Search Results (272)

In top-N recommendation, incorporating item-side information can improve ranking quality under sparse user–item interactions; however, common flat concatenation strategies may weaken the structural correspondence between user ratings and item attributes while simultaneously increasing model size. To address this issue, this study proposes DAERec-GCA, a deep autoencoder-based collaborative filtering framework that organizes rating signals and genre information in a genre-channel-aligned two-dimensional representation. The model applies shared weights across genre channels and aggregates channel outputs to generate item scores, enabling side-information integration without the parameter growth associated with flattened genre-aware formulations. The framework was evaluated on MovieLens-100K, 1M, and 10M under a warm-start five-fold cross-validation protocol using ranking-based metrics. In addition, a structured ablation study was conducted against ROnly, Flat1D, GenreProfile, GenreEmbed, and GenreGated, together with a controlled train-side sparsity analysis and a computational profiling analysis covering trainable parameters, epoch time, inference latency, and peak GPU memory. The results show that DAERec-GCA remains competitive across all three datasets and exhibits its clearest advantage under sparse and moderately sparse training conditions. The findings suggest that genre-channel alignment provides a practical trade-off between structural expressiveness, parameter efficiency, and recommendation quality in sparse recommendation settings. Full article

Objectives: Despite the widespread availability of digital clinical information, timely access to relevant biomedical evidence during routine consultations remains limited in practice. Primary care clinicians, in particular, face significant time constraints that make it difficult to integrate comprehensive literature searches into everyday workflows. This study evaluates whether an ontology-based recommender system can support routine clinical workflows by reducing information retrieval time while preserving the clinically acceptable usefulness of retrieved evidence. We assessed the performance of the HOPE (Health Operation for Personalised Evidence) system compared with realistic manual PubMed searches conducted by physicians. Materials and Methods: We conducted an observational evaluation involving 50 primary care physicians, who independently assessed 30 anonymised, rewritten clinical cases representative of common primary care scenarios. HOPE automatically extracted biomedical concepts from case descriptions using natural language processing and mapped them to Unified Medical Language System (UMLS) ontologies to generate ranked PubMed recommendations. A subset of 10 physicians also conducted manual PubMed searches in line with their usual clinical practice. Article relevance was assessed using a predefined binary criterion, and a reference relevance set was established by consensus among three senior physicians using a pooled document set. Retrieval performance was evaluated using Precision@k, relative Recall@k, and Normalised Discounted Cumulative Gain (NDCG@k). Manual search time was measured using a standardised stopwatch protocol, whereas HOPE response time was logged automatically by the system. Results: Inter-physician agreement in relevance assessment was substantial (Fleiss’ κ = 0.66; 95% CI: 0.61–0.70). HOPE achieved moderate-to-high precision within the top-ranked results (Precision@3 = 0.72), with relative recall increasing as additional documents were considered. Ranking metrics indicated that relevant articles were generally positioned early in the result lists. The mean total retrieval time for manual PubMed searches was 13.3 ± 1.7 min per case, compared with 17.4 ± 2.1 s for HOPE-assisted retrieval (p < 0.001). Conclusions: In a controlled, workflow-oriented evaluation using synthetic clinical cases, HOPE substantially reduced information retrieval time while maintaining clinically acceptable relevance in the retrieved literature. These findings support the use of ontology-based, AI-assisted systems as workflow-support tools to facilitate timely access to biomedical evidence, without replacing clinical judgment. Full article

Natural food-derived proteins are increasingly explored as alternatives to synthetic inhibitors for managing Type 2 diabetes mellitus. Despite the recognized health-promoting properties of Morchella esculenta, the potential of its bioactive proteins to modulate glucose metabolism remains largely unexplored. This study systematically investigated the structural basis and hypoglycemic mechanisms of MEP5 (Morchella esculenta Protein 5), a fucose-specific lectin from M. esculenta, using an integrated in silico pipeline. MEP5 (33.12 kDa) adopts a stable β-sheet-rich conformation and harbors a conserved fucose-binding carbohydrate-recognition domain. Protein–protein docking revealed that intact MEP5 binds directly to surface glycans of human α-glucosidase, generating steric hindrance that obstructs the catalytic pocket. Simulated gastrointestinal digestion yielded a highly bioavailable peptide profile. Following a rigorous multiparametric screening for toxicity, allergenicity, and water solubility, 11 short oligopeptides were identified as potent dipeptidyl peptidase-IV (DPP-IV) inhibitors. Molecular docking demonstrated that the top-ranked peptides, QPPR, DGTY, and DPDSH, occupy the S2 pocket of DPP-IV and form hydrogen bonds with catalytic triad residues (Ser630/His740). These findings delineate a dual-stage hypoglycemic mechanism, pre-digestion enzymatic blockade and post-digestion incretin regulation, and support the potential of MEP5 as a multifunctional candidate for glucose homeostasis-oriented functional foods. Full article

