Search Results (14,084)

Building code waiver assessments in Singapore remain largely discretionary, relying on case officers’ subjective judgement with limited decision-support tooling. This study presents the first machine learning framework for predicting building code waiver outcomes, trained on 197 historically decided cases from the Building and Construction Authority (BCA) across five waiver categories: barrier-free accessibility (n = 45), ventilation (n = 61), staircase design (n = 37), safety provisions (n = 30), and structural modifications (n = 24), spanning 2021 to 2023. Fourteen engineered features, including documentation completeness, technical justification quality, and compliance history, were extracted through domain-expert annotation. Four models were evaluated: L2-regularised logistic regression, random forest, gradient boosting (XGBoost 2.0.1), and a weighted ensemble. The ensemble achieved the highest predictive accuracy of 83.7% (95% CI: 79.2–88.1%) with an area under the receiver operating characteristic curve (AUC) of 0.891 (95% CI: 0.854–0.928), significantly outperforming all individual models (McNemar’s test, p < 0.05). SHAP analysis revealed that documentation completeness and technical justification quality collectively account for 55% of prediction variance. A companion five-by-five risk assessment matrix, combining predicted rejection probability with consequence severity, stratified cases into actionable risk tiers correlating with observed approval rates ranging from 90.3% (very low risk) to 10.0% (very high risk; Spearman rho = −0.71, p < 0.001). Performance varied across waiver categories: ventilation waivers achieved the highest balanced accuracy (87.1%) while safety waivers proved most challenging (balanced accuracy 64.3%, sensitivity 40.0%). The framework offers a transparent, data-driven decision-support complement to regulatory judgement, learning patterns from historically decided applications within the 2021–2023 BCA context, and demonstrates feasibility for integration into Singapore’s Corenet X digital building submission platform. These five waiver categories serve as domain stratification variables. The machine learning target variable is the binary regulatory outcome: Approved (46.2% of cases) or Rejected (53.8%). Full article

Compaction quality governs asphalt pavement durability, but conventional density checks are intermittent. Reliable compaction control of asphalt mixtures requires real-time information on internal responses rather than relying solely on endpoint density measurements. In this study, an embedded smart-particle framework is developed for in situ monitoring and index-based evaluation of vibratory compaction quality, integrating multi-source sensing, feature extraction, and compaction degree mapping. The smart particle integrates inertial/orientation sensing together with thermal–mechanical measurements, and its high-temperature survivability and calibratability are verified through thermal exposure and calibration tests. During laboratory vibratory compaction of representative asphalt mixtures, raw signals are converted into stable attitude responses via attitude estimation and filtering; posture-dominant descriptors are then extracted and used to establish a data-driven mapping from internal responses to compaction degree using regression models. Results show that the device remains stable under typical hot-mix asphalt conditions, with calibration exhibiting high linearity (temperature channel R² > 0.990; force channel R² > 0.980 in the relevant range). Filtering markedly enhances inertial-signal usability under strong vibration and improves the interpretability of attitude-response evolution during compaction. The evolution of attitude features is consistent with the “rapid-to-slow densification” process, yielding correlations of |r| ≈ 0.35–0.47 with compaction degree evolution. Nonlinear regressors outperform linear baselines, and the better-performing nonlinear models achieve strong predictive performance across all six specimens, with R² values reaching 0.740–0.960 and RMSE reaching 0.016–0.043. Moreover, machine-learning-based feature-importance analysis reveals distinct mixture-type-dependent characteristics, indicating that AC and SMA transmit compaction-state information through partly different dominant response features. These findings demonstrate the feasibility of embedded smart particles for online compaction-quality evaluation and provide a basis for real-time feedback in intelligent compaction. Full article

