جامعة المعرفة
المصدر المعتمد للمعلومات البحثية والمخرجات هو قاعدة بيانات سكوبس (Elsevier Scopus) مع تدقيق بيانات الباحثين من عمادة البحث العلمي.

Research outputs

المخرجات البحثية

مقالات ومراجعات وأوراق مؤتمرات وفصول كتب، مفهرسة برقم DOI ومربوطة بباحثي الجامعة.

23 مُخرَج نتائج البحث عن «latency»

مقالمفتوح (مستودع)20266استشهاد· Semantic Scholar

Blockchain Consensus Mechanisms and Enhancement Techniques for Federated Learning-Based Intrusion Detection Systems in IoT Smart Homes

Journal of Reliable and Secure Computing · مجلد 2 (1) · 1-26

The rapid proliferation of smart home IoT devices has introduced unprecedented cybersecurity vulnerabilities, necessitating scalable and privacy-preserving intrusion detection systems (IDS). Federated Learning (FL) offers a promising decentralized approach by training models locally without sharing raw data, but it remains susceptible to poisoning attacks and relies on a vulnerable central aggregator. This paper presents a novel blockchain-enhanced FL framework tailored for smart home IDS, integrating multiple consensus mechanisms—Proof-of-Stake (PoS), Practical Byzantine Fault Tolerance (PBFT), and Proof-of-Authority (PoA)—for the first time in this context. Our approach uniquely combines differential privacy (DP) and secure aggregation (SA) within a blockchain-managed workflow to mitigate gradient inversion and membership inference attacks while ensuring tamper-resistant, decentralized trust. Experimental evaluation using the N-BaIoT dataset demonstrates that the proposed system achieves up to 88.3% detection accuracy with manageable latency (~200 ms/round) and formal privacy guarantees ($\varepsilon$=1.0 DP). The framework introduces 52.8% system overhead compared to vanilla FL—a reasonable trade-off for enhanced security and privacy. This work establishes a robust, transparent, and scalable security infrastructure for smart homes, effectively addressing the limitations of both centralized and conventional FL-based IDS.

blockchainfederated learningintrusion detection systemshome automation
مقالوصول مفتوح20261استشهاد· Semantic Scholar

GLP-1 receptor agonists as potential disease-modifying agents in Parkinson’s and Alzheimer’s disease: mechanisms, clinical trial evidence, and the neuroprotection horizon

Frontiers in Aging Neuroscience · مجلد 18

Glucagon-like peptide-1 receptor agonists (GLP-1 RAs), originally developed as antidiabetic agents, have emerged as candidate disease-modifying therapies for Parkinson’s disease (PD) and Alzheimer’s disease (AD), reflecting the widespread expression of GLP-1 receptors across neurons, glia, and the cerebral vasculature. This narrative review synthesizes mechanistic, clinical trial, and biomarker evidence for GLP-1 RAs in PD and AD, based on a literature search of PubMed, Embase, Scopus, and Web of Science, with ClinicalTrials.gov searched separately for trial protocols and results, through May 2026. Preclinical data implicate GLP-1 receptor agonism in anti-neuroinflammatory signaling, mitochondrial preservation, autophagy and proteostasis enhancement, anti-apoptotic effects, synaptic plasticity, cerebrovascular protection, and glymphatic clearance. Clinical evidence in PD is mixed and agent- and formulation-dependent: the phase II Exenatide-PD trial reported a motor benefit that persisted after washout (∼3.5-point between-group difference in MDS-UPDRS Part III), and the phase II LIXIPARK trial (lixisenatide) reported a significant 3.08-point between-group difference (95% CI 0.86–5.30; p = 0.007) favoring lixisenatide, whereas the larger, longer phase III Exenatide-PD3 trial, using an extended-release weekly formulation, found no significant effect on the same endpoint (adjusted coefficient 0.92; 95% CI −1.56 to 3.39; p = 0.47); oral semaglutide is under investigation in the ongoing phase II MOST-ABLE trial. In AD, the phase IIb liraglutide (ELAD) trial did not achieve statistical benefit on either its primary imaging endpoint (cerebral glucose metabolic rate; p = 0.14) or on most secondary cognitive measures, and the phase III semaglutide trials EVOKE and EVOKE+ did not meet their primary CDR-SB endpoint (estimated difference −0.08, 95% CI −0.35 to 0.20, p = 0.57 in EVOKE; 0.10, 95% CI −0.17 to 0.38, p = 0.46 in EVOKE+), despite biomarker signals including reductions in cerebrospinal fluid tau species and inflammatory markers. Comparative pharmacology reveals substantial heterogeneity in central nervous system penetration, receptor engagement, and systemic bioavailability across exenatide, liraglutide, semaglutide, and the imbalanced GLP-1/GIP co-agonist tirzepatide, complicating cross-agent extrapolation. Persistent challenges include separating direct neuroprotection from indirect metabolic and cardiovascular benefit, limited characterization of brain drug exposure, trial durations that may be short relative to the expected latency of a disease-modifying effect, and the absence of validated response biomarkers. We conclude that although the mechanistic and epidemiological rationale for GLP-1 RAs in neurodegeneration remains biologically plausible, current trial evidence does not yet support their use outside clinical trials, irrespective of comorbid diabetes status; future studies should prioritize earlier intervention, biomarker-guided patient selection, adequately powered subgroup analyses, and brain-penetrant formulations.