Variable cross-section cement–soil pipe piles are an innovative soft ground improvement technology. They are tubular, special-shaped cement–soil mixing piles characterized by a tapered profile along the pile shaft (larger diameter at the top and smaller at the bottom) and an internal soil core. They offer advantages including reduced material consumption, lower engineering cost, and shorter construction duration. However, the systematic theoretical understanding of their bearing performance remains insufficient. In this study, the bearing mechanism and influencing parameters of variable cross-section pipe piles were systematically investigated via full-scale field tests, numerical simulations, and laboratory model tests. An exponential decay constitutive model considering the strain-softening behavior of cement–soil was developed and implemented through secondary development in the ABAQUS platform for parametric analysis. Laboratory model tests were further conducted to advance the understanding of the bearing mechanism of variable cross-section pipe piles. The results show that the ultimate bearing capacity of the proposed variable cross-section cement–soil pipe pile is approximately 189% higher than that of the conventional ones. The expanded outer diameter and expanded height are the dominant factors affecting the bearing capacity, while the inner diameter and pile length have a comparatively minimal influence: increasing the expanded outer diameter from 0.6 m to 1.2 m and the expanded height from 0 m to 5 m increased the ultimate bearing capacity from 445 kN to 868 kN and 936 kN, respectively. The effective pile length is determined to be 6 m, and the recommended minimum wall thickness of the pipe pile is 1/4 of the inner diameter. Laboratory tests further demonstrated an abrupt change in axial force at the variable section. The findings provide reliable theoretical support for the engineering design and field application of cement–soil variable cross-section pipe piles. Full article

Large-scale chest X-ray (CXR) datasets often rely on report-derived or weak labels, introducing missing and incorrect annotations that can degrade downstream models and limit trust. We study training-free mislabel detection in multi-label CXRs by scoring neighborhood label consistency in a fixed embedding space. Using the NIH Chest X-ray Kaggle sample (5606 CXRs), we extract intermediate CoAtNet features and obtain 64-dimensional embeddings with a frozen CoAtNet backbone and a lightweight refinement head. On top of these embeddings, we compare kNN consistency baselines with distance weighting and label-set similarity against LPV-DW-CS, clustered prototype voting weighted by distance and cluster support. We evaluate three synthetic label-noise regimes with review budgets matched to the corruption rate: random single-label (5% and 20%), boundary-noise (20% corruption within the lowest-density 20% subset), and disjoint-label replacement (20% within that subset). LPV-DW-CS yields the highest downstream macro-AUROC after filtering top-ranked samples (up to 0.8860), while kNN variants achieve higher Recall@budget at the same review rates (up to 99.44%). An image-only expert Likert review of top-ranked real samples finds substantial label-set inconsistencies (54.1% for LPV-DW-CS-280-A; 60.5% for KNN-DW-LSS), supporting neighborhood-consistency ranking as a practical, training-free tool for targeted dataset auditing. Full article

We present the performance of a middle atmosphere Rayleigh lidar system that employs three receiver channels. We characterize the biases in the density and temperature profiles retrieved from each of the receiver channels as well as the combined receiver signal. We associate these biases with pulse pile-up, gain switching, and variations in the detector gain due to signal amplitude. We use a top-down temperature convergence methodology to determine the upper altitude up to which the signals should be compensated for the variations in detector gain. We find that the channels have warm biases in their temperatures of 2–8 K at 40 km. These biases decrease to between 1 K and 3 K at 60 km. Uncertainty estimates derived from the photon-counting statistics indicate temperature uncertainties on the order of 2–5 K in the 40–70 km region, which are consistent with the observed level of inter-channel variability after correction. A comparison with MERRA-2 reanalysis indicates an overall agreement in temperatures and differences that are consistent with the comparisons between the Rayleigh lidars and MERRA-02 at other sites. These results demonstrate that the proposed approach proves reliable for processing the multi-channel Rayleigh lidar data, particularly for systems employing more than two detection channels, and improves the fidelity and accuracy of the temperature retrievals. Full article

