Search Results (195)

The assessment of wheel–rail force states is a key technical issue in the safety monitoring of high-speed railway turnouts. Due to the complex geometry and severe load fluctuations of turnouts, wheel–rail interactions exhibit strong nonlinearity, asymmetry, and multidimensional coupling characteristics. Traditional methods suffer from limitations such as reliance on labeled samples and poor real-time performance. This study proposes an intelligent evaluation method that integrates multivariate statistical analysis with unsupervised clustering, and establishes a multidimensional analytical framework incorporating data preprocessing, time-domain analysis, safety index evaluation, frequency-domain feature extraction, and cluster-based recognition. Using a turnout section of the Beijing–Tianjin Intercity Railway as a case study, four fundamental wheel–rail force components were selected as feature variables to reveal their dynamic patterns. The DBSCAN density-based clustering algorithm was employed to achieve unsupervised state identification, successfully classifying three typical operating states: normal, high-load abnormal, and extreme load. The clustering silhouette coefficient reached 0.563, significantly outperforming K-means and hierarchical clustering. Safety evaluation results indicate that all relevant indicators meet international standards. The proposed method requires no labeled samples and offers strong physical interpretability and engineering applicability, providing effective support for turnout condition awareness and predictive maintenance. Full article

Background: Mapping anti–HLA class I cross-reactivity from single-antigen bead (SAB) mean fluorescence intensity (MFI) data supports donor selection. However, interpretation is complicated by analytical choices and assay variability. Methods: A total of 4327 SAB assays were analyzed (antigen × test matrix) using an interpretable, distance-based workflow. Antigen profiles were z-scored across tests. Multidimensional scaling (MDS) was used for visualization and hierarchical clustering analysis (HCA) for grouping, and complemented these with a common PCA space for model selection (K-Means via Silhouette; Gaussian Mixture Models via BIC), agglomerative (Ward and average-link on 1–correlation), spectral clustering on correlation-derived affinities, and a graph approach (k-NN ∪ minimum-spanning-tree with modularity-based communities). Non-linear embeddings (t-SNE/UMAP) and density-based HDBSCAN were used only for visual analytics, not for primary inference. Results: The pipeline revealed coherent reactivity neighborhoods that partially overlapped known cross-reactive antigen groups (CREGs) and eplet-based expectations while also highlighting less-documented relationships. Robustness was confirmed through bootstrap resampling, graph modularity, and consensus clustering across methods. Conclusions: This unified, auditable workflow converts descriptive maps into method-robust summaries of antibody reactivity and cross-reactivity. While exploratory and performed on a single dataset without linked outcomes, the approach provides a reproducible structure for comparing cohorts and prioritizing hypotheses that could be prospectively validated for clinical decision support in transplantation. Full article

This study investigated the use of K-means and hierarchical clustering, to group Italian Mediterranean buffalo using routinely collected test-day records. The analysis was first conducted on a combined dataset comprising three buffalo herds and subsequently on each herd individually. The main objective was to determine whether data-driven groupings could be implemented to support improvements in general herd management strategies. Results indicated that K-means consistently outperformed hierarchical clustering across all datasets, as reflected by average silhouette scores (0.17–0.18 vs. 0.10–0.12 for K-means and hierarchical, respectively), favorable Davies–Bouldin Index (DBI; 2.05–2.16 vs. 2.11–2.5 for K-means and hierarchical, respectively) and Calinski–Harabasz Index values (CHI; 1034–3877 vs. 729–2109 for K-means and hierarchical, respectively). K-means identified two clusters in the combined dataset and in two of the three herds, while three clusters were identified in the remaining herd. Cluster composition analysis revealed that days in milk and milk yield were the main discriminating factors when two clusters were formed. When three clusters emerged, K-means also identified a subgroup of animals that differed from the others in both age and lactation stage. These findings were supported by the analysis of variance (ANOVA), which showed statistically significant differences among most of the evaluated variables. Full article