GLP-1 receptor agonistsParkinson's diseaseAlzheimer's diseasedisease-modifying therapy
مقالوصول مفتوح20261استشهاد· Semantic Scholar

L-Serine Attenuates Metabolic and Behavioural Features of Diabetic Neuropathy with Dose-Dependent Central Proteomic Correlates in a Rat Model

Biomolecules · مجلد 16 (6) · 881-881

Diabetic neuropathy (DN) is a multifactorial complication of diabetes mellitus driven by chronic hyperglycemia, insulin resistance, and disturbed metabolic homeostasis, leading to progressive injury of both the peripheral and central nervous systems. This study investigated whether L-serine supplementation could attenuate DN through dose-dependent metabolic and neuroprotective mechanisms in a high-fat diet (HFD) plus streptozotocin (STZ)-induced diabetic rat model. Male Wistar rats (n = 8 per group) were allocated to five groups: normal control (NC), diabetic control (DC), pioglitazone (PIO; 1.5 mg/kg/day), low-dose L-serine (S1; 200 mg/kg/day), and high-dose L-serine (S2; 400 mg/kg/day). After 60 days of oral gavage, behavioural testing, glucose and insulin profiling, HOMA-IR calculation, brain histopathology, nerve growth factor (NGF) immunohistochemistry, and LC–MS/MS-based proteomic analysis of cerebral tissue were performed. Diabetic rats exhibited marked hyperglycaemia (355.33 ± 4.72 mg/dL), hyperinsulinaemia, severe insulin resistance (HOMA-IR 16.8 ± 3.2; a 14-fold increase), impaired thermal nociception, motor dysfunction, and pronounced neuronal degeneration. L-serine supplementation significantly improved metabolic status: S1 reduced HOMA-IR by 77.4% and S2 by 87.5% relative to diabetic controls (p < 0.001). High-dose L-serine produced greater improvements in thermal sensitivity, motor coordination (rotarod latency 26.67 ± 1.52 s vs. 16.1 ± 0.85 s in DC; p < 0.05), and NGF expression (8.6-fold increase vs. DC). Histopathology confirmed attenuation of neuronal injury and gliosis in both treatment groups. Exploratory, group-level proteomic profiling identified dose-specific molecular signatures: S1 was predominantly associated with carbohydrate, lipid, and biosynthetic pathways, whereas S2 was associated with synaptic, neurotransmission-related, and proteostasis pathways. Within the constraints of an exploratory design—group-level pooled proteomics, analysis of cerebral rather than peripheral-nerve tissue, and only two doses—these findings indicate that L-serine attenuates the metabolic and behavioural features of experimental diabetic neuropathy and generates the testable hypothesis of dose-dependent neuro-metabolic remodelling. The proteomic signatures are hypothesis-generating and require orthogonal validation before any mechanistic or translational inference can be drawn.

diabetic neuropathyinsulin resistancehyperglycemiastreptozotocin-induced diabetes
مقالوصول مفتوح2026

