Search Results (496)

Intelligent surface vehicles, including unmanned surface vehicles (USVs) and autonomous surface vehicles (ASVs), have gained significant attention from both academic and industrial communities. However, shipboard maritime images captured under hazy weather conditions inevitably suffer from a blurred, distorted appearance. Low-quality maritime images can lead to negative effects on high-level computer vision tasks, such as object detection, recognition and tracking, etc. To avoid the negative influence of low-quality maritime images, it is necessary to develop a visual perception enhancement method for intelligent surface vehicles. To generate satisfactory haze-free maritime images, we propose development of a novel transmission map estimation and refinement framework. In this work, the coarse transmission map is obtained by the weighted fusion of transmission maps generated by dark channel prior (DCP)- and luminance-based estimation methods. To refine the transmission map, we take the segmented smooth feature of the transmission map into account. A joint variational framework with total generalized variation (TGV) and relative total variation (RTV) regularizers is accordingly proposed. The joint variational framework is effectively solved by an alternating-direction numerical algorithm, which decomposes the original nonconvex nonsmooth optimization problem into several subproblems. Each subproblem could be efficiently and easily handled using the existing optimization algorithm. Finally, comprehensive experiments are conducted on synthetic and realistic maritime images. The imaging results have illustrated that our method can outperform or achieve comparable results with other competing dehazing methods. The promoted visual perception is beneficial to improve navigation safety for intelligent surface vehicles under hazy weather conditions. Full article

Artificial intelligence is playing an increasingly important role in education. Learning path recommendation is one of the key technologies in artificial intelligence education applications. This paper applies knowledge space theory and fuzzy set theory to study the construction of consistent fuzzy competence spaces and their application to learning path recommendation. With the help of the outer fringe of fuzzy competence states, this paper proves the necessary and sufficient conditions for a fuzzy competence space to be a consistent fuzzy competence space and designs an algorithm for verifying consistent fuzzy competence spaces. It also proposes methods for constructing and reducing consistent fuzzy competence spaces, provides learning path recommendation algorithms from the competence perspective and combined with a disjunctive fuzzy skill mapping, and constructs a bottom-up gradual and effective learning path tree. Simulation experiments are carried out for the construction and reduction in consistent fuzzy competence spaces and for learning path recommendation, and the simulation studies show that the proposed methods achieve significant performance improvement compared with related research and produce a more complete recommendation of gradual and effective learning paths. The research of this paper can provide theoretical foundations and algorithmic references for the development of artificial intelligence education applications such as learning assessment systems and intelligent testing systems. Full article

This study analyzes the relational architecture of Brazilian traceable beef exports using a tripartite network model that connects certified meatpacking plants, AgriTrace sustainability protocols, and importing countries. By leveraging export authorization data from the Brazilian Ministry of Agriculture, it is shown that certification protocols function not merely as compliance tools but as relational governance infrastructures, mediating legitimacy, market access, and coordination within global value chains. Bipartite projections allowed the deriving and analyzing of two secondary networks: one mapping connections between meatpacking plants that share certifications, and the other linking consumer nations through common supply channels. The meatpacking plant network displays high modularity, featuring two dominant clusters alongside several smaller, regionally coherent clusters. This structure reflects diverse governance capabilities and strategic certification adoptions. Conversely, the consumer nation network shows lower modularity but identifies central hubs that organize international demand and signal regulatory alignment. These patterns reveal underlying dynamics of coopetition, where actors collaborate through shared standards yet compete through innovation. By integrating the Inner Development Goals (IDG) framework, it is revealed internal capacities, such as trust, complexity awareness, and shared purpose, underpinning the efficacy of traceability systems as ethical and adaptive infrastructures. This values-based lens provides a novel perspective on how technical systems can foster resilient, inclusive, and sustainable trade, thereby contributing to planetary health and human-centered development in global livestock governance. Full article