The implementation of Euro 7 emission standards demands advanced real-time NO_x monitoring systems for diesel vehicles. Existing unified models inadequately capture phase-dependent emission mechanisms during cold-start, urban, and highway operation. This study develops a novel Mixture of Experts (MoE) architecture with data-driven phase classification based on aftertreatment thermal dynamics. Real-world data from a Euro 6d commercial vehicle (3247 PEMS samples) were classified into three phases, cold (<70 °C coolant temperature), hot low-speed (<90 km/h), and hot high-speed (≥90 km/h), validated through t-SNE analysis (silhouette coefficient = 0.73). The key innovation integrates thermal–kinematic domain knowledge with specialized XGBoost regressors, achieving R² = 0.918 and a 58% RMSE reduction versus unified models (RMSE = 1.825 mg/s). The framework operates within real-time constraints (1.5 ms inference latency), integrating autoencoder-based anomaly detection (95.2% sensitivity) and Model Predictive Control (11–13% NO_x reduction). This represents the first systematic phase-specific NO_x modeling framework with validated Euro 7 OBM compliance capability, providing both methodological advances in expert allocation strategies and practical solutions for next-generation emission control systems. Full article

Dimensionality reduction is fundamental for analyzing high-dimensional data, supporting visualization, denoising, and structure discovery. We present a systematic, large-scale benchmark of three widely used methods—Principal Component Analysis (PCA), Isometric Mapping (Isomap), and t-Distributed Stochastic Neighbor Embedding (t-SNE)—evaluated by average silhouette scores to quantify cluster preservation after embedding. Our full factorial simulation varies sample size $n\in \{100,200,300,400,500\}$, noise variance ${\sigma }^2\in \{0.25,0.5,0.75,1,1.5,2\}$, and feature count $p\in \{20,50,100,200,300,400\}$ under four generative regimes: (1) a linear Gaussian mixture, (2) a linear Student-t mixture with heavy tails, (3) a nonlinear Swiss-roll manifold, and (4) a nonlinear concentric-spheres manifold, each replicated 1000 times per condition. Beyond empirical comparisons, we provide mathematical results that explain the observed rankings: under standard separation and sampling assumptions, PCA maximizes silhouettes for linear, low-rank structure, whereas Isomap dominates on smooth curved manifolds; t-SNE prioritizes local neighborhoods, yielding strong local separation but less reliable global geometry. Empirically, PCA consistently achieves the highest silhouettes for linear structure (Isomap second, t-SNE third); on manifolds the ordering reverses (Isomap > t-SNE > PCA). Increasing ${\sigma }^2$ and adding uninformative dimensions (larger p) degrade all methods, while larger n improves levels and stability. To our knowledge, this is the first integrated study combining a comprehensive factorial simulation across linear and nonlinear regimes with distribution-based summaries (density and violin plots) and supporting theory that predicts method orderings. The results offer clear, practice-oriented guidance: prefer PCA when structure is approximately linear; favor manifold learning—especially Isomap—when curvature is present; and use t-SNE for the exploratory visualization of local neighborhoods. Complete tables and replication materials are provided to facilitate method selection and reproducibility. Full article