Post quantum federated authentication framework for Industrial Internet of Things using FALCON threshold signatures and zero knowledge verification

Scientific Reports · مجلد 16 (1)

Abstract Distributed authentication techniques enable edge device trust in smart manufacturing and energy infrastructure Industrial Internet of Things contexts. Existing blockchain-based authentication schemes mostly use the elliptic curve digital signature algorithm, which can be exploited by quantum adversaries using harvest-now, decrypt-later attacks to record authenticated communications for cryptanalysis. CIPHER-QNL, a post-quantum federated authentication framework, integrates three complementary mechanisms: (1) FALCON threshold signature aggregation with federated polynomial key sharding over NTRU lattice rings for distributed multi-party authentication without centralized private-key exposure; and (2) zk-STARK-based privacy-preserving verification for blockchain consensus authentication proof validation without credential disclosure. Through threshold confidentiality, reduction-based reasoning, and computational complexity analysis, the proposed framework’s security is assessed under Module-SIS and NTRU lattice hardness assumptions. Controlled harvest now, decrypt adversarial authentication scenarios are used to evaluate TON-IoT communication performance. Scalable, privacy-preserving, post-quantum authentication for distributed Industrial Internet of Things environments is shown by 99.1% authentication integrity, 98.7% threshold signature aggregation latency reduction, and 0.29% false rejection rate.

federated authenticationIndustrial Internet of ThingsNTRU latticeblockchain consensus
مقالوصول مفتوح2026

Evaluating the efficacy and safety of melatonin for sleep onset insomnia in children aged 6–12: a systematic review and meta-analysis

BMC Pediatrics

Abstract Background Melatonin is an endogenous hormone that regulates the body’s sleep-wake cycles. Due to several clinical trials, it is currently used as an exogenous supplement in pediatric patients who suffer from sleep-onset insomnia (SOI). Consequently, this systematic review and meta-analysis aimed to assess the evidence for the clinical efficacy of melatonin for SOI in children aged 6–12. Methods This systematic review and meta-analysis evaluated the efficacy and safety of Melatonin for sleep-onset insomnia in children aged 6–12 by conducting literature searches in PubMed (97), Google Scholar (111), OVID (33), and Web of Science (156) databases. We performed statistical tests using RevMan for meta-analysis. Heterogeneity was evaluated using the I2 statistic. To maintain the validity of the studies, each included study was assessed by the Cochrane Collaboration Risk of Bias (ROB) tool. The outcomes investigated were sleep onset time (SOT), sleep onset latency (SOL), total sleep time (TST), all-cause dropout rates, and adverse-event dropout rates. Results Three hundred ninety-eight records were identified, and 10 randomized clinical trials met the inclusion criteria. The results demonstrated that melatonin treatment group was associated with an earlier sleep onset time compared with placebo with a mean difference (MD) of -0.48 h (approximately 29 min earlier) (95% confidence interval [CI]: -0.93 to -0.02 h, p = 0.04). The heterogeneity between studies was moderate (I2 = 63%). On the other hand, it was noted that there has been noticed there was a remarkable reduction in sleep onset latency with melatonin compared to placebo, with an MD of -0.38 (95% CI: -0.57 to -0.20, p < 0.0001), with high heterogeneity (I2 = 82%). Conclusion Our study confirmed that melatonin has a marked effect regarding Sleep-onset insomnia in childhood. Therefore, we found there was a statistical and clinical improvement in sleep parameters such as sleep onset time (SOT) and total sleep time (TST) which demonstrated the safety and efficacy of melatonin. However, long-term efficacy and safety need to be addressed, especially in the pediatric population.

melatoninsleep onset insomniapediatric insomniachildren
مقالوصول مفتوح2026

Federated Learning in Smart Home Intrusion Detection: Securing the Learning Process with Blockchain

