, which is typically based on the concept of decentralized data. As cyberattacks are frequently happening in the various applications deployed in real time, most industrialists are hesitating to move forward in adopting the technology of the Internet of Everything. This article aims to provide an extensive study on how FL could be utilized for providing better cybersecurity and prevent various cyberattacks in real time. We present an extensive survey of the various FL models currently developed by researchers for providing authentication, privacy, trust management, and attack detection. We also discuss few real-time use cases that have been deployed recently and how FL is adopted in them for preserving privacy of data and improving the performance of the system. Based on the study, we conclude this article with some prominent challenges and future directions on which the researchers can focus for adopting FL in real-time scenarios.

The price gouging or price hike is a worldwide issue, and it is related to inflation. Because of rising prices, people in various countries cannot afford nutritious food or proper treatment. Sometimes shops, restaurants, and transportation service providers charge more than the prescribed product price from buyers. In addition, unauthorized VAT or Tax is taken on products that the government exempts. Another reason for price hikes is bribery, and it occurs in transporting and delivering goods. This article introduces a blockchain-based Internet of Things model to monitor product price hikes and corruption from the Industry 4.0 and blockchain 5.0 point of view. Industries produce and package different products. Wholesalers and retailers purchase products from industrial companies. The primary goal of this article is to propose a blockchain mechanism for monitoring price hikes and corruption where the government can monitor buying and selling between buyers and industrial companies. Here, we have established blockchain-integrated remote database model where blockchain relates to a relational database management system that uses remote database access protocol and Cloud server. This article presents the brief evolution of blockchain and industry generations. Finally, this article provides a next generation blockchain model. An intelligent government connected with Industry 4.0 monitors price hikes and corruption.

The breakdown of vital communication infrastructures is one of the most common characteristics of all disasters. It can cause severe communication problems such as time delays and data loss, which cause deterioration in system performance. New techniques are needed to cope with such situations, many of which have been made possible due to the ongoing evolution of artificial intelligence technologies. In this study, we consider the case of a network consisting of several router allocation problems in situations of high priority and emergency data allocation. A novel network component called the scheduler is introduced and window constraints for routers are imposed. To solve the studied problem, four different algorithms are developed in this work. These algorithms were then applied in a particular scenario consisting of several routers and 2200 instances. In terms of the gap and running time, the proposed algorithms provide acceptable results. The best performances were achieved using the critical packet algorithm for 80% of instances with an average gap value of 0.009 and an average time of 0.209 s.

Nowadays, the Industrial Internet of Things (IIoT) has remarkably transformed our personal lifestyles and society operations into a novel digital mode, which brings tremendous associations with all walks of life, such as intelligent logistics, smart grid, and smart city. Moreover, with the rapid increase of IIoT devices, a large amount of data is swapped between heterogeneous sensors and devices every moment. This trend increases the risk of eavesdropping and hijacking attacks in communication channels, so maintaining data privacy and security becomes two notable concerns at present. Recently, based on the mechanism of the Schnorr signature, a more secure and lightweight certificateless signature (CLS) protocol is popular for the resource-constrained IIoT protocol design. Nevertheless, we found most of the existing CLS schemes are susceptible to several common security weaknesses such as man-in-the-middle attacks, key generation center compromised attacks, and distributed denial of service attacks. To tackle the challenges mentioned previously, in this article, we propose a novel pairing-free certificateless scheme that utilizes the state-of-the-art blockchain technique and smart contract to construct a novel reliable and efficient CLS scheme. Then, we simulate the Type-I and Type-II adversaries to verify the trustworthiness of our scheme. Security analysis as well as performance evaluation outcomes prove that our design can hold more reliable security assurance with less computation cost (i.e., reduced by around 40.0% at most) and communication cost (i.e., reduced by around 94.7% at most) than other related schemes.

