Search Results (3,552)

The increasing complexity and scale of cyber threats have pushed Cyber Threat Intelligence (CTI) beyond the capabilities of traditional rule-based systems. This article explores how Artificial Intelligence (AI), particularly Machine Learning (ML), Deep Learning (DL), Natural Language Processing (NLP), and graph-based analytics, is reshaping the CTI landscape. By automating threat data processing, enhancing attribution, and enabling predictive capabilities, AI is transforming CTI into a proactive and scalable discipline. By analysing CTI architectures, real-world use cases, platform comparisons, and current limitations, this study highlights the emerging opportunities and challenges at the intersection of cybersecurity and AI. This analysis concludes that the future of CTI lies in hybrid systems that seamlessly combine human expertise with intelligent automation. Full article

Acknowledging recent breakthroughs in the context of deep bio-inspired neural networks, several architectural deep network options have been deployed to create intelligent systems. The foundations of convolutional neural networks are influenced by hierarchical processing in the visual cortex. The graph neural networks mimic the communication of biological neurons. Considering these two computation methods, a novel deep ensemble network is used to propose a bio-inspired deep graph network for creating an intelligent supply chain model. An automated smart supply chain helps to create a more agile, resilient and sustainable system. Improving the sustainability of the network plays a key role in the efficiency of the supply chain’s performance. The proposed bio-inspired Chebyshev ensemble graph network (Ch-EGN) is hybrid learning for creating an intelligent supply chain. The functionality of the proposed deep network is assessed on two different databases including SupplyGraph and DataCo for risk administration, enhancing supply chain sustainability, identifying hidden risks and increasing the supply chain’s transparency. An average accuracy of 98.95% is obtained using the proposed network for automatic delivery status prediction. The performance metrics regarding multi-class categorization scenarios of the intelligent supply chain confirm the efficiency of the proposed bio-inspired approach for sustainability and risk management. Full article

With the rapid advancement of Generative Adversarial Networks (GANs), diffusion models, and other deep generative techniques, AI-generated images have achieved unprecedented levels of visual realism, posing severe challenges to the authenticity, security, and credibility of digital content. This paper proposes a novel hybrid transformer model that integrates spatial and frequency domains. It leverages CLIP to extract semantic inconsistencies in the image’s spatial domain while employing wavelet transforms to capture multi-scale frequency anomalies in AI-generated images. After cross-domain feature fusion, global modeling is performed within the Swin-Transformer architecture, enabling robust authenticity detection of AI-generated images. Extensive experiments demonstrate that our detector maintains high accuracy across diverse datasets. Full article

Advancements in Industry 4.0 technologies, which combine big data analytics, robotics, and intelligent decision systems to enable new ways to increase automation in the industrial sector, have undergone significant transformations. In this research, a Hybrid Attention-Gated Recurrent Unit (At-GRU) model, combined with Sand Cat Optimization (SCO), is proposed to enhance fault identification and predictive maintenance capabilities. The model utilized multivariate sensor data from cyber-physical and IoT-enabled robotic platforms to learn operational patterns and predict failures with enhanced reliability. The At-GRU provides deeper temporal feature extraction, thereby improving classification performance. The robustness of the proposed model is validated through analysis of a benchmark dataset for industrial robots, and the results demonstrate that the proposed model exhibits impressive predictive capacity, surpassing other prediction methods and predictive maintenance approaches. Additionally, the performance evaluation indicates a lower computational cost due to the lightweight gating architecture of GRU, combined with attention. The robotic motion is further optimized by the SCO algorithm, which reduces energy usage, execution delay, and trajectory deviations while ensuring smooth operation. Overall, the proposed work offers an intelligent and scalable solution for next-generation industrial automation systems. Furthermore, the proposed model demonstrates the real-world applicability and significant benefits of incorporating hybrid artificial intelligence models into real-time robot control applications for smart manufacturing environments. Full article

