Search Results (233)

Background/Objectives: Intravenous thrombolytic therapy remains the cornerstone of managing acute ischemic stroke (AIS) patients. Given the potential adverse effects of thrombolysis, patients are admitted to an intensive care unit (ICU) for close monitoring following administration. Alternative post-thrombolytic pathways may provide safe, cost-effective care in certain populations. We aimed to determine the proportion of patients treated with thrombolytics who required ICU care for reasons other than frequent neurologic monitoring and to define their characteristics. Methods: We retrospectively (May 2020–August 2022) reviewed patients ≥ 18 years of age who received Tenecteplase (TNK) or tissue plasminogen activator (tPA) for AIS at our stroke center. Patients were classified as requiring ICU care if they required intubation within 24 h of admission, required neurosurgical intervention, had symptomatic hemorrhagic conversion or brain compression, required a continuous infusion for hemodynamic management, or were in status epilepticus. Univariate and multivariable statistical analyses were performed. The study protocol was deemed exempt by our Institutional Review Board. Results: 262 patients met inclusion criteria. A total of 54 (20.6%) required ICU care. Multivariable analysis showed that patients on antithrombotic therapies prior to arrival (AOR: 3.344, p = 0.002) or who presented with higher initial NIH stroke scale (AOR: 1.116, p < 0.001) had a significantly higher likelihood of requiring an ICU level of care. Conclusions: In our cohort, approximately 21% of patients required critical care. Antithrombotic therapy before admission and greater NIH stroke scale on arrival were associated with an increased likelihood of requiring ICU care. Further prospective studies are indicated to assess the efficacy of alternative settings for post-thrombolytic care in selected AIS patients; however, our findings suggest that a specific subset of patients with AIS can be safely and effectively cared for in a non-ICU setting. This may have implications for the provision of safe, effective care while optimizing healthcare resource utilization. Full article

Residues in the grain tank of seed-production wheat harvesters often cause varietal admixture, challenging seed purity maintenance above 99%. To address this, an intelligent cleaning system was developed for automatic residue recognition and removal. The system utilizes an RGB-D camera and an embedded AI unit paired with an improved lightweight object detection model. This model, enhanced for feature extraction and compressed via LAMP, was successfully deployed on a Jetson Nano, achieving 92.5% detection accuracy and 13.37 FPS for real-time 3D localization of impurities. A D–H kinematic model was established for the 4-DOF cleaning manipulator. By integrating the PSO and FWA models, the motion trajectory was optimized for time-optimality, reducing movement time from 9 s to 5.96 s. Furthermore, a gas–solid coupled simulation verified the separation capability of the cyclone-type dust extraction unit, which prevents motor damage and centralizes residue collection. Field tests confirmed the system’s comprehensive functionality, achieving an average cleaning rate of 92.6%. The proposed system successfully enables autonomous residue cleanup, effectively minimizing the risk of variety mixing and significantly improving the harvest purity and operational reliability of seed-production wheat. It presents a novel technological path for efficient seed production under the paradigm of smart agriculture. Full article

We present a hybrid end-to-end learned image compression framework that combines a CNN-based variational autoencoder (VAE) with an efficient hierarchical Swin Transformer to address the limitations of existing entropy models in capturing global dependencies under computational constraints. Traditional VAE-based codecs typically rely on CNN-based priors with localized receptive fields, which are insufficient for modelling the complex, high-dimensional dependencies of the latent space, thereby limiting compression efficiency. While fully global transformer-based models can capture long-range dependencies, their high computational complexity makes them impractical for high-resolution image compression. To overcome this trade-off, our approach couples a CNN-based VAE with a patch-based hierarchical Swin Transformer hyperprior that employs shifted window self-attention to effectively model both local and global contextual information while maintaining computational efficiency. The proposed framework tightly integrates this expressive entropy model with an end-to-end differentiable quantization module, enabling joint optimization of the complete rate-distortion objective. By learning a more accurate probability distribution of the latent representation, the model achieves improved bitrate estimation and a more compact latent representation, resulting in enhanced compression performance. We validate our approach on the widely used Kodak, JPEG AI, and CLIC datasets, demonstrating that the proposed hybrid architecture achieves superior rate-distortion performance, delivering higher visual quality at lower bitrates compared to methods relying on simpler CNN-based entropy priors. This work demonstrates the effectiveness of integrating efficient transformer architectures into learned image compression and highlights their potential for advancing entropy modelling beyond conventional CNN-based designs. Full article