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

The integration of artificial intelligence and Internet of Things (IoT) has promoted the rapid development of artificial IoT (AIoT) networks. A wide range of AIoT applications have generated a great deal of data. The fifth-generation (5G) mobile communication has powerful data processing capabilities, and it is a key technology to enable AIoT big data processing. The explosive growth of the 5G users has made information security in AIoT networks a significant issue. Real-time security evaluation in AIoT networks is difficult due to user mobility and dynamic wireless environments. Thus, the evaluation and prediction of secrecy performance is a very critical research. In this article, new expressions for the nonzero secrecy capacity probability (NSCP) are derived to evaluate the mobile collaborative secrecy performance. An improved convolutional neural network (CNN) model, named as SI-CNN in this article, is proposed to predict the NSCP performance. The SI-CNN model combines the SqueezeNet and InceptionNet, and it has four convolution layers, which all adopt the same convolution model. For the first two layers, they employ a 2 × 1 convolution and a three-branch convolution, which not only increase the number of channels but also extract more features. For the last two layers, they employ the same structure, but different convolution kernels. The proposed SI-CNN prediction algorithm is shown to provide better NSCP performance prediction than other state-of-the-art methods. In particular, compared with wavelet neural network, the prediction precision of SI-CNN is improved by 26.8%.

The blockchain-enabled internet of medical things (IoMT) is an emerging paradigm that could provide strong trust establishment and ensure the traceability of data sharing in the IoMT networks. One of the fundamental building blocks for Blockchain is Elliptic Curve Digital Signature Algorithm (ECDSA). Nevertheless, when processing a large number of transactions, the verification of multiple signatures will incur cumbersome overhead to the nodes in Blockchain. Although batch verification is able to provide a promising approach that verifies multiple signatures simultaneously and efficiently, the upper bound of batch size is limited to small-scale and the efficiency will drop rapidly as the batch size grows in the state-of-the-art ECDSA batch schemes. Meanwhile, most of the existing researches only focus on improving the efficiency of batch verification algorithms in various cryptosystem while ignoring the identification of invalid signatures, which could cause severe performance degradation when the batch verification fails. Motivated by these observations, this paper proposes an efficient and large-scale batch verification scheme with group testing technology based on ECDSA. The application of the presented protocols in Bitcoin and Hyperledger Fabric has been analyzed as supportive and effective. When the batch verification returns a false result, we utilize group testing technology to improve the efficiency of identifying invalid signatures. Comprehensive simulation results demonstrate that our protocol outperforms the related ECDSA batch verification schemes.

The Intelligent Transportation System (ITS) is said to revolutionize the travel experience by making it safe, secure, and comfortable for the people. Although vehicles have been automated up to a certain extent, it still has critical security issues that require thorough study and advanced solutions. The security vulnerabilities of ITS allows the attacker to steal the vehicle. Therefore, the identification of drivers is required in order to develop a safe and secure system so that the vehicles can be protected from theft. There are two ways in which a driver can be identified: 1) face recognition of the driver, and 2) based on driving behavior. Face recognition includes image processing of 2-D images and learning of the features, which require high computational power. Drivers are known to have unique driving styles, whose data can be captured by the sensors. Therefore, the second method identifies drivers based on the analysis of the sensor data and it requires comparatively lesser computational power. In this paper, an optimized deep learning model is trained on the sensor data to correctly identify the drivers. The Long Short-Term Memory (LSTM) deep learning model is optimized for better performance. The novelty of the approach in this work is the inclusion of hyperparameter tuning using a nature-inspired optimization algorithm, which is an important and essential step in discovering the optimal hyperparameters for training the model which in turn increases the accuracy. The CAN-BUS dataset is used for experimentation and evaluation of the training model. Evaluation parameters such as accuracy, precision score, F1 score, and ROC AUC curve are considered to evaluate the performance of the model.

Malicious websites predominantly promote the growth of criminal activities over the Internet restraining the development of web services. Furthermore, we see different types of devices being equipped with WiFi capabilities, that allow web traffic to pass through the device’s data systems with ease. The proposed framework in the present study analyzes the Uniform Resource Locator (URL) through which malicious users can gain access to the content of the websites. It thus eliminates issues of run-time latency and possibilities of users being subjected to browser oriented vulnerabilities. The primary objective of this paper is to detect malicious links on the web using a machine learning classification technique that would help users defend against cyber-crime attacks and related threats of the real world. This may be helpful in the newly expanding Intelligent Infrastructures, where we see more data availability almost daily. The embedding of malicious URLs is a predominant web threat faced by the Internet community in the present day and age. Attackers falsely claim of being a trustworthy entity and lure users to click on compromised links to extract confidential information, victimizing them towards identity theft. The present work explores the various ways of detecting malicious links from the host-based and lexical features of the URL in order to protect users from being subjected to identity theft attacks.

