Search Results (4,858)

Immunonutrition continues to generate heterogeneous and often contradictory clinical outcomes, suggesting that nutrients do not exert fixed immunological effects but interact with the biological context in which they operate. Sarcopenic obesity (SO) represents a paradigmatic clinical model of this complexity, where chronic low-grade inflammation, mitochondrial dysfunction, anabolic resistance, metabolic inflexibility, and microbiota remodeling converge to compromise the adaptive capacity of integrated immunometabolic networks. We propose that this condition may be interpreted as a state of impaired immunometabolic plasticity, which may help explain the context-dependent variability of nutritional responses. Within this perspective, micronutrients are viewed not simply as cofactors supporting immune competence but as dynamic regulators of interconnected immunometabolic pathways. Particular attention is devoted to vitamin D and resveratrol, presented as complementary regulators of immunometabolic plasticity. Within the proposed framework, vitamin D may contribute to immunometabolic competence, whereas resveratrol may act as a broader signaling modulator through the SIRT1/AMPK–PGC-1α axis, influencing mitochondrial function, inflammatory tone, metabolic flexibility, and epigenetic adaptation. Beyond isolated compounds, bioactive-rich food matrices, exemplified by Opuntia ficus-indica, are discussed as examples of systems-level modulators capable of coordinating inflammatory, metabolic, redox, and microbiota-dependent biological circuitry. This review introduces immunometabolic plasticity as a conceptual framework linking nutritional signals to the coordinated regulation of immune and metabolic adaptation across diverse biological contexts. Finally, we discuss how biomarker-guided phenotyping, multi-omics integration, and context-aware nutritional interventions may provide a foundation for precision immunonutrition, shifting the field from generalized supplementation strategies toward restoration of adaptive immunometabolic resilience. Full article

Wi-Fi Channel State Information (CSI) provides a privacy-preserving modality for human activity recognition (HAR), particularly in environments where activity classes vary in complexity and temporal scale. This work presents an integrated framework that combines multi-scale Fourier operator learning with manifold-aware density refinement for coarse-grained CSI-based HAR. The adaptive Multi-Scale Fourier Neural Operator (MS-FNO) models CSI trajectories as structured stochastic processes and learns activity mappings directly in the function space. Its multi-scale design enables the model to capture both simple, quasi-periodic macro-activities and more complex multi-person interactions by adjusting its receptive field according to the intrinsic structure of each activity class. To address class imbalance and representation collapse, the framework incorporates a Manifold-Preserving Local Density Oversampling (MPLDO) module that performs locality-constrained interpolation in a correlation-projected latent subspace, followed by classifier-guided pruning to maintain decision-boundary consistency. Experimental results show that the combined MS-FNO and MPLDO pipeline improves class-conditional separability and enhances recognition accuracy across both low-complexity and high-complexity activities. The findings highlight the effectiveness of this integrated operator-learning pipeline for privacy-aware activity monitoring in cafés, elder-care facilities, hospitals, and other real-world environments where coarse-to-complex activity understanding is required. Full article

The increasing availability of electronic clinical records has enabled new opportunities for predictive modeling in healthcare. However, clinical data are characterized by heterogeneous patient information, limited sample availability, and highly imbalanced outcome distributions, which may hinder the ability of predictive models to capture complex patterns and generalize across underrepresented groups. This work investigates deep learning-based representation learning strategies for predicting the final post-stroke functional state derived from the modified Rankin Scale (mRS) using clinical tabular data. The proposed methodology learns informative patient representations while addressing class imbalance without altering the original data distribution, avoiding limitations of conventional resampling strategies. Specifically, the proposed framework combines a TabTransformer encoder with Supervised Contrastive Learning and Focal Loss to jointly optimize discriminative representation learning and imbalance-aware classification. By obtaining more separable latent representations and reducing the bias toward majority-class predictions, the approach aims to improve the identification of patients with unfavorable functional outcomes. Experimental results show that the proposed model achieves the highest accuracy (0.92) and macro-averaged F1-score (0.80), with balanced minority-class precision (0.67) and recall (0.64), unlike the other models, which showed a trade-off between these metrics. These results demonstrate improved minority-class identification while maintaining overall predictive performance in clinical outcome prediction. Full article

Translational oncology has moved rapidly from histopathology and single-analyte biomarkers toward multi-dimensional molecular profiling. Yet many clinically deployed tests still use reductionist biomarker strategies that under-represent cancer complexity. This review examines whether a mechanistic, multi-layered, and specimen-aware approach can improve cancer detection, classification, prognosis, minimal residual disease (MRD) assessment, and therapeutic selection. Evidence across solid tumours shows that genomic alterations alone incompletely explain tumour state, metastatic behaviour, immune evasion, or therapeutic vulnerability. Integrated genome and transcriptome analyses, proteogenomics, single-cell atlases, fragmentomic, methylation based cell-free DNA assays, metabolomics and microbiome assessments reveal clinically relevant biology that single modality tests cannot determine. Minimally invasive collected specimens can extend access to screening, diagnosis and longitudinal monitoring, but the choice of specimen should be matched to disease biology and analytes that represent mechanisms of oncogenesis. However, translation remains constrained by pre-analytical variability, contamination, differences in tumour shedding behaviour, clonal haematopoiesis, translation of generated models, incomplete external validation and uncertain downstream clinical utility for emerging platforms. This review provides a commentary on the future of cancer diagnostics, the considerations and barriers to clinical translation, the relationship between utility and dimensionality of biomarkers assessed and the emerging rationale towards mechanistically grounded integrated models. Full article