This work presents an evaluation of the effectiveness of active ventilation methods compared to passive ventilation methods in a typical B + GF + 9 building, focusing on the impact of burner height location on smoke control performance. The numerical model was validated using a full-scale room fire experiment involving a 4350 kJ/s wood crib load, where the HRR was calibrated via the mass loss method, achieving an RMSE of 210 kW and MRE of 5.04%. FDS simulations were conducted across six scenarios involving burners on the ground, fifth, and ninth floors. The findings demonstrate that, while natural ventilation allows the stairwell to reach lethal conditions with temperatures exceeding 180 °C and CO concentrations above 0.24%, the implementation of top-level mechanical pressurization maintains temperatures below the 60 °C tenability threshold. The mechanical ventilation system extended the Available Safe Egress Time (ASET) by 75% to 110%, with effectiveness increasing as the burner elevation approached the fan location. Overall, the study provides a validated approach for transforming stairwells into protected refuge zones in existing mid-rise buildings. Overall, merging empirical with computational methods is a proven basis for simulating scaled-up, complicated layouts. This guarantees accurate initial conditions when analyzing urban fire emergencies. Full article

Digital transformation is reshaping societies by promoting the adoption of advanced technologies. Moreover, the digitization of public services has become an important focus for governments. In this paper, digital government performance indicators are analyzed to improve the efficiency of digitizing public services. Based on this awareness, the seven main criteria and twenty-one sub-criteria are determined. Then, a fuzzy decision-making framework is proposed to evaluate digital government performance across 165 countries as alternatives. To the best of our knowledge, limited studies have investigated an integrated clustering-based fuzzy decision-making framework for evaluating digital government performance. The intuitionistic trapezoidal fuzzy number-based analytical hierarchy process (ITFNAHP), a part of the introduced framework, is developed to find the weights of the main criteria and sub-criteria. Digital technologies, innovation, and the economy are the most significant criteria for digital government operations. The k-means clustering method is then employed to group the alternatives. The four clusters are obtained from the clustering technique. Next, the technique of order preference similarity to ideal solution (TOPSIS) is introduced to rank the digital governments of each cluster. Switzerland, Rwanda, North Macedonia, and Eswatini are the top choices among others in each cluster, respectively. Additionally, a sensitivity analysis is conducted considering the ten different situations. In addition, the managerial and policy implications are discussed, including the achievement of Sustainable Development Goals (SDGs). Full article

Historic buildings often exhibit high energy use intensity (EUI), while conservation constraints limit envelope retrofits, making it difficult to identify robust and actionable operational predictors. Using four in-use historic buildings in Shenyang, China, this study presents a pilot methodological demonstration with a controlled-comparability workflow consisting of two linked layers: (i) a Driver layer of intervenable operational variables and (ii) a Pathway layer of calibrated EnergyPlus heat-balance terms for physics-informed interpretation. Three importance approaches (Spearman, wrapper RFE with XGBoost, and Random Forest) are compared; rankings are fused via reciprocal rank fusion, and stability is tested using cross-period rolling validation across Top-K feature sets. After similarity screening, EUI variation is better explained by operational predictors and the corresponding simulated loss channels than by macro-scale structural heterogeneity. Infiltration-related indicators and envelope/infiltration loss components remain consistently prominent, while Spearman importance is less stable in the Pathway layer under seasonal switching and nonlinear coupling. A Top-10 subset provides a favorable accuracy–stability trade-off. The proposed Driver–Pathway mapping supports conservation-compatible prioritization hypotheses within a simulation-consistent interpretive framework; findings are associational and context dependent and should be validated through field measurements and experimental or quasi-experimental studies before prescriptive claims are made. Full article

