Search Results (3,523)

Due to its unique benefits over conventional subtractive manufacturing, additive manufacturing methods continue to attract interest in both academia and industry. One such method is called Cold Spray Additive Manufacturing (CSAM), a solid-state coating deposition technology to manufacture repair metallic components using a gas jet and powder particles. CSAM offers low heat input, stable phases, suitability for heat-sensitive substrates, and high deposition rates. However, persistent challenges include porosity control, geometric accuracy near edges and concavities, anisotropy, and cost sensitivities linked to gas selection and nozzle wear. Interdisciplinary research across manufacturing science, materials characterisation, robotics, control, artificial intelligence (AI), and machine learning (ML) is deployed to overcome these issues. ML supports quality prediction, inverse parameter design, in situ monitoring, and surrogate models that couple process physics with data. To demonstrate the impact of AI and ML on CSAM, this study presents a systematic literature review to identify, evaluate, and analyse published studies in this domain. The most relevant studies in the literature are analysed using keyword co-occurrence and clustering. Four themes were identified: design for CSAM, material analytics, real-time monitoring and defect analytics, and deposition and AI-enabled optimisation. Based on this synthesis, core challenges are identified as small and varied datasets, transfer and identifiability limits, and fragmented sensing. Main opportunities are outlined as physics-based surrogates, active learning, uncertainty-aware inversion, and cloud-edge control for reliable and adaptable ML use in CSAM. By systematically mapping the current landscape, this work provides a critical roadmap for researchers to target the most significant challenges and opportunities in applying AI/ML to industrialise CSAM. Full article

Automated medical report generation (MRG) faces a critical hurdle in seamlessly integrating detailed visual evidence with accurate clinical diagnoses. Current approaches often rely on static knowledge transfer, overlooking the complex interdependencies among pathological findings and their nuanced alignment with visual evidence, often yielding reports that are linguistically sound but clinically misaligned. To address these limitations, we propose a novel graph-driven medical report generation framework with adaptive knowledge distillation. Our architecture leverages a dual-phase optimization process. First, visual–semantic enhancement proceeds through the explicit correlation of image features with a structured knowledge network and their concurrent enrichment via cross-modal semantic fusion, ensuring that generated descriptions are grounded in anatomical and pathological context. Second, a knowledge distillation mechanism iteratively refines both global narrative flow and local descriptive precision, enhancing the consistency between images and text. Comprehensive experiments on the MIMIC-CXR and IU X-Ray datasets demonstrate the effectiveness of our approach, which achieves state-of-the-art performance in clinical efficacy metrics across both datasets. Full article

Achieving a best-fit prosthetic socket is essential to comfort, functional performance, and long-term residual limb health in lower-limb amputees. To our knowledge, no previous study has quantitatively compared in vivo residual limb geometry under vacuum versus non-vacuum conditions using high-resolution computed tomography (CT). In this patient-specific case study of a bilateral knee-disarticulation (KD) amputee, both residual limbs were scanned under standardized conditions: one enclosed in a vacuum-compressed sleeve and the contralateral limb untreated as a natural control, thereby minimizing inter-subject variability. CT-based 3D reconstructions enabled volumetric and cross-sectional quantification, including symmetry/asymmetry analysis of paired limbs, while finite element analysis (FEA) assessed the biomechanical consequences for socket performance. Vacuum application resulted in a 4.1% reduction in total limb volume and a 5.3% reduction in mid-thigh cross-sectional area, with regionally asymmetric displacement of soft tissues. FEA demonstrated that vacuum-induced geometry reduced peak Von Mises stresses (27.43 MPa to 15.83 MPa), minimized maximum displacement (1.72 mm to 0.88 mm), and improved minimum factor of safety (~2.0 to ~3.0), while homogenizing contact pressure distribution (peak fell from 2.42 to 1.28 N/mm²). These findings provide preliminary CT-based evidence that vacuum application induces measurable morphological adaptations with implications for socket conformity, comfort, and load transfer. While limited to a single patient, this study highlights the potential of vacuum-induced modeling to inform personalized prosthetic socket design. Full article