Network and Communication Technologies · مجلد 10 (1) · 1-1

The rapid expansion of Internet of Things (IoT) devices has fundamentally reshaped traditional homes into highly interconnected smart environments, driving unprecedented convenience while simultaneously exposing critical cybersecurity vulnerabilities. Conventional centralized Intrusion Detection Systems (IDS) are increasingly inadequate for smart homes, owing to inherent privacy issues, latency, and susceptibility to single points of failure. Federated Learning (FL) offers a promising, privacy-preserving paradigm by enabling collaborative model training without the exchange of raw user data; however, FL remains vulnerable to model poisoning and integrity attacks. This comprehensive review systematically examines the integration of blockchain technology as a means to secure FL-based IDS in smart home contexts. We critically evaluate diverse blockchain frameworks, consensus protocols, and enhancement strategies that underpin the development of trustworthy, transparent, and resilient security architectures. Specifically, the review addresses two core research questions: (1) In what ways are blockchain frameworks and consensus mechanisms leveraged to secure FL-based IDS? and (2) What enhancement techniques and hybrid models are implemented to optimize the performance and efficiency of these integrated systems? Our synthesis reveals that permissioned blockchains—particularly those employing Proof of Authority (PoA) and Practical Byzantine Fault Tolerance (PBFT) consensus mechanisms—when combined with edge computing and lightweight architectural designs, deliver robust security while meeting the resource constraints characteristic of IoT devices. This technological synergy not only strengthens the resilience of the FL process but also advances the development of next-generation, secure smart home ecosystems.

federated learningintrusion detection systemshome automationblockchain
مقالوصول مغلق202512استشهاد· Semantic Scholar

Consumer Technology in Task Offloading and Edge Resource Allocation: AIoT and Edge Computing for Next-Generation Communication

IEEE Transactions on Consumer Electronics · مجلد 71 (2) · 5356-5365

Artificial Intelligence of Things (AIoT) edge computing has emerged as a critical enabler for consumer technology, easing the load on distribution grid networks through enhanced data transmission and processing capabilities. The Internet of Things (IoT), a modern network paradigm, connects devices using sensors and communication mediums to enable seamless information exchange. However, the limited computational capacity of edge nodes poses challenges in optimizing AIoT edge resources compared to cloud computing. To address this, a cloud-edge three-layer framework for task offloading and edge resource allocation is proposed in the context of consumer technology and distribution grids. This model incorporates random tasks, limited resources, unequal processing power, and high latency requirements. It features two key phases: a resource auction using a multi-round iterative process and compute offloading managed by a Deep Reinforcement Learning (DRL) approach. Enhanced algorithms such as Double DQN and Dueling DQN are integrated into the job offloading process to improve performance. Simulations validate the convergence of the task offloading algorithm and demonstrate that the proposed methods significantly enhance computational efficiency and resource utilization for edge nodes. These advancements offer promising solutions for the dynamic needs of consumer technology and future communication networks.

task offloadingedge resource allocationAIoTedge computing
مقالوصول مغلق20258استشهاد· Semantic Scholar

Synergistic Integration of 5G-Enabled Cloud Native Infrastructures With Advanced Technologies for Urban Safety Enhancement

IEEE Transactions on Consumer Electronics · مجلد 71 (2) · 5321-5334

Urban safety remains an important concern in modern cities, which makes it necessary for advanced approaches to address the progressing challenge such as fire risk assessment and security enhancement. This study explores the important integration of 5G-enabled cloud-native infrastructures with the Internet of Things (IoT), and Artificial Intelligence (AI) algorithm for empowering urban safety. Kubernetes is used as an essential component of the Cloud Native Computing Foundation (CNCF) ecosystem, for managing scalable and resilient infrastructures. This integration of 5G-enabled systems to cloud-native infrastructures proposes an efficient solution that offers high-speed connectivity, low latency, and the scalability required for real-time data processing and communication. In the proposed work, IoT devices are strategically deployed across urban areas to achieve comprehensive coverage and facilitate real-time data collection and monitoring, ideally integrated with Kubernetes-managed clusters to ensure data transmission and processing. Machine Learning (ML) and Deep Learning (DL) based model is trained on the collected data from the field, using Kubernetes for scalable and automated deployment providing real-time data analysis, accurate prediction, and decision-making. The proposed 5G integrated framework provides proactive risk management and enhanced emergency response strategies. The integration of 5G-enabled systems led to a significant reduction in latency, typically to 20 milliseconds, enhancing real-time performance and decision-making processes. This study introduces a framework designed to reduce latency to 20 ms and improve data transmission rates by 25%. Real-world applications, including fire detection and traffic management, demonstrated the systems effectiveness, achieving sensitivity and recall rates of 97% and 96%, respectively. These results underscore the potential of the proposed framework to enhance urban safety while addressing scalability and integration challenges for future implementations.