Accurate user positioning in 6G networks is essential for next-generation mobile services. However, classical approaches such as time-difference-of-arrival (TDoA) remain vulnerable to dense multipath and NLoS conditions commonly found in indoor and industrial environments. This paper proposes an AI-driven RF fingerprinting framework that leverages uplink channel state information (CSI) to achieve robust and privacy-preserving 2D localization. A lightweight convolutional neural network (CNN) extracts location-specific spectral–spatial fingerprints from CSI tensors, while a federated learning (FL) scheme enables distributed training across multiple gNBs without sharing raw channel data. The proposed integration of CSI tensor processing with FL and structured pruning is introduced as a novel solution for practical 6G edge positioning. To further reduce latency and communication costs, a structured pruning mechanism compresses the model by 40–60%, lowering the memory footprint with negligible accuracy loss. A performance evaluation in 3GPP-compliant indoor factory scenarios indicates a median positioning error below 1 m for over 90% of cases, significantly outperforming TDoA. Moreover, the compressed FL model reduces the FL communication load by ~38% and accelerates local training, establishing an efficient, secure, and deployment-ready positioning solution for 6G networks. Full article

The growing demand for intelligent and autonomous devices has accelerated the integration of neural networks into embedded systems, a paradigm known as Edge AI. While this approach enables real-time, low-latency processing with improved privacy, it remains constrained by strict limitations in memory, computation and energy. This paper presents a systematic review, aligned with PRISMA principles, that examines the current landscape of deep learning deployment on embedded hardware. The review analyzes key optimization techniques—including pruning, quantization and inference-level improvements—together with lightweight architectures such as CNNs, RNNs and compact networks, as well as a diverse ecosystem of hardware platforms and software frameworks. From the recurring patterns identified in the literature, we derive a practical five-stage methodology that guides developers through requirement definition, model selection, optimization, hardware alignment and deployment. Unlike existing surveys that mainly provide descriptive taxonomies, this methodology offers a structured and reproducible workflow explicitly designed to support multi-objective trade-offs in resource-constrained environments. The review also identifies emerging trends such as TinyML and hybrid architectures and highlights persistent gaps, including limited support for ultra-low-precision inference, variability in hardware toolchains and the absence of standardized holistic benchmarking. By synthesizing these insights into a coherent framework, this work aims to facilitate more efficient, robust and scalable Edge AI implementations. Full article

The convergence of artificial intelligence and synthetic biology is innovating and accelerating the design of novel viral genomes, expanding both therapeutic opportunities and dual-use risk. This review articulates a countermeasure strategy for emerging and engineered viruses leveraging the programmable CRISPR modality. Building on mounting in vitro and in vivo evidence that Cas9 degrades DNA viruses (e.g., Orthopoxviruses, HSV-1, ASFV), while Cas13 targets RNA viral genomes (e.g., Influenza A, Dengue, RSV), both leading to reduced viremia, diminished disease burden, and alleviated symptoms. Here, we outline a rapid-response pipeline to position CRISPR-based countermeasures in translational and pandemic-response frameworks, linking real-time sequencing to AI-assisted gRNA selection and multiplexed cassette design to achieve viral targeting efficacy. To minimize resistance and off-target risk, we emphasize multi-gRNA cocktails, continuous genomic surveillance, and adaptive gRNA rotation. We also propose governance mechanisms, such as pre-cleared gRNA repositories, transparent design logs, standardized off-target/safety screening, and alignment with evolving nucleic-acid-synthesis screening frameworks to enable emergency deployment while preserving security. Furthermore, compressing the time from sequence to treatment and complementary to vaccines and small-molecule antivirals, CRISPR represents a technologically agile and strategically essential capability to combat both natural outbreaks and AI-enabled biothreats. Collectively, programmable CRISPR antivirals represent an auditable, rapidly adaptable foundation for next-generation biodefense preparedness. Full article