Display-field communication (DFC) is an imperceptible screen-to-camera technology that embeds and recovers data from the frequency domain of an image frame. Conventional DFC requires a reference frame for each data frame to estimate the channel, a method that, while reliable, is not bandwidth-efficient. Similarly, iterative DFC requires the transmission of pilot symbols for channel estimation. In this paper, we propose an implicit DFC (iDFC) scheme that eliminates the need for reference frames by estimating them using the first-order statistics of the received image. The system employs discrete Fourier-transform-based subcarrier mapping and adds data directly to the frequency coefficients of the host image. At the receiver, statistical estimation enables blind channel equalization without sacrificing the data rate. The simulation results show that iDFC achieves an achievable data rate (ADR) of up to $1.52\times {10}^5$ bps, a significant enhancement of approximately 97% and 11% compared to conventional and iterative DFC schemes, respectively. Furthermore, the analysis reveals a critical trade-off between communication robustness and visual imperceptibility; allocating 70% of signal power to the image maintains high visual quality but results in a symbol error rate (SER) floor of $1.5\times {10}^{-1}$, whereas allocating only 10% improves the SER to below ${10}^{-2}$ at the cost of visible artifacts. The findings also identify QPSK as the optimal modulation order that maximizes the data rate, showing that higher-order schemes can be detrimental due to system impairments such as signal clipping. The proposed iDFC scheme presents a more efficient and robust solution for high-capacity DFC applications by balancing the competing demands of data throughput and visual fidelity. Full article

The Adriatic Sea is a critical neritic habitat for juvenile and adult female loggerhead sea turtles (Caretta caretta), where intense anthropogenic pressures and environmental stressors may influence their reproductive biology. Knowledge on the onset of puberty in this population is limited by scarce information on the sub-adult stage, a transitional phase in which reproductive competence is acquired. This study integrated histological analysis and Fourier-transform infrared (FTIR) imaging spectroscopy to provide both structural and biochemical characterization of folliculogenesis, with emphasis on vitellogenesis, in C. caretta from the north-central Adriatic Sea. Histological analysis determined the progression of follicle development, while FTIR imaging, a label-free and spatially resolved technique, mapped the distribution of proteins, lipids, and nucleic acids across ovarian compartments. Logistic regression estimated the size at which 50% of females are sexually mature (L₅₀) at 58.54 cm Curved Carapace Length (CCL). Based on this value, 60% of sub-adult females were already mature, indicating earlier puberty than previously inferred from macroscopic criteria. These preliminary results, along with reports of sporadic nesting in the Adriatic, raise the question of whether this basin may host further nesting events in the future. FTIR imaging proved to be a powerful tool for reproductive biology in non-model marine vertebrates. Full article

Urban models support sustainable, resilient, and equitable planning, but their validity hinges on underlying spatial data. This study examines the epistemological and technical consequences of relying on two dominant yet divergent platforms—OpenStreetMap (OSM) and Google Maps—for extracting proximity-based amenities within the 15-min city framework. Across four European contexts—Versilia, Gothenburg, Nice, and Vienna—we compare (i) data completeness and spatial coverage; (ii) semantic categories; and (iii) the effects of data heterogeneity on accessibility modelling. Findings show that OSM, while semantically consistent and openly accessible, systematically underrepresents peripheral amenities, introducing bias towards urban cores in accessibility metrics. Conversely, Google Maps provides broader coverage but is constrained by dependencies on extraction methods, opaque data structures, and ambiguous classification schemes, which hinder reproducibility, reduce interpretability, and limit its analytical robustness. These divergences yield distinct accessibility landscapes and competing readings of functionality and spatial equity. We argue that data source choice and protocol design are epistemological decisions and advocate transparent, hybrid strategies with cross-platform semantic harmonisation to strengthen robustness, equity, and policy relevance. Full article