Quercetin, a key flavonoid in Anoectochilus roxburghii (Wall.) Lindl., plays an important role in determining the pharmacological value of this medicinal herb. However, traditional methods for quercetin quantification are destructive and time-consuming, limiting their application in real-time quality monitoring. This study investigates the hyperspectral response characteristics of quercetin using near-infrared hyperspectral imaging and establishes a feature-based model to explore its detectability in A. roxburghii leaves. We scanned standard quercetin solutions of known concentration under the same imaging conditions as the leaves to produce a dilution series. Feature-selection methods used included the successive projections algorithm (SPA), Pearson correlation, and competitive adaptive reweighted sampling (CARS). A 1D convolutional neural network (1D-CNN) trained on SPA-selected wavelengths yielded the best prediction performance. These key wavelengths—particularly the 923 nm band—showed strong theoretical and statistical relevance to quercetin’s molecular absorption. When applied to plant leaf spectra, the standard-trained model produced continuous predicted quercetin values that effectively distinguished cultivars with varying flavonoid contents. PCA visualization and ROC-based classification confirmed spectral transferability and potential for functional evaluation. This study demonstrates a non-destructive, spatially resolved, and biochemically interpretable strategy for identifying bioactive markers in plant tissues, offering a methodological basis for future hyperspectral inversion studies and intelligent quality assessment in herbal medicine. Full article

Jiangsu Province is an important economic province on the eastern coast of China, revealing the spatial–temporal characteristics, dynamic degree, and transition direction of land use/cover change, and its main driving factors are significant for the effective use of land resources and the promotion of regional human–land coordinated development. Based on land use data of Jiangsu Province from 2000 to 2020, this study investigates the spatiotemporal evolution characteristics of land use/cover using the dynamics model and the transfer matrix model, and examines the influence and interaction of the driving factors between human activities and the natural environment based on 10-factor data using Geodetector. The results showed that (1) In the past 20 years, the type of land use/cover in Jiangsu Province primarily comprises cropland, water, and impervious, with the land use/cover change mode mainly consisting of a dramatic change in cropland and impervious and relatively little change in forest, grassland, water, and barren. (2) From the perspective of the dynamic rate of land use/cover change, the single land use dynamic degree showed that impervious is the only land type whose dynamics have positively increased from 2000 to 2010 and 2010 to 2020, with values of 3.67% and 3.03%, respectively. According to the classification of comprehensive motivation, the comprehensive land use motivation in Jiangsu Province in each time period from 2000 to 2010 and 2010 to 2020 is 0.46% and 0.43%, respectively, which belongs to the extremely slow change type. (3) From the perspective of land use/cover transfer, Jiangsu Province is mainly characterized by a large area of cropland transfer (−7954.30 km²) and a large area of impervious transfer (8759.58 km²). The increase in impervious is mainly attributed to the transformation of cropland and water, accounting for 4066.07 km² and 513.73 km² from 2010 to 2020, which indicates that the non-agricultural phenomenon of cropland in Jiangsu Province, i.e., the process of transforming cropland into non-agricultural construction land, is significant. (4) From the perspective of driving factors, population density (q = 0.154) and night light brightness (q = 0.156) have always been important drivers of land use/cover change in Jiangsu Province. The interaction detection indicates that the land use/cover change is driven by both socio-economic factors and natural geographic factors. (5) In response to the dual pressures of climate change and rapid urbanization, coordinating the multiple objectives of socio-economic development, food security, and ecological protection is the fundamental path to achieving sustainable land use in Jiangsu Province and similar developed coastal areas. By revealing the characteristics and driving factors of land use/cover change in Jiangsu Province, this study provides qualitative and quantitative theoretical support for the coordinated decision-making of economic development and land use planning in Jiangsu Province, specifically contributing to sustainable land planning, climate adaptation policy-making, and the enhancement of community well-being through optimized land use. Full article