Underground gas storage (UGS), encompassing hydrogen, natural gas, and compressed air, is a cornerstone of large-scale energy transition strategies, offering seasonal balancing, security of supply, and integration with renewable energy systems. However, the complexity of geological conditions, multiphysics coupling, and operational uncertainties pose significant challenges for UGS design, monitoring, and optimization. Artificial intelligence (AI)—particularly machine learning and deep learning—has emerged as a powerful tool to overcome these challenges. This review systematically examines AI applications in underground storage types such as salt caverns, depleted hydrocarbon reservoirs, abandoned mines, and lined rock caverns using bibliometric and knowledge-graph analysis of 176 publications retrieved from the Web of Science Core Collection. The study revealed a rapid surge in AI-related research on UGS since 2017, with underground hydrogen storage emerging as the most dynamic and rapidly expanding research frontier. The results reveal six dominant research frontiers: (i) AI-assisted geological characterization and property prediction; (ii) physics-informed proxy modeling and multi-physics simulation; (iii) gas–rock–fluid interaction, wettability, and interfacial behavior prediction; (iv) injection-production process optimization; (v) intelligent design and construction of underground storage, especially salt caverns; and (vi) intelligent monitoring, optimization, and risk management. Despite these advances, challenges persist in data scarcity, physical consistency, and generalization. Future efforts should focus on hybrid physics-informed AI, digital twin-enabled operation, and multi-gas comparative frameworks to achieve safe, efficient, and intelligent underground storage systems aligned with global carbon neutrality. Full article

Bidirectional Encoder Representations from Transformers (BERT) excels in natural language processing (NLP) but is costly on edge devices. We introduce an unsupervised, retraining-free structured pruning scheme for BERT, guided by mutual information (MI). Leveraging Rényi $\alpha$-order entropy, we design a representation-aware MI estimator and a principled kernel-bandwidth selection, producing stable, sample-efficient neuron-level pruning signals. This method removes redundant units while preserving representational capacity, reduces memory and latency, and deploys readily on commodity hardware. Explainable-AI visualizations clarify how compression reshapes intermediate features and predictions. Across benchmarks, the compressed models maintain minimal accuracy loss, outperform or match strong unsupervised baselines, and remain competitive with supervised alternatives. Full article

As optical networks continue to evolve toward higher speed and larger capacity, conventional security mechanisms relying on optoelectronic conversion are facing increasing limitations. The optical photonic firewall, as an emerging optical-layer security device, enables direct inspection in the optical domain, making its core technology—All-Optical Pattern Matching (AOPM)—a focal point of current research. This review provides a comprehensive survey of AOPM systems. It first introduces the main components of AOPM, namely symbol matching and system architectures, and analyzes their representative implementations. For low-order modulation formats such as OOK and BPSK, the review highlights matching schemes enabled by semiconductor optical amplifier (SOA) and highly nonlinear fiber (HNLF) logic gates, as well as their potential for reconfigurable extension. Building upon this foundation, the paper focuses on systems for high-order modulation formats including QPSK, 8PSK, and 16QAM, covering dimensionality-reduction-based approaches (e.g., PSA-based phase compression, squarer-based phase multiplication, constellation-mapping-based format conversion), direct symbol matching methods (e.g., phase interference, generalized XNOR, real-time Fourier transform correlation), and reconfigurable designs for multi-format adaptability. Furthermore, the review discusses optimization challenges under non-ideal conditions, such as noise accumulation, phase misalignment, and phase-locking-free operation. Finally, it outlines future directions in robust high-order modulation handling, photonic integration, and AI-driven intelligent matching, offering guidance for the development of optical-layer security technologies. Full article