As distributed terminals are increasingly integrated into modern power systems with high penetration of renewable energy and decentralized resources, access control mechanisms must support continuous and highly detailed trust assessment. Existing approaches based on machine learning primarily rely on network traffic features from a single source and analyze terminals in isolation, which limits their ability to capture complex device states and correlated attack behaviors. This paper presents a trust assessment framework for distributed power grid terminals that combines multidimensional behavioral modeling with dual domain graph neural networks. Behavioral features are collected from network traffic, runtime environment, and hardware or kernel events and are fused into compact representations through a variational autoencoder to mitigate redundancy and reduce computational overhead. Based on the fused features and observed communication relationships, two graphs are constructed in parallel: a feature domain graph reflecting behavioral similarity and a topological domain graph capturing communication structure between terminals. Graph convolution is performed in both domains to jointly model individual behavioral risk and correlation across terminals. A fusion mechanism based on attention is further introduced to adaptively integrate embeddings specific to each domain, together with a loss function that enforces both shared and complementary representations across domains. Experiments conducted on the CIC EV Charger Attack Dataset 2024 show that the proposed framework achieves a classification accuracy of 96.84%, while maintaining a recall rate above 95% for the low trust category. These results indicate that incorporating multidimensional behavior perception and dual domain relational modeling improves trust assessment performance for distributed power grid terminals under complex attack scenarios. Full article

The accuracy of transport properties, essential to the characterization of technological plasmas of interest in many fields, relies on the fundamental information about the collision integrals for the binary interactions in the system. The phenomenological approach has been demonstrated to provide a very useful theoretical framework for the derivation of transport cross sections, and in turn collision integrals, by a physics-sound description of the chemical species interaction. The features of the method and its validation are here briefly reviewed and the impact of the recent generalization of the correlation formulas on collision integrals for interactions involving Si species is estimated. Full article

Loss of skeletal muscle mass in cancer cachexia is associated with poorer survival, reduced treatment tolerance, and diminished quality of life. Routine oncology computed tomography (CT) can yield skeletal muscle area (SMA) and skeletal muscle index (SMI) for early cachexia assessment and prognostication, but manual annotation is labor intensive and existing automated tools often show inconsistent reliability. We developed SMAART-AI (Skeletal Muscle Assessment—Automated and Reliable Tool based on AI), a fully automated pipeline that localizes the third lumbar (L3) vertebral level, segments skeletal muscle, and quantifies prediction uncertainty to flag potentially unreliable outputs. Performance and reliability were evaluated across gastroesophageal, pancreatic, colorectal, and ovarian cancer cohorts, benchmarking against expert annotations and existing tools. SMAART-AI achieved a Dice score of 97.80% ± 0.93% in gastroesophageal cancer and a median SMA deviation of 2.48% from expert annotations across pancreatic, colorectal, and ovarian cohorts. Uncertainty scores correlated strongly with prediction error, enabling identification of high-error cases to support trustworthy deployment. Integrating the SMA/SMI with clinical features and body mass index (BMI) improved survival prediction (concordance index was +2.19% for colorectal, +9.82% for pancreatic, and +2.58% for ovarian cancer) and supported cachexia detection (70.00% accuracy; F1 80.00%). Overall, SMAART-AI provides an uncertainty-aware, clinically translatable framework for scalable CT-based muscle assessment and improved oncologic prognostication. Full article

Land surface bidirectional reflectance distribution functions (BRDF) are critical for quantitative remote sensing but are significantly constrained by scale effects, limiting the interoperability of multi-resolution data and the accuracy of quantitative inversion, thereby rendering the investigation of BRDF multi-scale effects increasingly urgent. This study utilized UAV (Unmanned Aerial Vehicle)-based multi-angular observations and the RPV model to retrieve the BRDF of typical land covers, employing the Window Averaging Method to simulate multi-scale responses and systematically investigate the relationship between BRDF characteristics and spatial scale. The results indicate the following key findings: (1) The RPV (Rahman–Pinty–Verstraete) model demonstrated high robustness and inversion accuracy, yielding RMSE (Root Mean Square Error) below 0.06 and RRMSE (Relative RMSE) below 25% across all land covers, with the 840 nm band exhibiting superior performance. (2) Significant spatial scale effects were observed, where BRDF characteristics varied distinctively with scale but eventually stabilized at specific thresholds; specifically, the stabilization scales were identified as 1.3 m for bare soil, 1.5 m for tea plantations, 1 m for rice, and 2 m for forests. (3) The scale evolution of BRDF features exhibited a parallel trend with spatial heterogeneity, a correlation that enables the quantitative identification of optimal observation scales for different land cover types. Full article

