Search Results (695)

The paper presents a model for the design and management of metadata that enables the efficient compilation of specialised datasets from large, heterogeneous data collections. The metadata are represented as a typed property graph that facilitates the FAIR principles in data compilation: Findable, Accessible, Interoperable, Reusable. The representation is general and independent of the modality and format of the data. The graph-based design of the metadata supports the incremental extension of categories and relationships without requiring the migration of existing data. Its feasibility is demonstrated through the use of a graph database, in which the metadata for 689,645 Bulgarian textual data units are combined with a web-based filtering interface. Metadata retrieval is implemented through Cypher queries executed as graph traversals, enabling the extraction of thematic and application-oriented data subsets based on combinations of selection criteria. The application validates the suitability of the graph-based metadata design for compiling specialised datasets for training and fine-tuning large language models and other NLP applications. Full article

This study presents a comprehensive multidimensional analysis of pedestrian accidents in Amman, Jordan, from 2014 to 2023. By integrating spatial, temporal, and statistical techniques, the research identifies critical risk patterns to inform evidence-based safety interventions. Characterizing a decade-long database of 14,821 cases, the study utilizes radar graphs, Kernel Density Estimation (KDE), and DBSCAN cluster analysis to delineate high-risk zones and temporal peaks. Temporal findings indicate that Thursdays recorded the highest accident frequency (2382 cases), with peak occurrences between 17:00 and 23:00. Spatial clustering identified five significant high-risk zones, with Central Amman emerging as the primary critical area. The study’s novelty lies in being the first in the Jordanian context to bridge accident frequency with severity mechanisms by integrating advanced spatial clustering and KDE with a robust Ordered Logit Model. Severity analysis reveals that while 59.34% of incidents resulted in minimal injuries, fatalities accounted for 5.02%. The model demonstrates that injury outcomes are systematically associated with traffic dynamics and behavior rather than environmental factors. Speed-related driver error was identified as the strongest predictor of severe outcomes (OR = 81.3). Significant dependencies were confirmed between vehicle category and road type (χ² = 2182.20, p < 0.001), lighting and road surface (χ² = 76.21, p < 0.001), and vehicle type and lighting (χ² = 148.52, p < 0.001). The study proposes a multi-layered framework combining site-specific nodal improvements with corridor-level strategies to enhance urban safety in Amman City. Full article

Non-Revenue Water (NRW) from leakage represents a major global economic and environmental challenge for urban utilities. While Deep Learning (DL) offers transformative potential for leak detection in Water Distribution Systems (WDSs) and existing reviews provide critical assessments, a consolidated, quantitative evaluation of real-world applicability and performance consistency that is actionable for engineering practice remains absent. This systematic review critically evaluates DL applications for WDS leak detection and localisation, with a focused analysis of model accuracy in relation to data types, methodological rigour, and the validation gap between controlled experiments and operational deployment. Following the Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA) framework, a systematic literature search was performed using Scopus, Web of Science, Google Scholar, ScienceDirect, Taylor & Francis, and MDPI databases for publications spanning the period from 2015 to 2025. From an initial 5265 records, 72 studies met the inclusion criteria for qualitative synthesis. Analysis revealed a specialisation of DL architectures by data modality: Convolutional Neural Networks (CNNs) applied to acoustic or vibration data yield the highest reported accuracy for direct leak identification; Long Short-Term Memory (LSTM) and Transformer models are predominant for temporal hydraulic data (pressure and flow); and Graph Neural Networks (GNNs) excel with topological data for state estimation. While reported accuracy is often high, performance is highly contingent on data quality and pre-processing. A significant disparity exists between results on synthetic versus real-world validation datasets, ranging from a decline of approximately 3 to 30 percentage points, with reported real-world accuracy spanning 70 to 79.7 percent. Moreover, DL demonstrates a paradigm shift in technical capability for leak management. However, transitioning to reliable field applications requires overcoming key challenges: standardising benchmarks and performance reporting, improving model generalisability and explainability, and fostering integration within practical Digital Twin (DT) frameworks to enable proactive infrastructure management. Full article