Urban transportation is a major source of air pollution. On urban highways, driver behavior significantly influences vehicle emissions, as tailpipe pollutants depend on driving patterns. Therefore, estimating the emission factors of key pollutants namely carbon monoxide (CO), carbon dioxide (CO₂), nitrogen oxides (NO_X), and hydrocarbons (HC) is essential. This study investigates the impact of driver behavior on environmental pollutants and derives field-based emission factors on urban highways in Mashhad, Iran, during June 2022. A total of 150 drivers were classified using the K-means algorithm based on their aggressiveness scores from the Driver Behavior Questionnaire (DBQ), maximum acceleration, frequency of maximum acceleration events, and the number of traffic accidents recorded over the past five years. The clustering quality was evaluated using the Silhouette score, leading to two categories: aggressive and non-aggressive drivers. Cochran’s formula was applied to select 10 drivers from each group, and emissions were measured using an onboard monitoring device. Results indicate that aggressive drivers exhibit higher speeds, more pronounced acceleration and deceleration (A/D) patterns, and elevated engine RPM compared with non-aggressive drivers. Spearman’s rank correlation analysis revealed a strong and significant relationship between engine RPM and tailpipe emissions in both driver groups, indicating increased emissions at higher RPMs. In contrast, A/D behavior showed no significant association with emissions, suggesting a minimal direct effect. Overall, emission factors for NO_X, CO₂, CO, and HC were 37.50%, 23.60%, 41.90%, and 53.13% higher, respectively, in aggressive drivers compared with non-aggressive drivers. Furthermore, the Mann–Whitney U test confirmed statistically significant differences in tailpipe emissions between the two groups. These findings demonstrate that distinct driving behaviors are closely linked to variations in vehicular emissions. Full article

This study critically examines the multidimensional differences in body image perceptions among female students who participate in regular sports activities compared to their sedentary counterparts. The investigation involved a sample of 436 female students divided into two distinct groups: the sports group (GS, n = 180), consisting of participants from physical education and sports disciplines, and the non-sports group (GNS, n = 256). Anthropometric measurements such as height, weight, and body mass index (BMI) were systematically taken, along with the administration of three validated psychometric tools: the Silhouette Rating Scale (SRS) to assess body perception and satisfaction, the Objectified Body Consciousness Scale (OBC) to evaluate body objectification, and the Ideal Body Stereotype Scale-Revised (IBIS-R) to analyze perceptions of ideal body stereotypes. Notably, body dissatisfaction (SRS-D) showed the strongest correlation with BMI in both groups, with the non-athletic group displaying slightly higher correlation coefficients (r = 0.940) compared to the athletic group (r = 0.904; p < 0.001). Additionally, stereotypes related to the ideal body (IBIS-R) were strongly correlated with BMI in the non-athletic group (r = 0.846), whereas the athletic group showed a slightly lower correlation (r = 0.805). The body objectification measure (OBC) demonstrated moderate correlations, with the non-athletic group showing stronger associations (r = 0.394 vs. r = 0.352). Linear regression analysis revealed that non-athletic individuals exhibited higher predictive validity, characterized by greater R² values and stronger correlations between physical and psychosocial factors. The results indicate that participation in sports serves as a protective factor against negative body image, shown by weaker correlations in the sports group. This research suggests that engaging in physical activities is associated with healthier body profiles and a more positive body image, leading to greater satisfaction and more realistic perceptions of body size. Full article

Gait analysis is essential in the evaluation of neuromuscular and musculoskeletal disorders; however, traditional approaches based on expert visual observation remain subjective and often lack consistency. Accurate and objective assessment of gait impairments is critical for early diagnosis, monitoring rehabilitation progress, and guiding clinical decision-making. Although Gait Energy Images (GEI) have become widely used in automated, vision-based gait analysis, they are limited in capturing boundary details and time-resolved motion dynamics, both critical for robust clinical interpretation. To overcome these limitations, we introduce four novel gait representation maps: the time-coded gait boundary image (tGBI), color-coded GEI (cGEI), time-coded gait delta image (tGDI), and color-coded boundary-to-image transform (cBIT). These representations are specifically designed to embed spatial, temporal, and boundary-specific features of the gait cycle, and are constructed from binary silhouette sequences through straightforward yet effective transformations that preserve key structural and dynamic information. Experiments on the INIT GAIT dataset demonstrate that the proposed representations consistently outperform the conventional GEI across multiple machine learning models and classification tasks involving different numbers of gait impairment categories (four and six classes). These findings highlight the potential of the proposed approaches to enhance the accuracy and reliability of automated clinical gait analysis. Full article