urban safety5Gcloud-native infrastructureKubernetes
مقالوصول مفتوح20257استشهاد· Semantic Scholar

Optimization of 6G resource allocation using CyberTwin function-based service enhancement scheme

EURASIP Journal on Wireless Communications and Networking · مجلد 2025 (1)

The most innovative Service-Optimized Logging for Resource Allocation (SOL-RA) is in situations that support 6G connection. The CyberTwin architecture optimizes the quality of service provided to end users in 6G communications by using the dependability of terahertz connections and interactions of a machine-type nature. Elastically sharing elastic resources among users is made possible by the proposed resource allocation strategy, which makes use of proprietary logger functions. This ensures that efficient allocation is achieved without overlapping or lengthy wait periods. Within the framework of SOL-RA, a categorization mechanism is implemented for dense requests, which differentiates them as either stationary or priority services. Resource allocations are dynamically done based on this categorization, which enhances the organization's responsiveness to different needs. Through a tree classifier learning mechanism, CyberTwin logs play an essential part in the processing of requests and the preparation of resources. This helps to ensure that resources are distributed without inefficiency. Requests that are generating a backlog are identified and processed in parallel by the system, which significantly reduces the amount of time that is wasted waiting. In order to guarantee a specialized distribution for the categorized outputs, resource allocations are directed by CyberTwin data logs. An examination of the performance of the SOL-RA scheme takes into account important metrics such service latency, service backlog, resource usage, and request-to-response ratio. This research offers insights into the efficacy of the scheme in maximizing service quality and resource consumption in 6G settings.

terahertz communicationmachine-type communicationclassification treesservice latency
مقالوصول مغلق20256استشهاد· Semantic Scholar

Certificate-Less Healthcare Signature Scheme for Secure Consumer Technology-Centric Wireless Medical Sensor Devices

IEEE Transactions on Consumer Electronics · مجلد 71 (2) · 5015-5024

The application of Consumer-Centric Wireless Medical Sensor Devices in the medical field has brought great convenience to doctors and patients. However, the transmission process may compromise patient privacy, making the authenticity and integrity of medical data a significant challenge in the healthcare industry. To address this issue, a certificate-less Healthcare Signature scheme is proposed to protect patient privacy. However, most schemes are unable to resist fully selective cipher text attacks and suffer from key exposure problems. To mitigate these issues, a scheme is proposed to resist fully selective attacks in real-time processing of Consumer-Centric Wireless Medical Sensor Devices with high latency issues, while utilizing parallel key isolation methods to address key exposure problems. The scheme’s enforceability is proven based on the random oracle model and the computational Diffie-Hellman assumption, and its resistance to fully selective key attacks is proven based on hash-based collision resistance. It is shown that this plan works well for wireless sensor networks in the medical field. Sensor nodes have limited resources, and sending vast volumes of patient medical data online significantly raises processing and communication costs. The low processing power of edge devices limits the effectiveness and performance of medical services. Efficiency analysis using the MIRACL library demonstrates that the proposed scheme outperforms other relevant schemes in terms of efficiency at each stage, while also having lower communication overhead.

wireless medical sensor networkspatient privacykey exposurecomputational Diffie-Hellman assumption
مقالوصول مفتوح20255استشهاد· Semantic Scholar

Neuroprotective effect of silymarin-loaded nanoliposomes against monosodium glutamate-induced cerebellar motor deficit and Purkinje cell damage in experimental rats via PI3K/AKT pathway activation