Clinical question answering over electronic health records (EHRs) increasingly relies on large language model (LLM) agents that retrieve structured patient data through external tools. Published benchmarks, however, evaluate these systems at a single patient-population size, and rarely measure the effect of backend representation from that of the retrieval interface design. This paper compares six retrieval configurations that vary along two axes: backend (a property graph database, a relational database and a dense vector index) and interface design (curated domain-specific tool calls, model-generated queries, full-text search, and single-shot dense retrieval). The evaluation covers a 334-question bank spanning six categories (simple lookup, multi-hop, temporal, cohort, reasoning, and unanswerable), instantiated at three nested population scales: 200, 2000, and 20,000 alive patients from a single Synthea cohort. Four models are compared: Claude Haiku 4.5, Qwen 2.5 72B, Llama 3.1 8B, and Llama 3.3 70B, spanning closed-frontier and open-source alternatives. Curated tool-calling configurations improve accuracy over retrieval-augmented baselines for capable models, but reduce accuracy for a small open-source model due to function-calling protocol failures. We report how accuracy, latency, and cost evolve with each approach, model size, and cohort size, supported by paired statistical tests and confidence intervals. All benchmark components, databases, and evaluation code are publicly available. Full article

Background: Retinoblastoma (RB) is a rare pediatric malignancy characterized by small sample sizes and low event rates, where conventional association-driven feature selection may lead to unstable models, overadjustment, and limited generalizability. However, existing survival prediction studies lack a careful treatment of feature selection that accounts for underlying causal structure. Objectives: To develop and validate a causality-guided machine learning model for RB survival prediction by jointly incorporating survival time and survival status as outcome variables. Methods: We analyzed 1015 RB patients from the SEER database (1975–2020). A causality-informed feature selection framework was developed to address the challenges of rare-disease data. Specifically, candidate variables were evaluated through a three-step evidence-integration process: (1) univariate Cox proportional hazards (CPH) analysis for initial statistical screening; (2) causal structure learning using the PC algorithm on the variables retained from Step 1 to construct a directed acyclic graph (DAG) and exclude structurally inappropriate variables (colliders or descendants of the outcome); and (3) LASSO-based feature screening performed independently on the full set of candidate variables. The final features were obtained by taking the intersection of the variables retained from Step 2 and Step 3. Survival models were then trained using the selected features, with model comparison performed as a secondary step. Results: The proposed framework consistently identified four structurally and prognostically robust predictors—laterality, “SEER historic stage A”, “RX Summ”, and sequence number—through this evidence-integration process. Compared with conventional approaches, the causality-informed framework reduced the feature set while improving model stability and interpretability. Notably, compared with LASSO-only selection, which retained a larger set of variables, the causality-informed approach yielded a more parsimonious feature set with improved predictive performance, suggesting reduced overfitting in a low-event setting. Survival models trained on this refined feature set demonstrated reliable predictive performance, with the random survival forest achieving the highest discrimination (C-index = 0.739). Importantly, the selected predictors aligned with clinically plausible pathways in the learned DAG, supporting their causal relevance. Conclusions: This study demonstrates that incorporating causal structure into feature selection provides a more reliable and interpretable foundation for survival modeling in retinoblastoma. Rather than focusing on algorithmic comparison alone, our findings highlight that careful, causality-informed feature selection is critical for improving robustness in rare-disease prediction tasks. This framework may serve as a generalizable methodological template for other rare clinical settings prone to spurious associations. Full article

In the digital transformation of the petroleum industry, massive multi-source heterogeneous tables are distributed across databases, Word documents, PDF reports, and engineering systems. Their unstructured format and weakly expressed inter-table relationships make it difficult for conventional keyword-based or single-table retrieval methods to locate the complete set of tables needed for complex queries. To address this problem, this paper proposes Relatab, a multi-table retrieval framework based on implicit association reasoning. Relatab first estimates query–table relevance through a dual-level semantic matching mechanism that combines table-level signals, including captions and column names, with value-level signals weighted by entropy and CRITIC criteria. It then constructs an implicit table graph using column-name and column-content similarity, and applies a max-product multi-hop propagation rule with decay and pruning to identify complementary tables that are not directly matched by the query. Finally, direct relevance and inter-table complementarity are fused to produce the retrieved table set. Experiments on Spider, Bird, and CementingTables show that Relatab achieves Top-2 recall rates of 79.21%, 61.26%, and 77.88%, respectively, outperforming DTR by 1.74, 2.33, and 1.85 percentage points. The results indicate that explicit modeling of implicit inter-table associations improves retrieval coverage in complex multi-table scenarios while remaining applicable to petroleum-domain documents. Full article