Artificial intelligence (AI) is an important tool for improving agricultural tasks. In particular, object detection methods based on convolutional neural networks (CNNs) enable the detection and classification of objects directly in the field. Combined with unmanned aerial vehicles (UAVs, drones), these methods allow efficient crop monitoring. The primary challenge is to develop models that are both accurate and feasible under real-world conditions. This study addresses this challenge by evaluating marigold flower detection using three groups of CNN detectors: canonical models, including YOLOv2, Faster R-CNN, and SSD with their original backbones; modified versions of these detectors using DarkNet-53; and modern architectures, including YOLOv11, YOLOv12, and the RT-DETR. The dataset consisted of 392 images from marigold fields, which were manually labeled and augmented to a total of 940 images. The results showed that YOLOv2 with DarkNet-53 achieved the best performance, with 98.8% mean average precision (mAP) and 97.9% F1-score (F1). SSD and Faster R-CNN also improved, reaching 63.1% and 52.8%, respectively. Modern models obtained strong results: YOLOv11 and YOLOv12 reached 96–97%, and RT-DETR 93.5%. The modification of YOLOv2 allowed this classical detector to compete directly with, and even surpass, recent models. Precision–recall (PR) curves, F1-scores, and complexity analysis confirmed the trade-offs between accuracy and efficiency. These findings demonstrate that while modern detectors are efficient baselines, classical models with updated backbones can still deliver state-of-the-art results for UAV-based crop monitoring. Full article

Fingerprint authentication systems encounter growing threats from presentation attacks, making strong liveness detection crucial. This work presents a deep learning-based framework integrating EfficientNetB0 with a Squeeze-and-Excitation (SE) attention approach, using transfer learning to enhance feature extraction. The LivDet 2015 dataset, composed of both real and fake fingerprints taken using four optical sensors and spoofs made using PlayDoh, Ecoflex, and Gelatine, is used to train and test the model architecture. Stratified splitting is performed once the images being input have been scaled and normalized to conform to EfficientNetB0’s format. The SE module adaptively improves appropriate features to competently differentiate live from fake inputs. The classification head comprises fully connected layers, dropout, batch normalization, and a sigmoid output. Empirical results exhibit accuracy between 98.50% and 99.50%, with an AUC varying from 0.978 to 0.9995, providing high precision and recall for genuine users, and robust generalization across unseen spoof types. Compared to existing methods like Slim-ResCNN and HyiPAD, the novelty of our model lies in the Squeeze-and-Excitation mechanism, which enhances feature discrimination by adaptively recalibrating the channels of the feature maps, thereby improving the model’s ability to differentiate between live and spoofed fingerprints. This model has practical implications for deployment in real-time biometric systems, including mobile authentication and secure access control, presenting an efficient solution for protecting against sophisticated spoofing methods. Future research will focus on sensor-invariant learning and adaptive thresholds to further enhance resilience against varying spoofing attacks. Full article

Remote sensing provides a viable alternative for understanding landscape modifications attributed to beaver activity. The central objective of this study is to integrate multi-source remote sensing observations in tandem with a deep learning (DL) (convolutional neural net or transformer) model to automatically map beaver-influenced floodplain inundations (BIFI) over large geographical extents. We trained, validated, and tested eleven different model configurations in three architectures using five ResNet and five B-Finetuned encoders. The training dataset consisted of >25,000 manually annotated aerial image tiles of BIFIs in Connecticut. The YOLOv8 architecture outperformed competing configurations and achieved an F1 score of 80.59% and pixel-based map accuracy of 98.95%. SegFormer and U-Net++’s highest-performing models had F1 scores of 68.98% and 78.86%, respectively. The YOLOv8l-seg model was deployed at a statewide scale based on 1 m resolution multi-temporal aerial imagery acquired from 1990 to 2019 under leaf-on and leaf-off conditions. Our results suggest a variety of inferences when comparing leaf-on and leaf-off conditions of the same year. The model exhibits limitations in identifying BIFIs in panchromatic imagery in occluded environments. Study findings demonstrate the potential of harnessing historical and modern aerial image datasets with state-of-the-art DL models to increase our understanding of beaver activity across space and time. Full article