Background: Personalizing adjuvant chemotherapy (ACT) after curative resection in early-stage NSCLC remains unmet because prior ACT-biomarker findings rarely reproduce across studies. Key barriers are platform and preprocessing heterogeneity, dominant batch effects, and incomplete ACT annotations. As a result, many signatures that perform well in a single cohort fail during external validation. We created an open, harmonized meta-database linking gene expression with curated ACT exposure and survival to enable fair benchmarking and modeling. Methods: A PRISMA-guided search of 999 GEO studies (through January 2025) used LLM-assisted triage of titles, clinical tables, and free text to identify datasets with explicit ACT status and patient-level survival. Eight Affymetrix microarray cohorts (GPL570/GPL96) met eligibility. Raw CEL files underwent robust multi-array average; probes were re-annotated to Entrez IDs and collapsed by median. Covariate-preserving ComBat adjusted platform/study while retaining several clinical factors. Batch structure was quantified by principal-component analysis (PCA) variance, silhouette width, and UMAP. Two quality-control (QC) filters, median M-score deviation and PCA leverage, flagged and removed technical outliers. Results: The final meta-database comprises 1340 patients (223 (16.6%) ACT; 1117 (83.4%) observation), 13,039 intersecting genes, and 594 overall-survival events. Batch-associated variance (PC1 + PC2) decreased from 63.1% to 20.1%, and mean silhouette width shifted from 0.82 to −0.19 post-correction. Seven arrays (0.5%) were excluded by QC. Event depth supports high-dimensional survival and heterogeneity-of-treatment modeling, and the multi-cohort design enables internal–external validation. Conclusions: This first open, rigorously harmonized NSCLC transcriptomic database provides the sample size, demographic diversity, and technical consistency required to benchmark ACT-benefit markers. By making these data openly available, it will accelerate equitable precision-oncology research and enable data-driven treatment decisions in early-stage NSCLC. Full article

(1) Background: University students face increasing mental health challenges, with sociodemographic disparities shaping well-being outcomes and highlighting the need for machine learning approaches to identify distinct psychological profiles. (2) Methods: This cross-sectional study surveyed 4911 Chinese university students (aged 18–25) using the EPOCH Questionnaire, which measures Engagement, Perseverance, Optimism, Connectedness, and Happiness. Data were collected via WenjuanXing (WJX), with recruitment promoted through official channels. Well-being profiles were identified through exploratory K-means clustering, with internal validity and the optimal cluster number assessed using the silhouette coefficient. (3) Results: Cluster analysis identified two distinct groups: Cluster 0 (41.09%) with higher well-being scores and Cluster 1 (58.91%) with lower scores. Differences across all five EPOCH dimensions exceeded 1.0, most notably in Optimism (Δ = 1.31) and Happiness (Δ = 1.37). A subgroup of concern within Cluster 1 (n = 92), primarily male sophomores from rural, low-income, multi-child families receiving financial aid, showed particularly low scores in Connectedness (Δ = −0.57) and Happiness (Δ = −0.43). In contrast, a high well-being subgroup in Cluster 0 (n = 108), mainly urban female freshmen from high-income, only-child families, exhibited elevated scores, especially in Connectedness (Δ = 0.69) and Happiness (Δ = 0.65). (4) Conclusions: This exploratory clustering study identified distinct well-being profiles among Chinese university students, with demographic and socioeconomic vulnerabilities associated with diminished psychological well-being, particularly in Connectedness, Happiness, and Optimism. These findings highlight the need for targeted interventions that integrate psychosocial support with financial assistance to reduce inequalities and promote flourishing. Full article