Seafood fraud, such as mislabeling low-cost rainbow trout as premium salmon, poses serious food safety risks and damages consumer rights. To address this growing concern, this study develops a deep learning-based, smartphone-compatible sensing system for fish meat identification and salmon freshness grading. By providing consumers with real-time, image-based verification tools, the system supports informed purchasing decisions and enhances food safety. The system adopts a two-stage design: first classifying fish meat types, then grading salmon freshness into three levels based on visual cues. An improved DenseNet121 architecture, enhanced with global average pooling, dropout layers, and a customized output layer, improves accuracy and reduces overfitting, while transfer learning with partial layer freezing enhances efficiency by reducing training time without significant accuracy loss. Experimental results show that the two-stage method outperforms the one-stage approach and several baseline models, achieving robust accuracy in both classification and grading tasks. Sensitivity analysis demonstrates resilience to blur and camera tilt, though real-world adaptability under diverse lighting and packaging conditions remains a challenge. Overall, the proposed system represents a practical, consumer-oriented tool for seafood authentication and freshness evaluation, with potential to enhance food safety and consumer protection. Full article

Plastic pollution has emerged as a pervasive and systemic driver of ecological and biogeochemical disruption in freshwater and marine environments. Unlike natural materials that circulate within closed biogeochemical loops, synthetic polymers predominantly follow unidirectional and irreversible trajectories, a phenomenon we describe as “irreversible plastic transport.” These flows culminate in sedimentary entrapment, where plastics persist as long-term ecological stressors and potential vectors of contaminant transfer. Recent global syntheses indicate that sedimentary microplastic loads can exceed 27,000 particles/kg dry weight in certain river systems, highlighting the urgency of sediment-inclusive risk assessments. This review synthesizes interdisciplinary findings to conceptualize plastics as both pollutants and governance challenges. We highlighted the dominant transport pathways of micro- and nanoplastics and emphasize that sedimentary sinks are critical long-term retention zones. Current monitoring frameworks often underestimate sedimentary burdens by focusing on surface water and overlooking subsurface ecological legacies. We propose an integrated governance approach combining cross-media monitoring, Earth system modeling, and adaptive policies to address these persistent synthetic agents. Embedding plastic dynamics within comprehensive risk assessment frameworks is essential for sustainable water management during the Anthropocene. Our synthesis supports risk-based decision-making and encourages proactive, transdisciplinary global governance strategies that integrate sediment-focused monitoring and long-term ecological risk management. Full article

The Watershed Sustainability Index (WSI) is a widely used parameter that provides an integrated assessment of the baseline state of watershed management, considering hydrology, environment, life, and policy. The impacts of climate change on sustainability are becoming increasingly evident. These impacts are discussed in the 6th Assessment Report of the Intergovernmental Panel on Climate Change (IPCC). This study refines the Watershed Sustainability Index (WSI) by embedding climate discontinuities from the IPCC AR6, applying dual climate scenarios (RCP4.5 and RCP8.5), and incorporating comprehensive sensitivity and uncertainty analyses. The approach provides a transferable basis for basin-scale management tools that integrate climate stressors, explore alternative futures, and support adaptive water governance. The impacts of climate change on watershed sustainability have been developed from hydrological, environmental, life, and policy perspectives with an innovative approach. The new WSI assessment methodology is implemented for the Central North Aegean Basin, Türkiye. The WSI was applied to two periods, including five years of baseline condition (2016–2020) and ten years of projected future condition (2021–2030). The future condition was assessed with climate change impacts. The study shows how WSI assessment under climate change considerations may support coordination among all relevant institutions and stakeholders responsible for natural resource management. This approach can be a valuable resource for decision-makers and provide an effective management tool for the basin, considering future conditions. Full article

Thermophilic microorganisms represent an untapped reservoir of thermostable biocatalysts and stress-resilient biomolecules for industrial biotechnology. Aeribacillus pallidus, a Gram-positive moderate thermophile, has attracted attention for its enzymatic versatility and environmental adaptability, yet its genomic potential remains underexplored. Here, we present a comparative genomic analysis of 13 A. pallidus strains to uncover conserved and strain-specific traits relevant to biotechnology. Genomes ranged from 3.24 to 4.98 Mb, with GC content largely conserved (~39%) except for GS3372 (57.4%), indicating possible horizontal gene transfer. All strains encoded complete central metabolic pathways, while carbohydrate-active enzyme profiling revealed abundant glycoside hydrolases and glycosyltransferases, with GS3372 and MHI3390 enriched for lignocellulose-degrading enzymes. Secondary metabolite mining identified diverse biosynthetic gene clusters, including terpenes, sactipeptides, and bacteriocins, with PI8, W-12, and 8m3 exhibiting the greatest biosynthetic diversity. A core set of heat shock and universal stress proteins underscored robust thermotolerance. Phylogenomic and pan-genome analyses revealed high intraspecific diversity and an open pan-genome structure. Collectively, these findings position A. pallidus as a promising thermophilic chassis organism for sustainable applications, including biomass conversion, biofuel production, bioremediation, and the synthesis of heat-stable antimicrobial agents. Full article