The presence of an unbalanced gut microbiome and the dysregulation of bile acid signalling are considered pivotal causes of various inflammation-based diseases. The Takeda G protein-coupled receptor (TGR5), TGR5 is a bile acid-responsive receptor that modulates inflammatory signalling pathways, making it an enticing molecular target for the discovery of novel anti-inflammatory agents. Herein, a comprehensive in silico approach was employed to identify potential TGR5 agonists from sterol-rich phytocompounds present in Triphala, a traditional polyherbal formulation. Using in silico computational methods, such as molecular docking and molecular dynamics simulations (MDS), we screened the putative agonistic potential of 10 phytocompounds obtained from Terminalia chebula, Terminalia bellirica, and Phyllanthus emblica against the crystal structure of human TGR5 (PDB ID: 7XTQ). Based on binding energy and molecular interactions, ergosterol (−12.34 ± 0.17 kcal/mol) and stigmasterol (−10.35 ± 0.04 kcal/mol) were predicted to be the top and best compounds. Furthermore, the stability of these two compounds in the docked complex was analysed using MDS for 200 ns. The mean Cα RMSD values were 0.22 ± 0.02 nm for both ergosterol- and stigmasterol-bound complexes, compared to 0.21 ± 0.02 nm for the unbound apo protein. Further, the molecular mechanics/Poisson–Boltzmann surface area (MMPBSA) analysis revealed that ergosterol exhibited binding free energy (−139.868 ± 12.318 kJ/mol) comparable to that of the co-crystallised ligand R399 −93.424 ± 8.919 kJ/mol. In silico ADMET predictions indicated acceptable drug-like properties and low toxicity for both compounds. Collectively, these computational findings suggest that ergosterol is a promising putative TGR5 agonist, warranting further experimental validation of its potential role in modulating inflammation-related pathways. Full article

Background/Objectives: This study aims to develop a comprehensive Clinical Decision Support System (CDSS) that integrates multi-sequence sacroiliac joint (SIJ) MRIs with rheumatological, clinical, and laboratory findings into the decision-making process for the early diagnosis of axial spondyloarthritis (axSpA), incorporating segmentation-supported explainability. Methods: Multi-sequence SIJ MRI data (T1-WI, T2-WI, STIR, and PD-WI) were analysed from 367 participants (n = 193 axSpA; n = 174 non-axSpA controls). Sequence-based classification was performed using VGG16, ResNet50, DenseNet121, and InceptionV3 models; additionally, a lightweight and parameter-efficient SacroNet architecture was developed. Slice-level probability scores were converted to patient-level scores using the Dynamic Top-K Averaging method. Image-based scores were combined with a logistic regression-based clinical risk score using weighted linear integration (0.60 image/0.40 clinical) and a conservative threshold (τ = 0.70). Grad-CAM was applied for visual interpretability. Furthermore, to support the diagnostic outcomes with precise spatial data, active inflammation in STIR and T2-WI sequences was segmented. For this purpose, the MDC-UNet model was employed and compared with baseline U-Net derivatives. Results: Sequence-specific analysis showed VGG16 performing best on T1-WI (AUC = 0.920; Accuracy = 0.878) and DenseNet121 on STIR (AUC = 0.793; Accuracy = 0.771). The SacroNet architecture provided competitive classification performance at the patient level despite its low number of parameters (~110 K). Furthermore, MDC-UNet successfully segmented active inflammation, yielding Dice scores of 0.752 (HD95: 19.25) for STIR and 0.682 (HD95: 26.21) for T2-WI. Conclusions: The findings demonstrate that patient-level decision integration based on multi-sequence MRI, when used in conjunction with clinical risk scoring and segmentation-assisted interpretability, can provide a feasible and interpretable DSS framework for the early diagnosis of axSpA. Full article

Background: Klebsiella pneumoniae is a Gram-negative bacterium that is found in human microbiota and in diverse environments. This opportunistic pathogen exhibits a highly variable genetic background and is responsible for a broad range of hospital- and community-acquired, multidrug-resistant infections worldwide. To track transmission pathways and understand genetic diversity, single-nucleotide polymorphism (SNP) clustering has become an essential tool. Methods: This study examines data from 2018 to 2024 in the NCBI Pathogen Detection database to determine the temporal and spatial distribution of SNP clusters in clinical K. pneumoniae across Middle East and North Africa (MENA) countries. Results: Among 1858 isolates, a heterogeneous population structure was observed. Of the 478 identified SNP clusters, a few dominant clusters accounted for 37% of the isolates, and numerous low-frequency lineages were detected. The descriptive yearly snapshot revealed a diverse representation of top clusters. Geographical analysis showed the presence of both localized and limited cross-border distribution patterns. Countries with diverse clusters also exhibit higher diversity of carbapenem- and ESBL-resistant genes. Conclusions: These findings provide valuable insights into the dominant, regionally concentrated K. pneumoniae lineage across MENA countries, assisting future genomic surveillance and efforts to combat clinical K. pneumoniae infections in this region. Full article