Radar image extrapolation serves as a fundamental methodology in meteorological forecasting, facilitating precise short-term weather prediction through spatiotemporal sequence analysis. Conventional approaches remain constrained by progressive image degradation and artifacts, substantially limiting operational forecasting reliability. This research introduces E-HEOA—an enhanced deep learning architecture with integrated hyperparameter optimization. Our framework incorporates two fundamental innovations: (a) a hybrid metaheuristic optimizer merging a Gaussian-mutated ESOA and Cauchy-mutated HEOA for autonomous learning rate and dropout optimization and (b) embedded ConvLSTM2D modules for enhanced spatiotemporal feature preservation. Experimental validation on 170,000 radar echo samples demonstrates superior performance, demonstrating considerable enhancement in almost all aspects relative to the baseline model while establishing new state-of-the-art benchmarks in prediction fidelity, convergence efficiency, and structural similarity metrics. Full article

Fog water collectors (FWCs) present a sustainable solution for arid regions where fog is a primary water source. To improve their efficiency, we developed a durable and high-performance mesh composed of electrospun hydrophobic thermoplastic polyurethane (TPU) fibers combined with hydrophilic cellulose acetate (CA) microbeads. This hybrid design represents a novel biomimetic strategy, mimicking natural fog-harvesting mechanisms by optimizing wetting and drainage. Despite the significant reduction in average fiber diameter, the TPU-CA mesh maintained mechanical strength close to 1 MPa, comparable to pristine TPU. The introduction of hydrophilic domains into a hydrophobic fibrous network is a unique architectural approach that enhanced fog collection performance, achieving a high water harvesting rate of 127 ± 12 mg·cm⁻²·h⁻¹. Remarkably, although the mesh remained predominantly hydrophobic, droplets shed completely from its vertical surface, exhibiting near-zero contact angle hysteresis. This synergistic wetting concept enables performance unattainable with conventional single-wettability meshes. Compared to single-material meshes, the TPU-CA hybrid showed nearly double the water collection efficiency. The innovative interplay between surface chemistry, microscale heterogeneity, and mechanical robustness is key to maximizing water capture and transport, offering a promising path for scalable, efficient FWCs in poor water-stressed regions. Full article

In this study, we emphasize that the maximum sum rate can be achieved through AI-based subchannel allocation, while taking into account all users’ quality of service (QoS) requirements in data rates for hybrid beamforming systems. We assume a limited number of radio frequency (RF) chains in practical hybrid beamforming architectures. This constraint makes subchannel allocation a critical aspect of hybrid beamforming in massive multiple-input multiple-output (MIMO) systems with orthogonal frequency division multiple access (MIMO-OFDMA), as it enables the system to serve more users within a single time slot. Unlike conventional subcarrier allocation methods, we employ a deep reinforcement learning (DRL)-based algorithm to address real-time decision-making challenges. Specifically, we propose a dueling double deep Q-network (Dueling-DDQN) to implement dynamic subchannel allocation. Simulation results demonstrate that the performance of the proposed algorithm gradually approaches that of the greedy method. Furthermore, both the average sum rate and the average spectral efficiency per user improve with a reasonable variation in outage probability. Full article

In modern marine seismic exploration, ocean bottom node (OBN) acquisition systems are increasingly valued for their flexibility in deep-water complex structural surveys. However, the high operational costs associated with OBN systems often lead to spatially sparse sampling, which adversely affects the fidelity of wavefield reconstruction. To overcome these limitations, hybrid deep learning frameworks that integrate physics-driven and data-driven approaches show significant potential for interpolating OBN four-component (4C) seismic data. The proposed frequency-domain residual-attention U-Net (ResAtt-Unet) architecture systematically exploits the inherent physical correlations among 4C data to improve interpolation performance. Specifically, an innovative dual-branch dual-channel network topology is designed to process OBN 4C data by grouping them into complementary P–Z (hydrophone–vertical geophone) and X–Y (horizontal geophone) pairs. A synchronized joint training strategy is employed to optimize parameters across both branches. Comprehensive evaluations demonstrate that the ResAtt-Unet achieves superior performance in component-wise interpolation, particularly in preserving signal fidelity and maintaining frequency-domain characteristics across all seismic components. Future work should focus on expanding the training dataset to include diverse geological scenarios and incorporating domain-specific physical constraints to improve model generalizability. These advancements will support robust seismic interpretation in challenging ocean-bottom environments characterized by complex velocity variations and irregular illumination. Full article