Background: Febrile neutropenia (FN) is a common and potentially life-threatening complication in pediatric oncology. Rapid initiation of empiric antibiotics is critical to improving prognosis. This study evaluated the impact of simple changes to a standard operating procedure (SOP) for FN treatment on the time-to-antibiotic (TTA) in pediatric cancer patients, as well as potential clinical effects. Methods: In this retrospective, single-center, cohort study, children with cancer presenting with FN at the emergency room (pedER) or oncology outpatient department (OD) were included over two one-year periods—before and after SOP adaption. The revised SOP defined a target TTA of ≤30 min. The primary endpoint was to compare median TTA and the proportion of FN episodes meeting target TTA. Secondary endpoints comprised adverse events (AEs) (e.g., ICU admission, need for respiratory or circulatory support, sepsis criteria). Results: After SOP adaption, 32.9% of episodes met target TTA, up from 5.9% before. Median TTA was significantly reduced (44 min vs. 93 min). The improvement persisted during the study period. AE rates showed no significant change. Conclusions: Simple procedural adjustments may significantly improve quality indicators of care, e.g., reducing TTA in pediatric FN patients. These adjustments may be transferable to other pediatric oncology settings. Full article

As the core refrigeration equipment in cooling systems, the operational state of chiller units is crucial for ship support, equipment cooling, and mission stability. However, because of their sensitivity and the complexity of operating environments, obtaining large volumes of complete, fault-labeled data is difficult in practical engineering appli-cations. This limitation makes it challenging for traditional data-driven approaches to deliver accurate fault diagnoses. Furthermore, data collected from different devices or under varying operating conditions often differ significantly in both feature dimensions and distributions, i.e., data heterogeneity, which further complicates model transfer. To address these challenges, this study proposes a deep transfer learning–based fault di-agnosis method designed to leverage abundant knowledge from the source domain while adaptively learning features of the target domain. Given the persistent difficulties in collecting sufficient high-quality labeled fault data, traditional data-driven models continue to face restricted diagnostic performance on target equipment. At the same time, data heterogeneity across devices or operating conditions intensifies the challenge of cross-domain knowledge transfer. To overcome these issues, this study develops a heterogeneous transfer learning method that integrates a dual-channel autoencoder, domain adversarial training, and pseudo-label self-training. This combination enables precise small-sample knowledge transfer from the source to the target domain. Specifi-cally, the dual-channel autoencoder is first applied to align heterogeneous feature di-mensions. Then, a Gradient Reversal Layer (GRL) and a domain discriminator are in-troduced to extract domain-invariant features. In parallel, high-confidence pseu-do-labeled samples from the target domain are incorporated into joint training to im-prove generalization and robustness. Experimental results confirm that the method achieves high fault diagnosis accuracy in typical industrial application scenarios, ena-bling effective identification of common faults in various types of chiller units under conventional operating conditions, the proposed method achieves higher accuracy and F1-scores in multi-class fault diagnosis tasks compared with both traditional approaches and existing transfer learning methods. These findings provide a novel perspective for advancing the intelligent operation and maintenance of chiller units. Full article

E-textiles, a type of textile integrated with conductive sensors, allows users to freely utilize any area of the body in a convenient and comfortable manner. Thus, interactions with e-textiles are attracting more and more attention, especially for text input. However, the functional aging of e-textiles affects the characteristics and even the quality of the captured signal, presenting serious challenges for character recognition. This paper focuses on studying the behavior of e-textile functional aging and alleviating its impact on text input with an unsupervised domain adaptation technique, named A²TEXT (aging-aware e-textile-based text input). We first designed a deep kernel-based two-sample test method to validate the impact of functional aging on handwriting with an e-textile input. Based on that, we introduced a so-called Gabor domain adaptation technique, which adopts a novel Gabor orientation filter in feature extraction under an adversarial domain adaptation framework. We demonstrated superior performance compared to traditional models in four different transfer tasks, validating the effectiveness of our work. Full article