Assembling expert teams under strict skill-coverage and communication-distance constraints is a fundamental challenge in collaborative knowledge work. Existing learning-based approaches excel at probabilistic link prediction but cannot reliably enforce hard logical constraints or provide interpretable justifications. This study presents a constructive heuristic framework for team formation on Heterogeneous Information Networks (HINs), integrating authors, papers, departments, and organizations into a unified graph database. Seven algorithms exploit distinct structural features—topological proximity, co-authorship history, organizational affiliation, citation impact, and temporal recency—and guarantee constraint satisfaction by construction. Experiments on a subset of the AMiner DBLP dataset (≈625,000 nodes, 973,000 edges) covering 12,045 formation requests across 147 configurations show that algorithm choice is the dominant determinant of runtime, while skill frequency governs feasibility: success rates decline from 81.2% under abundant keywords to 14.9% in the long tail. Algorithms further form statistically distinct clusters in communication cost, and specialized heuristics operate in nearly disjoint solution spaces—supporting a toolbox approach over single-algorithm deployment. These results provide actionable selection guidance: proximity-based algorithms for communication-efficient teams; citation- or recency-aware algorithms when impact matters; cohesion-based algorithms when internal collaboration is the priority. Full article

The outbreak of coronavirus disease 2019 (COVID-19), caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), has emerged as one of the most significant global health crises in recent history. Coronaviruses are a diverse group of RNA viruses classified into alpha, beta, gamma, and delta genera, with SARS-CoV-2 belonging to the beta-coronavirus family. The virus exhibits high transmissibility and causes a wide spectrum of clinical manifestations ranging from mild respiratory symptoms to severe complications such as acute respiratory distress syndrome, multi-organ failure, and death, particularly among elderly and immunocompromised individuals. Structurally, SARS-CoV-2 possesses a large single-stranded RNA genome encoding major structural proteins, including spike (S), envelope (E), membrane (M), and nucleocapsid (N) proteins, which play critical roles in host-cell recognition and viral infection. Understanding the molecular mechanisms of virus–host interactions, especially protein–protein interactions (PPIs), is essential for uncovering viral pathogenesis and identifying potential therapeutic targets. Traditional experimental techniques for PPI detection, such as yeast two-hybrid and affinity purification methods, are often expensive, labor-intensive, and prone to inaccuracies. Consequently, computational approaches based on machine learning (ML) and deep learning (DL) have gained significant attention for efficient and scalable PPI prediction. These methods use diverse biological information, including protein sequences, structural features, genomic data, Gene Ontology annotations, and interaction networks, to model complex biological relationships. This survey reviews computational approaches to PPI prediction, highlighting ML- and DL-based techniques, methodological advances, performance evaluation practices, and limitations that affect benchmark comparability. It also discusses biological databases and data sources commonly used in PPI studies and explicitly considers how models trained in coronavirus-centered settings may generalize to other viral families with different mechanisms of host interaction. Full article

Short-term airport traffic forecasting faces a structural gap: temporal ensemble models ignore route-network dependencies that shape hub operations, while deep graph neural networks require synchronised multi-airport operational data streams unavailable to single-airport operators, who have access only to their own operational records and publicly available route topology. To our knowledge, this study provides the first systematic evaluation of three graph representation classes—centrality measures, DeepWalk, and Node2Vec—as structural augmentations to Random Forest (RF), XGBoost, and LightGBM for hourly aircraft movement prediction at King Khalid International Airport (RUH), using a two-hop aviation graph combining RUH operational data with the OpenFlights database. Across all three ensemble families, random-walk graph augmentations consistently reduce MAE by approximately 9–17% relative to temporal-only baselines, whereas handcrafted centrality measures provide smaller and less consistent gains. Diebold–Mariano tests confirm that both RF+DeepWalk and RF+Node2Vec significantly outperform all nine baseline models ($p<0.05$), while no statistically significant difference is observed between the two embedding methods within any ensemble family, indicating that the benefit arises from the class of random-walk representations rather than a specific algorithm. RF+DeepWalk achieves the lowest observed MAE of 1.810 (RMSE = 2.481, sMAPE = 6.17%). SHAP analysis indicates that graph embedding dimensions rank among the top predictors, suggesting that they capture structural signal absent from temporal features. Full article