Recent advances in computer vision and artificial intelligence have enabled new approaches for non-destructive post-earthquake assessment of masonry structures. This study proposes a hybrid AI–FEA framework that integrates a MobileNetV2 convolutional neural network for crack-image-based material property inference with nonlinear finite element analysis (FEA) of confined masonry walls. The model predicts key mechanical parameters, including elastic modulus, compressive and tensile strengths, and fracture energies, directly from crack morphology, and these parameters are subsequently used as input for DIANA FEA to simulate the wall’s seismic response. The framework is validated against reference experimental data, achieving a strong parametric correlation (R² = 0.91) and accurately reproducing characteristic nonlinear behavior such as stiffness degradation, diagonal cracking, and post-peak softening in pushover analysis. Photographs from the Limatambo urban area in Lima, Peru, are included to illustrate typical damage patterns in a high-seismic-risk context, although the numerical model represents a standardized confined masonry wall typology rather than site-specific buildings. The proposed methodology offers a consistent, non-destructive, and efficient tool for seismic performance evaluation and supports the digital modernization of structural diagnostics in earthquake-prone regions. Full article

Background: Artificial intelligence (AI) and machine learning (ML) have rapidly expanded across the continuum of cardiopulmonary resuscitation (CPR), with growing evidence of their contribution to improving early recognition, intervention quality, and post-cardiac arrest outcomes. This narrative review synthesizes the current advancements and challenges in AI/ML-enhanced resuscitation science. Methods: A targeted literature search was conducted in Web of Science for the period 2018–2025 using the keywords “artificial intelligence” and “cardiopulmonary resuscitation”. The search identified studies addressing AI/ML applications across the resuscitation pathway, which were reviewed and categorized according to the American Heart Association’s Chain of Survival—prevention and preparedness, activation of the emergency response system, high-quality CPR including early defibrillation, advanced resuscitation interventions, post-cardiac arrest care, and recovery. Results: The literature demonstrates substantial promise for AI/ML in several domains: (1) early recognition and timely activation of emergency medical services through real-time detection algorithms; (2) optimization of high-quality CPR, including feedback systems, automated assessment of chest compressions, and prediction of defibrillation success; (3) support for advanced resuscitation interventions, such as rhythm classification, prognostication, and intra-arrest decision support; (4) post-cardiac arrest care, including outcome prediction and neuroprognostication; and (5) integrative and cross-domain approaches that link multiple phases of resuscitation into end-to-end AI-supported systems. Emerging work also highlights the role of AI in education and training, with applications in simulation, assessment, and skill reinforcement. Conclusions: AI/ML technologies hold significant potential to augment clinical performance across all links of the Chain of Survival. Their effective implementation requires attention to ethical considerations, data representativeness, and real-world validation. Future research should prioritize multicenter datasets, transparency, bias mitigation, and clinically embedded evaluation frameworks to ensure that AI/ML systems support safe, equitable, and high-impact resuscitation care. Full article