The proliferation of data-intensive IoT applications has created unprecedented demand for wireless spectrum, necessitating more efficient bandwidth management. Spectrum sensing allows unlicensed secondary users to dynamically access idle channels assigned to primary users. However, traditional sensing techniques are hindered by their sensitivity to noise and reliance on prior knowledge of primary user signals. This limitation has propelled research into machine learning (ML) and deep learning (DL) solutions, which operate without such constraints. This study presents a comprehensive performance assessment of prominent ML models: random forest (RF), K-nearest neighbor (KNN), and support vector machine (SVM) against DL architectures, namely a convolutional neural network (CNN) and an Autoencoder. Evaluated using a robust suite of metrics (probability of detection, false alarm, missed detection, accuracy, and F1-score), the results reveal the clear and consistent superiority of RF. Notably, RF achieved a probability of detection of 95.7%, accuracy of 97.17%, and an F1-score of 96.93%, while maintaining excellent performance in low signal-to-noise ratio (SNR) conditions, even surpassing existing hybrid DL models. These findings underscore RF’s exceptional noise resilience and establish it as an ideal, high-performance candidate for practical spectrum sensing in wireless networks. Full article

Modern passport systems face significant challenges in secure data sharing, real-time verification, and user-controlled authorization, particularly in cross-border scenarios. Existing digital passport solutions, often built on permissioned blockchains, suffer from limited transparency, scalability, and high operational costs. This paper proposes a decentralized passport management system based on an Ethereum Layer 2 architecture that combines global governance with high-throughput and cost-efficient passport operations. The system adopts a hybrid design in which a Global Passport Registry smart contract is deployed on the Ethereum mainnet for cross-country coordination, while passport issuance, access control, and identity management are handled on Layer 2 networks through country-operated Passport Managers and user-specific Personal Passport smart contracts. Extensive performance evaluations show that Ethereum Layer 1 throughput saturates at approximately 40–50 transactions per second (TPS), whereas the proposed Layer 2 deployment consistently exceeds 150 TPS and reaches up to 300 TPS under higher-performance environments, significantly surpassing the estimated system requirement of 70 TPS. These improvements result in faster response times, reduced congestion, and substantially lower transaction costs, demonstrating that public Ethereum Layer 2 infrastructures can effectively support a scalable, self-sovereign, privacy-preserving, and globally verifiable digital passport system suitable for real-world deployment. Full article

Metal–organic frameworks (MOFs) are among the most structurally diverse classes of crystalline nanomaterials, offering exceptional tunability, porosity, and chemical modularity. These characteristics have positioned MOFs as promising platforms for nanomedicine, bioimaging, and integrated nanotheranostic applications. However, the rational design of MOFs that satisfy stringent biomedical requirements, including high drug loading capacity, controlled and stimuli responsive release, selective targeting, physiological stability, biodegradability, and multimodal imaging capability, remains challenging due to the vast combinatorial design space and the complex interplay between physicochemical properties and biological responses. The objective of this review is to critically examine recent advances in artificial intelligence approaches based on Transformer architectures for the design and optimization of MOFs aimed at next-generation nanotheranostics. In contrast to prior reviews that broadly survey machine learning methods for MOF research, this article focuses specifically on Transformer-based models and their ability to capture long-range, hierarchical, and multiscale relationships governing MOF structure, chemistry, and functional behavior. We review state-of-the-art models, including MOFormer, MOFNet, MOFTransformer, and Uni MOF, and discuss graph-based and sequence-based representations used to encode MOF topology and composition. This review highlights how Transformer-based models enable predictive assessment of properties directly relevant to nanotheranostic performance, such as adsorption energetics, framework stability, diffusion pathways, pore accessibility, and surface functionality. By explicitly linking these predictive capabilities to drug delivery efficiency, imaging performance, targeted therapeutic action, and combined diagnostic and therapeutic applications, this work delineates the specific contribution of Transformer-based artificial intelligence to biomedical translation. Finally, we discuss emerging opportunities and remaining challenges, including generative Transformer models for inverse MOF design, self-supervised learning on hybrid experimental and computational datasets, and integration with autonomous synthesis and screening workflows. By defining the scope, novelty, and contribution of Transformer-based design strategies, this review provides a focused roadmap for accelerating the development of MOF-based platforms for next-generation nanotheranostics. Full article