Frontiers in Molecular Biosciences · مجلد 12 · 1621240-1621240

Background and aim: This study investigated the ameliorative effect of Silymarin-nanoliposome (SLNPs) against monosodium glutamate (MSG)-induced cerebellar toxicity, illuminating its impact on motor coordination. Methods: Forty male Wistar albino rats were divided into four groups. Group I (control group): rats received 2 mL of 0.9% NaCl solution; Group II (SLNPs group): rats received SLNPs with a dose of 500 μg/kg bw orally; Group III (MSG group): rats received 3.5 mg/kg bw of MSG intraperitoneally; and Group IV: rats received combined treatment of MSG + SLNPs for ten consecutive days. Results: MSG-induced cerebellar motor incoordination is represented by increased falls in rats and decreased tow latency spent on the rotarod test. Moreover, MSG altered cerebellar histological structure and significantly (p < 0.05) decreased antioxidant system activity and protein levels of phosphorylated phosphoinositide 3-kinases (p-PI3K), phosphorylated protein kinase B (p-AKT), and brain-derived neurotrophic factor (BDNF). Additionally, there is a decrease in the immunoexpression of nuclear factor erythroid 2-related factor 2 (Nrf2) and gene expression of heme oxygenase-1 (HO-1), tropomyosin receptor kinase B (TrkB), and anti-apoptotic B-cell lymphoma-2 (Bcl-2), alongside an increase in the sera and protein levels of proinflammatory cytokines tumor necrosis factor-alpha (TNF-α), interleukin-6 (IL-6), interleukin-1 beta (IL-1β), immunoexpression of glial fibrillary acidic protein (GFAP), nuclear factor kabba beta (NF-κB), caspase-3, and gene expression of proapoptotic Bax. However, SLNPs prevented MSG-induced cerebellar toxicity, improving motor coordination and morphological structure by enhancing antioxidant, anti-inflammatory, and anti-apoptotic activity by stimulating the PI3K/AKT pathway. Conclusion: The current study indicated that SLNP administration protects against MSG-induced cerebellar damage, preventing cerebellar oxidative stress, inflammation, and apoptosis, opening the door to examining its clinical use in preventing MSG-induced cerebellar motor incoordination.

silymarinnanoliposomesmonosodium glutamatecerebellar toxicity
مقالوصول مغلق20253استشهاد· Semantic Scholar

An IoT-Enabled Cyber-Physical System for Early Detection of Obsessive-Compulsive Disorder Using Neurosymbolic AI and Hybrid RBF-Competitive Neural Networks

IEEE Transactions on Consumer Electronics · مجلد 71 (4) · 12029-12036

Smart healthcare is advancing through the integration of Cyber-Physical Systems (CPS), Internet of Things (IoT), and Artificial Intelligence (AI). This work presents an IoT-enabled Healthcare CPS (H-CPS) for early detection and classification of Obsessive-Compulsive Disorder (OCD). The proposed system employs a hybrid machine learning framework that combines Radial Basis Function (RBF) Neural Networks, Competitive Neural Networks, and Neuro-Symbolic AI within a CPS architecture to enable intelligent coordination across healthcare infrastructure. The H-CPS leverages IoT devices, LoRa-based communication, and cloud computing to implement an OCD detection system. Oxidative Stress Biomarkers (OSBs) serve as predictive indicators, distinguishing patients with OCD (POCD), genetically predisposed first-degree relatives (GFDR), and healthy controls (HC). The model comprises a competitive input layer, an RBF-based nonlinear transformation layer, and a competitive clustering layer, with Neuro-Symbolic AI applied for cluster labeling. Experimental evaluation on two independent datasets achieved high prediction accuracies (0.9492 and 0.9317), outperforming state-of-the-art clustering methods. A four-layer IoT prototype further demonstrated real-time feasibility with 1–2 second latency, confirming scalability for healthcare deployment.

obsessive-compulsive disorderearly detectionneuro-symbolic AIradial basis function neural network
مقالمفتوح (مستودع)20253استشهاد· Semantic Scholar

Digital Twin Enabled 6G MEC Networks: Computational Energy Efficiency for Consumer IIoT in Industry 5.0