Artificial Intelligence (AI) is rapidly transforming engineering fields, from robotics to aerospace, with applications in control systems for UAVs and satellites. This work builds on a previously developed AI attitude controller for the InnoCube 3U nanosatellite. Deploying complex Neural Networks (NNs) on resource-limited microcontrollers presents a significant challenge. To overcome this, we propose distilling a Multi-Layer Perceptron (MLP) trained with Deep Reinforcement Learning (DRL) for attitude control into a Kolmogorov–Arnold Network (KAN). We convert this numeric KAN into a symbolic KAN, where each edge represents a learnable mathematical function, and finally extract a concise symbolic formula. This symbolic representation dramatically reduces memory usage and computational complexity, making it ideal for pico- and nanosatellites. We evaluate and demonstrate the feasibility of this approach for inertial pointing with reaction wheels in simulation using a realistic model of the InnoCube satellite. Our results show that the highly compressed KANs successfully solve the attitude control problem, while reducing the required memory footprint and inference time on the InnoCube ADCS hardware by over an order of magnitude. Beyond attitude control, we believe symbolic KANs hold great potential in aerospace for neural network compression and interpretable, data-driven modeling and system identification in future space missions. Full article

The prediction of concrete compressive strength (CSMPa) is fundamental in experimental civil engineering as it enables the optimization of mix design and complements laboratory testing through predictive tools. This study presents a systematic and reproducible methodology for comparing eight regression algorithms—including linear models, neural networks, and boosting methods—applied to three experimental datasets that represent different types of concrete: high-performance concrete (HPC), conventional concrete, and recycled-aggregate concrete (RAC). In order to make such comparison, some performance metrics were calculated (RMSE, MAE, MAPE, $R^2$, and nRMSE) through hyperparameter optimization using RandomizedSearchCV and homogeneous cross-validation. The boosting methods achieved the best performance, with CatBoost standing out by reaching $R^2$ values between 0.92 and 0.95 and RMSE between 3.4 and 4.4 MPa, confirming its inter-dataset stability and generalization capability. These results indicate consistent predictive accuracy across concretes of different compositions and production contexts. As an applied contribution, three interactive inference systems were developed in Google Colab to estimate CS from mix parameters, promoting reproducibility, open access, and practical use in quality-control processes. Full article

With the rapid advancement in smart city infrastructures, the demand for personalized and explainable educational services has become increasingly prominent. To address the challenges of information overload and the lack of interpretability in traditional learning resource recommendation, this paper proposes a Structure-aware and Attention-enhanced explainable learning resource Recommendation approach (StAR) for smart education. StAR constructs a reinforcement learning framework grounded in a knowledge graph to model learner–resource interactions. First, a multi-head attention mechanism encodes path states and extracts key semantic features, enhancing the model’s ability to represent complex learning contexts. Then, a dual-layer action pruning strategy compresses the action space and improves reasoning efficiency. Finally, a structure-aware reward function guides the generation of semantically coherent and interpretable recommendation paths. Experiments on two real-world educational datasets, COCO and MoocCube, demonstrate that StAR outperforms several baseline models, achieving improvements of 14.2% and 12.6% in NDCG and Recall on COCO, and 5.2% and 4.2% on MoocCube, respectively. The results validate the effectiveness of StAR in enhancing recommendation accuracy, reasoning efficiency, and interpretability, offering a promising AI-enhanced solution for personalized learning in smart cities. Full article

This study examines the carbonation and mechanical behavior of cement mortar incorporating artificial interior stone (AIS) sludge and recycled mask fibers (RMFs). Sludge, derived from AIS waste, replaced 30 wt.% of fine aggregate, while RMF from polypropylene masks was added at 0–1 wt.% of cement. Specimens were cured under normal and carbonation conditions (10% CO₂, 25 °C, 60% RH) for 7 and 28 days. Carbonation curing improved compressive and flexural strengths by up to 28% and 88%, respectively, and enhanced microstructural densification. Although the incorporation of AIS sludge reduced compressive strength due to its inert and irregular particle characteristics, it effectively refined the pore structure and decreased overall porosity. The inclusion of RMF at moderate contents (0.25–0.5 wt.%) improved crack resistance and lowered thermal conductivity, demonstrating a favorable balance between strength and thermal performance. TGA/DTG results confirmed increased CaCO₃ formation and greater CO₂ uptake. After exposure to 500 °C, carbonation-cured mortars retained higher residual strength, indicating superior thermal stability. Full article