Generative AI systems increasingly mediate how students retrieve literature and generate citations, shifting methodological rigor toward the maintenance of an auditable evidence trail. This study audits the search stage of AI-assisted literature review work, focusing on retrieval performance and citation traceability rather than downstream screening or synthesis. Four widely accessible tools were compared across two retrieval postures, and Boolean queries were executed against Scopus and evaluated against a DOI-verified librarian baseline built from Scopus, Web of Science, and Google Scholar. Using a canonical prompt and a bounded top-k capture rule (k = 20), each bibliographic record was evaluated for DOI traceability, DOI resolution integrity, metadata accuracy, and run-to-run drift. Records were screened through staged title/abstract and full-text eligibility review, and the final set included 37 studies after quality appraisal was 37 studies. Across sixteen audit runs, natural-language prompting frequently produced under-target yields, recurrent integrity failures, and low overlap with the librarian benchmark. Boolean translation improved run completion and increased the proportion of auditable records, but reproducibility remained unstable across repeated runs. These findings show that correctness at the record level does not ensure stability at the evidence-set level. Limitations include the bounded tool set, the search-stage focus, and the absence of downstream screening or synthesis evaluation. Retrieval posture, therefore, emerges as a practical governance lever for AI-assisted literature review workflows and supports the use of a student-facing verification checklist anchored in DOI verification and transparent protocol capture. This research received no external funding. OSF registration: Open Science Framework, 10.17605/OSF.IO/U8NHT. The manuscript reports the final included set as n = 37, states no external funding, and lists the OSF registration DOI. Full article

Next Point-of-Interest (POI) recommendation focuses on predicting a user’s subsequent location based on historical check-in data. In practice, however, check-in logs frequently contain uncertain records in which ambiguous spatial, temporal, or behavioral information obscures the underlying mobility regularities, thereby degrading prediction performance. To address this challenge, this study first infers user preferences from historical trajectories and reweights transition importance based on temporal and spatial proximity. It then models transition relationships using three complementary feature dimensions: POI category, spatial area, and routine versus non-routine behavioral patterns. Using transition probability analysis, feature-level dependencies in user mobility are systematically investigated. The findings demonstrate that these transition features contribute unevenly to predictive performance, with area-based transitions yielding the strongest results when used in isolation. Nonetheless, their joint integration consistently achieves the highest accuracy, underscoring the critical role of transition-aware modeling. Across two real-world datasets, the proposed framework consistently achieves state-of-the-art performance in top-ranked accuracy (Recall@1) and ranking quality (NDCG@1), while delivering competitive effectiveness at higher cutoff values ($k=3$ and $k=5$). Notably, on the NYC dataset, MTF-POI achieves the highest Recall@1 (+19.01% over the strongest baseline) with a marginal trade-off at Recall@3, reflecting the framework’s design emphasis on precise next-step prediction. Full article

The Eocene Pinghu Formation in the Xihu Depression, East China Sea Shelf Basin, is a key coal-bearing unit for offshore China’s petroleum exploration. However, the mechanisms of coal accumulation controlled by astronomical cycles and the stacking patterns of coal seams remain underexplored. Recent studies using wavelet analysis have highlighted the need for further investigation into the role of Milankovitch cycles in coal formation. This study uses natural gamma-ray logging data from Well K and applies cyclic stratigraphy to investigate how astronomical orbital cycles control coal seam development, identifying the link between cyclic stratigraphy and coal accumulation, and the distribution patterns of coal seams across different cycle levels. The top of the Pinghu Formation was used as the astronomical anchor, and tuning was conducted from top to base following a “cycle identification–anchor tying–astronomical tuning” workflow. The resulting astronomical timescale indicates a depositional duration of 8.17 Ma. COCO/eCOCO analyses with 5000 Monte Carlo simulations (sedimentation-rate range: 7–11 cm/kyr; step: 0.1 cm/kyr) yield a mean sedimentation rate of 9 cm/kyr. Coal accumulation is influenced by Milankovitch cycles. High eccentricity periods correspond to warmer climates that promote coal development, while low eccentricity phases synchronize with optimal climatic conditions for coal formation. Based on these findings, this study proposes a coal seam development model for the Pinghu Formation in Area A of the Xihu Depression, offering insights for cyclic stratigraphy and coal accumulation research in similar basins and supporting sustainable development of coal-bearing strata in the East China Sea Basin. Full article