Background: As diabetes mellitus continues to escalate into a global health crisis, particularly in China, the limitations of conventional pharmacotherapy underscore the need for complementary interventions. This study systematically reviews two decades of research progress on acupuncture for diabetes management. Methods: A total of 391 publications met the inclusion criteria from the Web of Science Core Collection (2004–2024) using the search terms “acupuncture” AND “diabetes”. These comprised 294 original studies and 97 reviews. CiteSpace 6.3.R1 was used to perform multidimensional analyses, including co-occurrence networks, centrality algorithms, and silhouette metrics across countries/regions, institutions, authors, journals, references, and keywords. Results: The analysis shows a significant increase in publications on acupuncture for diabetes management after 2013. China and the United States lead in research output, yet collaboration between the two countries remains limited. Most researchers currently work within isolated clusters, underscoring the need for greater exchanges and cooperation. Furthermore, this study identified three key research hotspots: insulin resistance, complications, and interdisciplinary research. Conclusions: This bibliometric analysis reveals dynamic growth patterns and paradigm shifts in acupuncture and diabetes research. The findings provide valuable implications for integrating acupuncture into diabetes treatment. Full article

Soundscape monitoring has become an increasingly important tool for studying ecological processes and supporting habitat conservation. While many recent advances focus on identifying species through supervised learning, there is growing interest in understanding the soundscape as a whole while considering patterns that extend beyond individual vocalizations. This broader view requires unsupervised approaches capable of capturing meaningful structures related to temporal dynamics, frequency content, spatial distribution, and ecological variability. In this study, we present a fully unsupervised framework for analyzing large-scale soundscape data using deep learning. We applied a convolutional autoencoder (Soundscape-Net) to extract acoustic representations from over 60,000 recordings collected across a grid-based sampling design in the Rey Zamuro Reserve in Colombia. These features were initially compared with other audio characterization methods, showing superior performance in multiclass classification, with accuracies of 0.85 for habitat cover identification and 0.89 for time-of-day classification across 13 days. For the unsupervised study, optimized dimensionality reduction methods (Uniform Manifold Approximation and Projection and Pairwise Controlled Manifold Approximation and Projection) were applied to project the learned features, achieving trustworthiness scores above 0.96. Subsequently, clustering was performed using KMeans and Density-Based Spatial Clustering of Applications with Noise (DBSCAN), with evaluations based on metrics such as the silhouette, where scores above 0.45 were obtained, thus supporting the robustness of the discovered latent acoustic structures. To interpret and validate the resulting clusters, we combined multiple strategies: spatial mapping through interpolation, analysis of acoustic index variance to understand the cluster structure, and graph-based connectivity analysis to identify ecological relationships between the recording sites. Our results demonstrate that this approach can uncover both local and broad-scale patterns in the soundscape, providing a flexible and interpretable pathway for unsupervised ecological monitoring. Full article

Industrial process monitoring increasingly relies on sensor-generated time-series data, yet the lack of labels, high variability, and operational noise make it difficult to extract meaningful patterns using conventional methods. Existing clustering techniques either rely on fixed distance metrics or deep models designed for static data, limiting their ability to handle dynamic, unstructured industrial sequences. Addressing this gap, this paper proposes a novel framework for unsupervised discovery of operational modes in univariate time-series data using image-based convolutional clustering with composite internal evaluation. The proposed framework improves upon existing approaches in three ways: (1) raw time-series sequences are transformed into grayscale matrix representations via overlapping sliding windows, allowing effective feature extraction using a deep convolutional autoencoder; (2) the framework integrates both soft and hard clustering outputs and refines the selection through a two-stage strategy; and (3) clustering performance is objectively evaluated by a newly developed composite score, $S_{eva}$, which combines normalized Silhouette, Calinski–Harabasz, and Davies–Bouldin indices. Applied to over 3900 furnace melting operations from a Nordic foundry, the method identifies seven explainable operational patterns, revealing significant differences in energy consumption, thermal dynamics, and production duration. Compared to classical and deep clustering baselines, the proposed approach achieves superior overall performance, greater robustness, and domain-aligned explainability. The framework addresses key challenges in unsupervised time-series analysis, such as sequence irregularity, overlapping modes, and metric inconsistency, and provides a generalizable solution for data-driven diagnostics and energy optimization in industrial systems. Full article