Geospatial data analysis systems are currently very relevant. Most such systems use either relational databases or graph databases. This paper presents the idea of using both approaches, taking into account the main features and advantages of each. A concrete example of a city transport network is used to experimentally examine the use of this hybrid approach. A special ETL procedure was developed to transform data from the corresponding graph database to a relational one, as well as the reverse process from the relational to the graph database. The results show which type of queries are better suited for relational databases, and which for graph databases. Additionally, for certain specific queries and applications, neither database type is capable of providing any results. Although this kind of hybrid architecture has issues with data duplication, the performance gains achieved are significant, making this approach highly efficient. Full article

This paper proposes a novel, dual-output, hybrid-clamped, quasi-five-level inverter (DO-HC-FLI) topology, capable of providing two independent AC voltage outputs with adjustable frequency and amplitude. Derived from a dual-output, active, neutral-point-clamped, three-level inverter, the proposed topology introduces three additional switches per phase to create dynamic switching paths. This expands the available range of DC-side voltage outputs and significantly improves the utilization rate of the DC–link voltage. Additionally, by adopting an asymmetric DC–link voltage configuration, the output line voltage levels of the conventional four-level inverter are increased to a number comparable to that of a five-level inverter. The front-end stage employs a hybrid series-parallel architecture, integrating dual Buck circuits with DC power sources. This configuration supplies the subsequent inverter stage with DC voltage levels at an optimal asymmetric ratio. In conjunction with a dual-output space vector pulse width modulation (SVPWM) strategy, the proposed system can collaboratively optimize the output voltage level characteristics of the inverter stage. Furthermore, a comprehensive analysis and comparison with other multilevel inverters are presented to demonstrate the superiority of the proposed topology. Finally, simulations and experiments are conducted to validate the effectiveness and feasibility of the proposed topology and modulation strategy. Full article

The blood-brain barrier (BBB) is one of the most selective physiological interfaces in the human body. Transendothelial electrical resistance (TEER) has become a widely adopted quantitative metric for assessing its in vitro structural and functional integrity. Although TEER measurements are routinely incorporated into BBB-on-chips, the absence of harmonized electrode architectures, measurement settings, and reporting standards continues to undermine reproducibility and translational reliability among laboratories. This systematic review provides the first comprehensive classification and critical comparison of electrode configurations used for TEER assessment, specifically within BBB-on-chip systems. Eligible studies were analyzed and categorized according to electrode design, fabrication method, integration strategy, and operational constraints. We critically evaluated six principal electrode architectures, highlighting their performance trade-offs in terms of uniformity of current distribution, long-term stability, scalability, and compatibility with dynamic shear conditions. Furthermore, we propose a bioinspired TEER reporting framework that consolidates essential metadata, including electrode specification, temperature control, viscosity effects, and blank resistance correction. Our analysis proposes screen-printed and hybrid silver-indium tin oxide (ITO) electrodes as promising candidates for next-generation BBB platforms. Moreover, our review provides a structured roadmap for standardizing TEER electrode design and reporting practices to facilitate interlaboratory consistency and accelerate the adoption of BBB-on-chip systems as truly biomimetic platforms for predictive neuropharmacological workflows. Full article

In logistics systems, the organization of information retrieval plays a key role in human interaction with technical systems to ensure decision-making speed, route optimization, planning, and resource allocation. At the same time, the efficiency of the logistics system when simultaneously processing large volumes of data and constantly updating it is determined by the speed of processing user requests and the accuracy of the responses provided by the system. Within the retrieval-augmented generation architecture, a hybrid information retrieval method has been proposed, based on the combined use of a vector-graph data representation structure and large language model. Experiments showed that the hybrid method achieved best accuracy rates of 0.24–0.25 (among all considered methods) with enhanced scalability capabilities (when the number of nodes increases fourfold, the time increases only twofold—from 0.09 s to 0.20 s) due to the limitation of the graph traversal area when implementing the graph component of the hybrid search. An optimal range of 30–50 nodes to be traversed was also identified, balancing precision and query processing speed. The findings are of practical value to logistics system developers and supply chain managers aiming to implement high-precision, natural language-based information retrieval in dynamic operational environments. Full article