To address the residual lateral coil misalignment after an unmanned aerial vehicle (UAV) lands on a fixed wireless-charging platform, this study proposes a graph-attention-based knowledge distillation method for embedded self-alignment localization. Four detection-coil voltages form an induced-voltage fingerprint database organized as a multi-scale spatial graph. A graph attention network (GAT) teacher model is trained offline to learn neighborhood correlations in the voltage–position mapping, and its spatial knowledge is distilled into a lightweight Tiny-MLP student model for microcontroller unit (MCU)-based online inference. Experimental results show that the GAT teacher achieves a mean absolute error (MAE) of 0.589 cm, while the distilled Tiny-MLP reduces the MAE of the directly trained Tiny-MLP from 1.548 cm to 1.148 cm (a 25.8% reduction under a fixed seed). In 2000 closed-loop alignment trials with random initial positions, the system achieves an 85.5% success rate under a 0.5 cm threshold, indicating that the method supports low-complexity closed-loop self-alignment for UAV wireless charging. Full article

This study proposes VulnPattern-TKG, an end-to-end temporal knowledge graph framework that forecasts the emergence of CVE-derived vulnerability-pattern relations from Common Vulnerabilities and Exposures (CVE) descriptions. The framework does not aim to predict the real-world exploitation of individual CVEs; instead, it models how standardized relations among Weakness Factor (WF), Exploitation Outcome (EO), and Exploitation Prerequisite (EP) categories evolve over time in vulnerability disclosure text. It processes 205,600 National Vulnerability Database (NVD) CVE descriptions from 2014 to 2024 using a hybrid pipeline combining SecureBERT+CRF-based entity extraction, dependency-parsing-based relation rules, and four-stage hierarchical standardization. The resulting compact Knowledge Layer contains 26 standardized category nodes and 48,371 confidence-filtered triples. VulnTEC is a lightweight confidence- and time-weighted Node2Vec graph embedding framework that ranks relation-compatible candidate tails using cosine similarity over shared node embeddings. An internal four-component priority-score framework, integrating prediction confidence, temporal rise, exploitation-prerequisite prevalence-risk proxy, and extraction confidence, supports an analyst-side review of the forecasted relations. Under the novel-only triggers evaluation, VulnTEC achieves a mean MRR of 0.410 ± 0.020; however, the theoretical random baseline already reaches 0.408 because the candidate tail space contains only six EO categories. The results are interpreted as directional ranking evidence, and query-level Top-K results are reported only as descriptive analyst-side review evidence. Full article

In modern cloud-native systems, a single root cause can trigger cascading anomalies across multiple entities (e.g., microservices, databases, and hosts), generating alert storms with hundreds or thousands of heterogeneous alerts. Alert convergence (automatically grouping these alerts into actionable incident tickets) is critical for reducing operator burden and recovery time. Existing graph-based methods construct a topological graph from known entity dependencies and then leverage Graph Neural Networks (GNNs) for information propagation, but they rely on static physical topologies that fail to capture implicit fault propagation paths. Large Language Model (LLM)-based methods focus on reasoning about the textual information of alerts, yet they do not incorporate global topological structure and struggle with consistency at scale. Motivated by these limitations, we propose LLM-Guided Graph Structure Learning (LLM-GSL), a novel framework that combines the semantic reasoning ability of LLMs with the structural modeling power of GNNs for alert convergence. Specifically, LLM-GSL first leverages an LLM to evaluate pairwise entity relationships and discover implicit fault propagation paths that are absent from static topologies, thereby enhancing the physical-topology graph into a more complete structure. A Graph Attention Network (GAT) then refines alert representations over this enhanced graph via graph message passing, guided by a self-supervised graph affinity loss with continuous multi-modal supervision targets that fuse adjacency structure, textual affinity, and temporal affinity. Finally, density-based clustering groups the learned representations into incident tickets. Experiments on five public datasets, including four LogHub-derived datasets and one RCAEval microservice fault-injection subset, demonstrate that LLM-GSL achieves an average F1-score of 96.2%, outperforming six baselines including both traditional clustering and LLM-based methods by at least 14.0 percentage points. Full article