Fish stocks and their management are paramount for sustainable fisheries under the ongoing changes in atmosphere–sea interactions. The Aegean Sea, one of the composite seas influenced by different water masses, is characterized by a diverse ecosystem. Small pelagic fish are abundant and tend to form schools that vary in size. One of the most efficient and rapid techniques for sampling fish schools over a large area is the use of acoustic methods. Therefore, an acoustic survey was conducted in the coastal areas along the entire Turkish Aegean waters between June and August 2024, using a scientific quantitative echosounder equipped with a split-beam transducer operating at 206 kHz. During the survey, environmental parameters, including water physics, optics, and bathymetry, were measured at 321 stations. Additionally, satellite data were used to obtain water primary production levels for each sampling month across the entire study area. Using a custom computer algorithm written during the present study in MATLAB (2021a), fish schools were automatically detected to measure various morphological and acoustic features. Through a series of statistical analyses, three optimal clusters, validated with the total silhouette sum of distances (1317.38), were identified, each characterized by specific morphological, acoustic, and environmental variables associated with different areas of the study. School morphology and acoustic properties also varied with bottom depth. Cluster 1 was mostly found in open and relatively deep waters. Cluster 2 appeared in areas impacted by anthropogenic sources. Principal Component Analysis (PCA) revealed that the first component (PCA1) was correlated with school height from the bottom (HFB) and overall school height (SH), followed by minimum depth (MnD), maximum depth (MxD), and volume backscattering strength at the school edge (SvE). The second component (PCA2) was associated with school width (SW) and area (A). Cluster 1 was characterized by schools with large SW and A, and relatively high HFB and SH. Cluster 2 showed low HFB and SH, while Cluster 3 had high MnD and MxD and low SvE. Based on the descriptors for these clusters, each cluster could be attributed to fish species at different life stages inferred based on target strength (TS), namely sardine, horse mackerel, and chub mackerel, distributed along the entire Turkish Aegean coast. Full article

The increasing urgency of global sustainability challenges has elevated the role of the United Nations Sustainable Development Goals (SDGs) as benchmarks for both academic research and policy development. Within the European Union, measuring how national research systems contribute to SDG-related knowledge is critical for guiding evidence-based policymaking and evaluating progress toward the 2030 Agenda. Since the adoption of the UN 2030 Agenda, research related to the Sustainable Development Goals (SDGs) has expanded significantly, reflecting their central role in guiding both global and European science policy. Despite this growing attention, systematic comparative evidence on how EU27 countries contribute to SDG-related knowledge production remains limited. This study provides a bibliometric analysis of research related to the SDGs across EU27 countries between 2019 and 2023. Drawing on data from Elsevier’s Scopus and SciVal platforms, we examine publication volume, relative share (RS), citation impact (FWCI), growth dynamics (CAGR), and thematic distributions. The dataset includes all document types associated with SDG1–SDG16. Germany, Italy, and France lead in absolute publication output, while smaller member states such as Cyprus, Malta, and Luxembourg display disproportionately high RS values. Health-related research (SDG3) dominates, followed by SDG7 (Affordable and Clean Energy) and SDG12 (Responsible Consumption and Production), whereas socially oriented goals (SDG2 and SDG5) remain underrepresented. Hierarchical cluster analysis, validated through silhouette and agglomeration tests, identifies three groups of countries: (1) high-output, high-impact Northern and Western leaders; (2) diversified performers with balanced portfolios; and (3) emerging contributors from Eastern and Southern Europe. Explanatory analyses link bibliometric outcomes to contextual variables, showing strong correlations with Horizon Europe funding per capita and international collaboration, and moderate associations with GDP per capita and GERD. Institutional-level findings highlight the prominence of leading universities and research institutes, particularly in health sciences. The study introduces a robust cluster-based typology and a multidimensional framework that connects bibliometric performance with economic capacity, research investment, EU funding participation, and collaboration intensity. Policy recommendations are proposed to strengthen thematic balance, improve equitable participation in EU research programs, and foster international cooperation across the European Research Area. Full article