Edible hydrogels are the central material class in 3D food printing because they reconcile two competing needs: (i) low resistance to flow under nozzle shear and (ii) fast recovery of elastic structure after deposition to preserve geometry. This review consolidates the recent years of progress on hydrogel formulations—gelatin, alginate, pectin, carrageenan, agar, starch-based gels, gellan, and cellulose derivatives, xanthan/konjac blends, protein–polysaccharide composites, and emulsion gels alongside a critical analysis of printing technologies relevant to food: extrusion, inkjet, binder jetting, and laser-based approaches. For each material, this review connects gelation triggers and compositional variables to rheology signatures that govern printability and then maps these to process windows and post-processing routes. This review consolidates a decision-oriented workflow for edible-hydrogel printability that links formulation variables, process parameters, and geometric fidelity through standardized test constructs (single line, bridge, thin wall) and rheology-anchored gates (e.g., yield stress and recovery). Building on these elements, a “printability map/window” is formalized to position inks within actionable operating regions, enabling recipe screening and process transfer. Compared with prior reviews, the emphasis is on decisions: what to measure, how to interpret it, and how to adjust inks and post-set enablers to meet target fidelity and texture. Reporting minima and a stability checklist are identified to close the loop from design to shelf. Full article

Critical thinking, as a crucial component of 21st-century core competencies, poses significant challenges for effective assessment in educational evaluation. This study proposes an automated assessment method for critical thinking in middle school Chinese language based on a Bidirectional Encoder Representations from Transformers—Convolutional Neural Network (BERT-CNN) hybrid model, achieving a multi-dimensional quantitative assessment of students’ critical thinking performance in writing through the synergistic effect of deep semantic encoding and local feature extraction. The research constructs an annotated dataset containing 4827 argumentative essays from three middle school grades, employing expert scoring across nine dimensions of the Paul–Elder framework, and designs three types of logic chain extraction algorithms: argument–evidence mapping, causal reasoning chains, and rebuttal–support structures. Experimental results demonstrate that the BERT-CNN hybrid model achieves a Pearson correlation coefficient of 0.872 in overall assessment tasks and an average F1 score of 0.770 in logic chain recognition tasks, outperforming the traditional baseline methods tested in our experiments. Ablation experiments confirm the hierarchical contributions of semantic features (31.2%), syntactic features (24.1%), and logical markers (18.9%), while revealing the model’s limitations in assessing higher-order cognitive dimensions. The findings provide a feasible technical solution for the intelligent assessment of critical thinking, offering significant theoretical value and practical implications for advancing educational evaluation reform and personalized instruction. Full article

Distance learning has become essential to higher education, yet its application in military officer training presents unique academic, operational, and security challenges. For Lithuania’s future officers, remote education must foster not only knowledge acquisition but also decision-making, leadership, and operational readiness—competencies traditionally developed in immersive, in-person environments. This study addresses these challenges by integrating System Dynamics Modelling, Contemporary Risk Management Standards (ISO 31000:2022; Dynamic Risk Management Framework), and Learning Analytics to evaluate the interdependencies among twelve critical factors influencing the system resilience and effectiveness of distance military education. Data were collected from fifteen domain experts through structured pairwise influence assessments, applying the fuzzy DEMATEL method to map causal relationships between criteria. Results identified key causal drivers such as Feedback Loop Effectiveness, Scenario Simulation Capability, and Predictive Intervention Effectiveness, which most strongly influence downstream outcomes like learner engagement, risk identification, and instructional adaptability. These findings emphasize the strategic importance of upstream feedback, proactive risk planning, and advanced analytics in enhancing operational readiness. By bridging theoretical modelling, contemporary risk governance, and advanced learning analytics, this study offers a scalable framework for decision-making in complex, high-stakes education systems. The causal relationships revealed here provide a blueprint not only for optimizing military distance education but also for enhancing overall system resilience and adaptability in other critical domains. Full article