With the explosive advancements in smartphone technology, video uploading/downloading has become a routine part of digital social networking. Video contents contain valuable information as more incidents are being recorded now than ever before. In this paper, we present a comprehensive survey on information extraction from video contents and forgery detection. In this context, we review various modern techniques such as computer vision and different machine learning (ML) algorithms including deep learning (DL) proposed for video forgery detection. Furthermore, we discuss the persistent general, resource, legal, and technical challenges, as well as challenges in using DL for the problem at hand, such as the theory behind DL, CV, limited datasets, real-time processing, and the challenges with the emergence of ML techniques used with the Internet of Things (IoT)-based heterogeneous devices. Moreover, this survey presents prominent video analysis products used for video forensics investigation and analysis. In summary, this survey provides a detailed and broader investigation about information extraction and forgery detection in video contents under one umbrella, which was not presented yet to the best of our knowledge.

In a broad spectrum, software metrics play a vital role in attribute assessment, which successively moves software projects. The metrics measure gives many crucial facets of the system, enhancing the system quality of software developed. Moreover, maintenance is the correction process that works out in the software system once the software is initially made. The noteworthy characteristic of any software is ‘change,’ and as a result, additional concern ought to be taken in developing software. So, the software is expected to be modified effortlessly (maintainable). Predicting software maintainability is still challenging, and accurate prediction models with low error rates are required. Since there are so many modern programming languages on the horizon. To accurately measure software maintainability, new techniques have to been introduced. This paper proposes a maintainability index (MI) by considering various software metrics by which the error gets minimized. It also intends to adopt a renowned optimization algorithm, namely Firefly (FF), for the optimum result. The proposed Base Model-FF is compared to other traditional models like BM-Differential Evolution (BM-DE), BM-Artificial Bee Colony (BM-ABC), BM-Particle Swarm Optimization (BM-PSO), and BM-Genetic Algorithm (BM- GA) in terms of performance metrics like Differential ratio, correlation coefficient, and Random Mean Square Error (RMSE).

Summary In the competing era of online industries, understanding customer feedback and satisfaction is one of the important concern for any business organization. The well‐known social media platforms like Twitter are a place where customers share their feedbacks. Analyzing customer feedback is beneficial, as it provides an advantage way of unveiling customer interests. The proposed system, namely Senti‐eSystem, aims at the development of sentiment‐based eSystem using hybridized Fuzzy and Deep Neural Network for Measuring Customer Satisfaction to assist business organizations for improving the quality of their services and products. The proposed approach initially deploys a Bidirectional Long Short Term Memory with attention mechanism to predict the sentiment polarity that is positive and negative, followed by Fuzzy logic approach to determine the customer satisfaction level, which further strengthens the capabilities of the proposed approach. The system achieves an accuracy of 92.86%, outperforming the previous state‐of‐art lexicon‐based approaches. Moreover, the effectiveness of the proposed system is also validated by applying the statistical test.

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.

As the number of digital text documents increases on a daily basis, the classification of text is becoming a challenging task. Each text document consists of a large number of words (or features) that drive down the efficiency of a classification algorithm. This article presents an optimized feature selection algorithm designed to reduce a large number of features to improve the accuracy of the text classification algorithm. The proposed algorithm uses noun-based filtering, a word ranking that enhances the performance of the text classification algorithm. Experiments are carried out on three benchmark datasets, and the results show that the proposed classification algorithm has achieved the maximum accuracy when compared to the existing algorithms. The proposed algorithm is compared to Term Frequency-Inverse Document Frequency, Balanced Accuracy Measure, GINI Index, Information Gain, and Chi-Square. The experimental results clearly show the strength of the proposed algorithm.