IEEE Transactions on Consumer Electronics · مجلد 71 (3) · 7874-7881

The integration of digital twins (DTs) with mobile edge computing (MEC) offers transformative potential for computational energy efficiency in Industry 5.0-driven 6G networks. However, existing frameworks often lack proactive resource allocation using DTs, relying instead on reactive adjustments. This paper proposes a novel DT-MEC framework that uniquely employs virtual DT replicas of MEC servers to predict computational states (e.g., server workloads, latency trends) in real time, enabling dynamic optimization of task offloading for large-scale Industrial IoT (IIoT) networks. Unlike prior DT-MEC integrations that focus on static resource allocation, our approach leverages predictive DT modeling to preemptively adjust resources, addressing a critical gap in the literature. To maximize energy efficiency, we formulate a mixed-integer non-linear problem (MINLP) that jointly optimizes local computation, transmission power, DT-edge association, and task execution time. The problem is transformed into a tractable form using piecewise linearization to reduce computational complexity and solved via an adaptive iterative algorithm that alternates between resource allocation and DT state updates. This method ensures a balance between solution accuracy and computational overhead, a key innovation compared to conventional optimization techniques. Simulations demonstrate that our framework achieves 40% higher energy efficiency, 50% lower outage probability, and 95% task completion rates compared to state-of-the-art benchmarks. Specific improvements include a 6.63% gain over binary offloading and 150.08% over edge-only schemes, validating its practicality for Industry 5.0 deployments. These results highlight our contributions: (1) a proactive DT-driven resource allocation mechanism, (2) a linearization technique for non-convex MINLP problems, and (3) an adaptive iterative solver that outperforms existing approaches in dynamic IIoT environments.

digital twinmobile edge computing6Gtask offloading
مقالوصول مغلق20252استشهاد· Semantic Scholar

Blockchain‐Based Anomaly Detection in Vehicular Ad‐Hoc Networks Using Deep Reinforcement Learning

Transactions on Emerging Telecommunications Technologies · مجلد 36 (10)

ABSTRACT Utilizing blockchain in vehicular ad‐hoc networks (VANETs) can proficiently resolve concerns pertaining to data security and privacy. The limited throughput of blockchain obstructs its extensive implementation in VANETs. Current studies on enhancing blockchain throughput frequently encounter the issue of action space proliferation, leading to inadequate scalability. This research presents a strategy for optimizing blockchain performance on VANETs using deep reinforcement learning (DRL). The suggested method enhances blockchain throughput by selecting block producers and consensus methods, and by modifying block size and intervals, while maintaining decentralization, low latency, and security in VANET‐based blockchain systems. Furthermore, to augment network security, an anomaly detection mechanism is incorporated, utilizing machine learning techniques to identify and mitigate potential attacks aimed at VANETs. The proposed system enhances throughput and fortifies resilience against malicious operations by identifying anomalous patterns in network behavior. The method uses the BDQ framework to meticulously partition the action space, tackling the action space explosion issue that occurs with conventional DRL techniques in blockchain throughput optimization. Simulation results indicate that the suggested solution significantly improves the throughput and security of the VANET‐based blockchain system.

vehicular ad hoc networksblockchainanomaly detectiondeep reinforcement learning
مقالوصول مغلق20251استشهاد· Semantic Scholar

Optimized Deep Learning for Intrusion Detection in Federated IoT Environments

Journal of Circuits Systems and Computers · مجلد 35 (07)

Current developments on the Internet of Things (IoT) have completely changed the landscape of Consumer Electronics (CE), enabling next-generation gadgets to be highly intelligent, networked and capable of utilizing large models. In addition to improving data accessibility, this improved connectivity between sensors, actuators and appliances allows autonomous control inside CE networks. Although deep learning models are highly effective in analyzing large amounts of data, controlling the intricacy of deep learning-based intrusion detection in low-latency IoT networks continues to be a formidable task. This paper presents a deep learning-based intrusion detection technique inspired by federated learning (FL), specifically designed for SDN-enabled CE networks. The application of the approach involves stringent training and testing protocols. In order to improve performance and handle the very complicated training data, the Pearson correlation coefficient (PCC) approach of feature selection (FS) is used in this work. Based on the UNSW-NB15 attack detection dataset, the results show that this approach performs better than other current security solutions, making it a promising option for next-generation smart CE networks. Comprehensive experimental evaluations demonstrated the value of the suggested intrusion detection system (IDS), which demonstrated exceptional intrusion detection accuracy in every domain under investigation.

intrusion detectionfederated learningInternet of Things securitysmart home networks