Sonochlorination (US/chlorine) is an emerging sonohybrid advanced oxidation process whose performance reportedly surpasses that of its individual components. However, the underlying oxidant budget is still being debated. We mapped the mechanism by systematically probing the US/chlorine system with selective scavengers (ascorbic acid, nitrobenzene, tert-butanol, 2-propanol, and phenol), competing anions (nitrite), and natural organic matter (humic acid). The kinetic hierarchy US/chlorine > US > chlorine remained consistent across all conditions, though its magnitude depended heavily on the matrix composition. Efficient ^•OH traps, such as alcohols and nitrobenzene, only partially suppressed the US/chlorine system. However, they greatly slowed sonolysis. This reveals a substantial non-^•OH channel in the hybrid process. Ascorbic acid eliminated synergy by stoichiometrically removing free chlorine. Phenol quenched HOCl and chlorine-centered radicals. Nitrite imposed a dual penalty by scavenging ^•OH and consuming HOCl via the nitryl chloride (ClNO₂) pathway. Humic acid acted as a three-way sink for ^•OH, HOCl, and chlorine radicals. These patterns suggest that reactivity is co-controlled by Cl^•, Cl₂^•−, and ClO^•. The results obtained are mechanistically consistent with cavitation-assisted activation of HOCl/OCl⁻ at pH 5–6, where HOCl concentration is maximal. This yields a mixed oxidant suite in which Cl₂^•− is the dominant bulk oxidant, Cl^• provides fast interfacial initiation, and ClO^• offers selective support. Full article

Artificial Intelligence, especially Convolutional Neural Networks (CNN), is gaining importance in health sciences, including forensic odontology. This study aimed to systematically analyze elements for automated dental status registration on OPGs using CNNs, on different image segments and resolutions. A dataset of 1400 manually annotated digital OPGs was divided into train, test, and validation sets (75%–12.5%–12.5%). Pre-trained and from-scratch models were developed and evaluated on images from full OPGs to individual and segmented teeth and sizes from 256 px to 1820 px. Performance was measured by Sørensen–Dice coefficient for segmentation and mean average precision (mAP) for detection. For segmentation, the UNet Big model was the most successful, using segmented or individual images, achieving 89.14% for crown and 84.90% for fillings, and UNet with 79.09% for root canal fillings. Caries presented a significant challenge, with the UNet model achieving the highest score of 64.68%. In detection, YOLOv5x6, trained from scratch, achieved the highest mAP of 98.02% on 1820 px images. Larger image resolutions and individual tooth inputs significantly improved performance. This study confirms the success of CNN models in specific tasks on OPGs. Image quality and input (individual tooth, resolutions above 640 px) critically influenced model competence. Further research with from-scratch models, higher resolutions, and smaller image segments is recommended. Full article

The provision of care to critically ill patients demands specialized training. Virtual reality (VR) has emerged as an effective tool in nursing education, promoting active learning and fostering the development of essential care competencies. Therefore, this study aimed to map the existing literature on the content related to the teaching of adult critical care nursing practices that have been modeled in VR environments. This study employed a scoping review methodology, guided by the Joanna Briggs Institute (JBI) and the Preferred Reporting Items for Systematic reviews and Meta-Analyses extension for Scoping Reviews (PRISMA-ScR) guidelines. A comprehensive search was conducted across 13 data sources, including grey literature. A total of 27 studies were included, highlighting key content areas such as cardiopulmonary resuscitation, tracheostomy care, and mechanical ventilation. The findings indicate that VR has a positive impact on knowledge acquisition, technical skill development, critical thinking, and the enhancement of student and professional confidence and safety. VR demonstrates considerable promise as a pedagogical tool for nursing education in complex clinical settings. However, methodological and technical limitations persist and require further attention. This review contributes to the scientific advancement by systematically organizing the evidence on the use of immersive technologies in health education. Full article