With the increasing use of modern technologies in interior design, numerous recent studies have made the effects of kinetic-based design techniques on users’ perceptions a crucial topic, and sustainable performance has emerged as essential. From this standpoint, this study uses a space syntax approach to investigate how human behavioral performance in workspaces is affected by kinetic interiors. Three kinetic-based design strategies were employed to evaluate changes in spatial configuration characteristics, and the relevant terminology was adapted to account for the use of kinetic technology. The paper adopts a comparative analysis model to follow these changes using four syntactic measures: integration, choice, connectivity, and clustering coefficient. The proposed evaluation approach is applied to a traditional office building in Port Said, Egypt, showcasing various aspects of kinetic technology in workspaces. The study’s findings elucidate the correlations between design strategies and the resulting spatial characteristics, guiding designers in evaluating the features of each system and facilitating comparisons between them. Finally, the study’s main aim is to propose a three-step design process as a guideline for creating an integrated kinetic technology design, involving the evaluation of the proposed alternatives to achieve the desired spatial characteristics. Full article

Quantitative analysis of leaf cell microstructure is crucial for deciphering agronomic traits in Chinese cabbage, including photosynthetic efficiency, stress tolerance, and yield potential. Traditional manual observation methods are inefficient and highly subjective, failing to meet the demands of large-scale breeding for high-throughput, reproducible microscopic phenotyping. To transition breeding practices from experience-driven to data-driven, there is an urgent need to establish automated, standardized systems for acquiring cell-scale phenotypes. Therefore, this study proposes an automated instance segmentation and phenotyping analysis framework for multi-tissue cells in Chinese cabbage leaf cross-sections. This framework systematically optimizes Mask R-CNN by introducing an attention mechanism to enhance cellular feature responses in complex backgrounds. It employs weighted multi-scale feature fusion to process densely distributed small-scale cells and integrates a refined boundary optimization module to improve recognition accuracy in adherent and blurred regions. On a microscopic image dataset spanning multiple varieties, this method achieves high-precision predictions in instance segmentation tasks. Based on the predicted cell masks, an interactive phenotyping analysis tool was further developed to automatically extract standardized single-cell morphological parameters, including area, perimeter, and Feret’s diameter. The measured parameters exhibit high consistency with manual annotations (correlation coefficients (r) all exceed 0.97). This framework enables high-throughput, standardized phenotypic analysis at the cellular level of leaf cross-sections, providing a reliable method for the digital and automated interpretation of crop microscopic traits. This technical solution not only supports the systematic integration of microscopic phenotypes in Chinese cabbage breeding but also offers a scalable solution for cellular-scale phenotypic research in other crops. Full article

The precursor infiltration and pyrolysis (PIP) route is widely adopted to fabricate carbon fiber-reinforced silicon carbide (C_f/SiC) composites; however, the atomic-scale restructuring of the pyrolytic carbon/silicon carbide (PyC/SiC) interface during ceramization—and its impact on mechanical integrity—remains elusive. Here, reactive molecular dynamics (ReaxFF MD) simulations elucidate the coupled thermochemical–mechanical evolution of polycarbosilane (PCS) precursors on PyC substrates with orientation angles (OAs) of 0°, 25°, 55°, and 85°. Dynamic pyrolysis triggers a pivotal transition from sp² to sp³ hybridization at the interface. High-OA substrates (55° and 85°) present a dense population of reactive edge sites, fostering extensive cross-interfacial covalent bonding. Subsequent shear loading reveals that these pyrolysis-induced chemical bridges govern failure modes, shifting from interlayer sliding dominated by weak non-bonded interactions (0°) to ductile fracture featuring uniform plasticity and crack deflection. The OA = 55° interface attains a theoretical peak shear strength of 15 GPa and exhibits the most favorable combination of high strength and ductile failure under tensile loading, owing to an optimal balance between reactive site availability and interlayer steric openness. In contrast, the OA = 85° interface, despite comparable peak stress, fails via brittle crack penetration into the SiC matrix. By correlating atomistic structure with macroscopic performance, this study provides a bottom-up framework for engineering C_f/SiC composites via interfacial texturing and optimized pyrolysis protocols. Full article