Human Activity Recognition (HAR) is the automated process of identifying human actions using sensor data or video, which is widely used in healthcare, smart environments, and surveillance. Although HAR based on computer vision has advanced rapidly, existing reviews do not adequately address the recent shift toward hybrid deep-learning architectures or provide a structured comparison of the trade-offs relevant to real-world deployment. This literature review addresses that gap through a PRISMA-guided analysis of articles published between 2021 and 2025 and retrieved from four major databases. The review develops a reproducible taxonomy of nine architectural families and applies a multidimensional evaluation framework covering classification accuracy, computational efficiency for edge deployment, environmental generalization, and fine-grained activity recognition. The findings show that hybrid architectures are the dominant design strategy, while attention-based and graph-based models play important specialized roles depending on temporal complexity, privacy requirements, and deployment constraints, with the literature concentrated mainly in healthcare and security applications. Full article

The rapid advancement of internet technology has transformed the tourism industry from traditional offline services to digital networked, and intelligent platforms. WebGIS has become critical infrastructure for tourism information retrieval and spatial decision-making. However, the growing volume and heterogeneity of multi-source tourism data expose fundamental limitations in conventional relational database architectures, particularly in handling complex spatial semantic queries. To address this, the present study proposes a WebGIS design methodology that integrates knowledge graphs with relational databases through a dual-database collaborative architecture. Using tourist attraction data from China’s Xinjiang Uyghur Autonomous Region as a case study, a prototype Xinjiang Smart Tourism WebGIS system was constructed, which consists of an asynchronous synchronization mechanism based on Change Data Capture (CDC) to ensure data consistency across heterogeneous databases. Subsequently, tourism semantic queries of varying depths were constructed and comprehensively tested across different data scales. The experimental results indicate that the proposed methodology effectively decouples business transactions and supports complex relationship computations, achieving shorter cross-domain semantic query times and higher latency stability. These findings offer practical guidance for designing high-performance regional tourism information services. Full article

As tunnel engineering continues to advance toward deeper, longer, and more complex projects, the risks encountered during the construction phase have evolved into a combination of various disaster types and the accumulation of multiple contributing factors. Traditional empirical and semi-empirical risk management methods are increasingly revealing shortcomings in terms of timeliness, accuracy, and the ability to process multi-source data. In recent years, driven by advancements in computing power and sensor technology, artificial intelligence algorithms (AI algorithms) such as machine learning and deep learning have been rapidly adopted in tunnel construction risk management. This paper retrieved relevant literature from the Web of Science database covering the period from 2010 to 2025. After rigorous screening, 96 highly relevant papers were selected for bibliometric analysis. This paper systematically reviews research progress from two perspectives: algorithmic models and engineering applications. The review indicates that, in terms of algorithmic models, traditional machine learning, convolutional neural network, recurrent neural network, generative adversarial network, Transformer, and graph neural network constitute a multi-level technical framework encompassing feature representation, risk perception, and intelligent decision-making. In terms of applications, AI algorithms have been widely integrated into typical scenarios such as geological hazard identification and prediction, surrounding rock stability and deformation prediction, rock burst assessment and early warning, lining defect detection and structural safety assessment, construction-induced ground settlement prediction, and tunnel gas and fire hazard prediction, significantly enhancing risk identification and early warning capabilities. However, several challenges remain, including the scarcity of high-quality datasets, the prevalence of noisy, incomplete, and heterogeneous monitoring data, insufficient coupling between model interpretability and engineering mechanisms, limited cross-project transferability, and the lack of integrated management systems for multi-hazard lifecycle control. Based on this, this paper proposes future research directions in areas such as data infrastructure development, integration of mechanism constraints, and multi-hazard collaborative modeling, aiming to provide guidance for the further development of intelligent risk management in tunnel construction. Full article