Urban growth models often prioritize environmental and accessibility factors while underestimating behavioral and functional dynamics. This study develops a POI-enhanced Cellular Automata (CA) framework to simulate urban expansion by incorporating three semantic indicators derived from Point-of-Interest (POI) data—density (PD), diversity (PDI), and functional centrality (FC). Taking Yan’an, China, as a case, the model integrates these indicators with terrain and infrastructure variables via logistic regression to estimate land-use transition probabilities. To ensure robustness, spatial block cross-validation was adopted to reduce spatial autocorrelation bias. Results show that the POI-based model outperforms the baseline in both Kappa and Figure of Merit metrics. High-density and mixed-function POI zones correspond with compact infill growth, while high-centrality zones predict decentralized expansion beyond administrative cores. These findings highlight how functional semantics sharpen spatial prediction and uncover latent behavioral demand. Policy implications include using POI-informed maps for adaptive zoning, ecological buffer protection, and growth hotspot management. The study contributes a transferable workflow for embedding behavioral logic into spatial simulation. However, limitations remain: the model relies on static POI data, omits vertical (3D) development, and lacks direct comparison with alternative models like Random Forest or SVM. Future research could explore dynamic POI trajectories, integrate 3D building forms, or adopt agent-based modeling for richer institutional representation. Overall, the approach enhances both the accuracy and interpretability of urban growth modeling, providing a flexible tool for planning in functionally evolving and ecologically constrained cities. Full article

Rotating detonation engines (RDEs) are expected to have higher specific work and efficiency, but the high-temperature transonic flow delivered by the combustor poses relevant design and technological difficulties. This work proposes a 1D model for turbine internal cooling design which can be used to explore multiple design options during the preliminary design of the cooling system. Being based on an energy balance applied to an infinitesimal control volume, the model is general and can be adapted to other applications. The model is applied to design a cooling system for a pre-existing stator blade geometry. Both the inputs and the outputs of the 1D simulation are in good agreement with the values found in the literature. Subsequently, 1D results are compared to a full conjugate heat transfer (CHT) simulation. The agreement on the internal heat transfer coefficient is excellent and is entirely within the uncertainty of the correlation. Despite some criticality in finding agreement with the thermal power distribution, the Mach number, the total pressure drop, and the coolant temperature increase in the cooling channels are accurately predicted by the 1D code, thus confirming its value as a preliminary design tool. To guarantee the integrity of the blade at the extremities, a cooling solution with coolant injection at the leading and trailing edge is studied. A finite element analysis of the cooled blade ensures the structural feasibility of the cooling system. The computational economy of the 1D code is then exploited to perform a global sensitivity analysis using a polynomial chaos expansion (PCE) surrogate model to compute Sobol’ indices. Full article

Accurate estimation of chlorophyll and nitrogen content in tea leaves is essential for effective nutrient management. This study introduces a proof-of-concept dual-view RGB regression framework developed under controlled scanner conditions. Paired adaxial and abaxial images of Yun Kang 10 tea leaves were collected from four villages in Lincang, Yunnan, alongside corresponding soil and plant analyzer development (SPAD) and nitrogen measurements. A lightweight dual-input CoAtNet backbone with streamlined Bneck modules was designed, and three fusion strategies, Pre-fusion, Mid-fusion, and Late-fusion, were systematically compared. Ten-fold cross-validation revealed that Mid-fusion delivered the best performance ($R^2$ = 94.19% ± 1.75%, root mean square error ($RMSE$) = 3.84 ± 0.65, $MAE$ = 3.00 ± 0.45) with only 1.92 M parameters, outperforming both the single-view baseline and other compact models. Transferability was further validated on a combined smartphone–scanner dataset, where the framework maintained robust accuracy. Overall, these findings demonstrate a compact and effective system for non-destructive biochemical trait estimation, providing a strong foundation for future adaptation to field conditions and broader crop applications. Full article