Non-intrusive load monitoring (NILM) is a key enabler for smart-grid applications, yet practical deployment is often hindered by limited appliance-level labels and severe distribution shifts across households and operating conditions. As a result, many deep learning approaches become unreliable in small-sample and out-of-distribution (OOD) settings. In this paper, we propose CR-MAT, a causality-driven representation learning framework for few-shot NILM classification. Instead of relying on large-scale training or heavy data augmentation, CR-MAT injects causal representation learning into multi-appliance task modeling, encouraging the network to learn appliance-discriminative features that are stable across environments while suppressing spurious, domain-specific correlations. We conduct extensive experiments under multiple OOD scenarios and consistently observe improved classification robustness compared with deep NILM baselines. Further analysis indicates that causal representation learning enhances resilience to non-stationary consumption patterns and improves generalization under OOD scenarios. The proposed framework provides a practical route toward reliable NILM classification and supports downstream smart-grid applications such as flexible load control and demand response. Full article

Mitochondrial dysfunction profoundly alters cellular metabolism, yet its systems-level consequences remain incompletely characterized. Here, we present a comprehensive untargeted metabolomics analysis of respiratory-deficient (ρ⁰) and competent (ρ⁺) Saccharomyces cerevisiae prototrophic cells using ultra-high-performance liquid chromatography coupled to Orbitrap Fusion™ Tribrid™ high-resolution mass spectrometry. By integrating hydrophilic interaction and reversed-phase chromatography in both ionization modes, we detected ~7000 features per chromatographic condition, of which ~12% were structurally annotated through MSⁿ fragmentation and in silico spectral matching. Principal component analysis revealed distinct metabolic signatures between ρ⁰ and ρ⁺ cells, with ~73% of total variance explained by the first two components. Volcano plot and hierarchical clustering analyses identified a marked accumulation of phosphate-containing metabolites, sphingolipids, ceramides, and fatty acid residues in ρ⁰ cells, whereas amino acids, excluding arginine, cysteine, and aromatics, were enriched in ρ⁺ cells. Notably, branched-chain amino acid depletion in ρ⁰ cells correlated with impaired growth and mitochondrial stress. Pathway enrichment analysis, supported by transcriptomic integration, prompted us to further investigate reprogramming of polyamine biosynthesis and aromatic amino acid metabolism. Calibration curves constructed from certified standards validated the accuracy of the LC–MS platform and reinforced annotation confidence. Our findings demonstrate that advanced untargeted metabolomics, coupled with MS³ fragmentation and multi-omics integration, enables high-resolution mapping of metabolic reconfiguration under mitochondrial dysfunction, offering mechanistic insights into mitochondrial retrograde signaling and adaptation. Full article

Rotating machinery serves as a critical component in various engineering systems, making accurate prediction of its Remaining Useful Life (RUL) essential for ensuring operational stability. To address the technical limitations of mainstream RUL prediction models comprehensively capturing spatial correlations among multiple sensors, this paper proposes a multi-graph-structured spatiotemporal feature fusion model for RUL prediction of rotating machinery. Breaking through the constraints of constructing a single correlation graph, the model first builds two distinct graphs—a prior correlation graph based on the structural mechanism of the rotating machinery and a similarity correlation graph derived from monitoring data distribution characteristics. These dual-perspective graphs collectively characterize the potential spatial dependencies among multiple sensors. Subsequently, a Graph Attention Network (GAT) is introduced to aggregate spatial features from both graphs, and a feature concatenation fusion strategy is adopted to achieve a comprehensive representation of the inter-sensor spatial dependencies. Finally, a Long Short-Term Memory (LSTM) network is employed to extract temporal evolution features from the operational data. The effective fusion of these spatial and temporal features enhances the model’s RUL prediction performance. Simulation experiments conducted on the Commercial Modular Aero-Propulsion System Simulation (C-MAPSS) dataset validated the robustness of the proposed method. Full article

Background: Endometriosis is a complex condition that impairs women’s quality of life and reproductive potential. Its diagnosis remains significant challenge for clinicians. The aim of the study was to investigate cancer-like immune evasion mechanisms in endometriosis and to develop a novel diagnostic model using machine learning. Methods: In this study, we measured the levels of soluble forms of the following immune markers in blood serum and peritoneal fluid (PF): sMICA, sMICB, sEng, sCD25, s4-1BB, sB7.2, sCTLA-4, sPD-L1, sPD-1, sTIM-3, sLAG-3, and sGal-9. Results: sMICB levels in PF differed across endometriosis stages and were higher in patients with endometriosis-associated adhesions. sMICA levels in PF were elevated in women with endometriosis-associated infertility. The disease severity was inversely correlated with serum sB7.2 levels and positively correlated with serum sTIM-3 levels. A logistic regression model achieved an accuracy = 0.79, AUC = 0.94, and F1-score = 0.88, whereas XGBoost performed better with accuracy = 0.94, AUC = 0.95, and F1-score = 0.96. The key predictive features in both models were sMICB serum level and patients’ pain score. Conclusions: Our results demonstrate the potential role of sMICA and sMICB shedding in endometriosis and present a novel, minimally invasive diagnostic approach. Full article

Background/Objectives: Glypican-3 (GPC3), a membrane-bound heparan sulfate proteoglycan, has been identified as a promising target for both the diagnosis and treatment of hepatocellular carcinoma (HCC). However, the diagnosis of GPC3 expression mainly depended on invasive procedures. This study aimed to investigate the potential of dual-energy computed tomography (DECT)-derived parameters for noninvasive prediction of GPC3 expression in HCC. Methods: This retrospective study included 79 HCC patients with confirmed GPC3 immunohistochemistry and pretreatment contrast-enhanced DECT. Qualitative imaging features and quantitative DECT parameters, including iodine density of HCC (ID_Ca), normalized iodine density (NID), slope of spectral attenuation curve (λ_HU), and effective atomic number (Z_eff), were evaluated in both arterial and portal venous phases. Univariate and multivariate logistic regression analyses were employed to identify independent predictors, and a combined model was subsequently constructed. Receiver operating characteristic (ROC) curve analysis was performed to assess the diagnostic efficiency of imaging parameters in predicting GPC3 expression. Interobserver agreement of DECT parameters was evaluated using intraclass correlation coefficients (ICC). Results: GPC3-positive HCCs demonstrated significantly higher arterial phase (AP) ID_Ca, NID, λ_HU, and Z_eff (all p ≤ 0.001) than GPC3-negative HCCs. Multivariate logistic regression analysis identified NID-AP [Odds ratio (OR) = 2.00, p = 0.010] and peritumoral enhancement (OR = 9.25, p = 0.046) as independent predictors. The model combining NID-AP and peritumoral enhancement achieved the best diagnostic performance (AUC = 0.781, sensitivity = 67.86%, specificity = 78.26%) for predicting GPC3 expression. All DECT-derived parameters showed excellent interobserver reproducibility (ICC > 0.75 for all). Conclusions: Parameters derived from DECT, especially combining NID-AP and peritumoral enhancement, may be a potential tool to noninvasively predict GPC3 expression in HCC. Full article

Laser Powder Bed Fusion (LPBF)-processed AlSi10Mg produces highly heterogeneous microstructures, where fine α-Al cells, Si-rich networks, and melt-pool boundaries govern local mechanical behavior. Nanoindentation has emerged as a key tool for probing these variations, yet systematic understanding of the links between processing parameters, microstructure, and nano-mechanical response remains limited. This critical review examines how laser processing parameters influence local mechanical response through their impact on microstructural features. Key challenges in interpreting nanoindentation are highlighted, alongside inconsistencies in experimental protocols and reporting practices that hinder cross-study comparisons. Beyond summarizing existing findings, underexplored aspects of nanoindentation in LPBF AlSi10Mg are identified, including spatially correlated microstructure-mechanical mapping, depth-resolved measurements, and integration with advanced characterization and data-driven approaches. By synthesizing current knowledge and clarifying methodological constraints, this review positions nanoindentation not merely as a descriptive tool, but as a mechanistically informed approach for linking processing conditions, microstructural heterogeneity, and local mechanical response. These insights aim to support more rigorous interpretation of small-scale mechanical data and to guide future studies toward predictive understanding and rational process optimization in additively manufactured aluminum alloys. Full article