The personal care product market has expanded rapidly in recent years, along with growing consumer awareness of chemical exposures and increasing demand for “clean” products. Consumer perceptions of product safety and potential health impacts are commonly based on ingredient labels, intended use, and certifications, rather than the full chemical composition of finished products. In this study, we conducted a targeted review of certification and ingredient-evaluation programs in the United States and European markets. Eighteen programs were identified and characterized based on their evaluation approaches, data sources, and whether they incorporate analytical measurement of finished products. We also evaluated the current U.S. and EU regulatory frameworks. Across both certification and regulatory systems, evaluation was found to rely primarily on ingredient-based approaches and supporting documentation, with limited incorporation of analytical measurement. As a result, contaminants, impurities, and incidentals/non-intentionally added substances (which have previously been identified in many consumer products) may not be consistently identified or evaluated for safety. These findings highlight a fundamental gap between intended formulation and actual product composition. Incorporating analytical measurement, particularly non-targeted approaches, provides a complementary groundwork for identifying previously unrecognized chemical exposures and improving the accuracy of product safety certification programs and hazard assessments. Aligning evaluation with measured chemical composition may enhance transparency and better reflect real-world exposure, support more credible sustainability claims, enhance consumer trust, support growing market demand, support consumer safety, and contribute to more effective regulation in the personal care industry. Full article

Predicting target intent in complex, dynamic multi-agent environments remains a formidable challenge due to incomplete perception and the highly dynamic nature of multi-target interactions. Conventional approaches—such as D-S evidence theory, expert systems, and Recurrent Neural Networks (RNNs)—are often constrained by data incompleteness and rigid behavioral assumptions, limiting their adaptability to dynamic high-value target identification and multi-target situational awareness on the ground. To address these challenges, a novel framework termed Threat Field–Gated Recurrent Unit (TF-GRU) is proposed. The TF-GRU framework integrates threat field modeling with a dynamic repair mechanism to enhance intent prediction under partial perception. Specifically, threat field modeling associates target attributes with intentions through the construction of static and dynamic threat fields, effectively capturing the temporal and semantic relationships among multiple targets. A particle filtering and dynamic time warping fusion strategy (PF-DTW) is employed to repair data gaps via short-term filtering and long-term trajectory matching, further refined by a neighborhood-angle constraint for accurate multi-target state estimation. In addition, trajectory and threat field features are processed using a Mish activation function and a threat-adaptive gating mechanism, which dynamically regulate information flow within the recurrent unit to model behavioral evolution. Experimental evaluations demonstrate that TF-GRU significantly enhances intent prediction accuracy under incomplete data conditions, thereby improving comprehensive situational awareness and supporting high-confidence decision-making in dynamic multi-target scenarios. Full article

Point-of-interest (POI) recommendation in location-based social networks (LBSNs) predicts a user’s next visit using check-in records. As critical factors influencing user decision making, geographic and social contexts are incorporated to deliver higher-quality recommendation services. However, current methods suffer from two limitations: geographical modeling is confined to distance thresholds, ignoring long-range spatio-temporal transitions, and social graphs remain static, failing to capture dynamic behavioral similarities among unconnected users. To address these gaps, we propose GSTRDFA (Global Spatio-Temporal Relationship- and Dynamic Friendship-Aware), a model comprising three layers. First, we construct spatio-temporal KGs (STKGs) that encode four relationship types: global spatio-temporal and local geospatial POI–POI links, dynamic user–user friendships, and static social ties. Second, four dedicated encoders—STSEncoder (spatio-temporal state embedding), GeoEncoder (geographical convolution), DFEncoder (graph attention network), and SocEncoder (GraphSAGE)—propagate and aggregate user and POI embeddings along these STKG relations. Third, a GRU-based sequence predictor uses the fused embeddings to match candidate POIs to the user. Evaluations on Foursquare datasets (NYC, JK, CA) show that GSTRDFA outperforms existing methods, improving Acc@1/5/10 and MRR by 0.24–3.31%. Key contributions include (1) unifying spatial, temporal, and dynamic social signals via STKGs; (2) jointly modeling global spatio-temporal transitions and dynamic friendships; and (3) enabling balanced short-/long-range and short-/long-term transition prediction. Full article

Internet of Things(IoT)/edge intrusion-detection systems operate on distributed traffic and system-state data whose distributions vary across gateways, services, and attack conditions. We study a server-assisted federated setting in which a teacher reference is fitted from a permitted server-accessible training pool and explicitly distinguish this simulation assumption from fully decentralized deployment. The proposed framework evaluates progressive local training through boundary stabilization, confidence-weighted decision distillation, representation alignment, and validation-quality-aware aggregation. The evaluation uses a leakage-controlled protocol: server and client validation subsets are held out before federated training, update quality and early stopping use validation data only, and the final-test split is evaluated once. Results on NSL-KDD, CIC-IDS2017, Edge-IIoTset, and the ToN-IoT network dataset show competitive primary performance and stronger robustness in several severe label-skew settings. On the Telemetry of Things(ToN-IoT) with Dirichlet alpha = 0.1, the proposed method achieves 91.46 ± 5.54 F1, compared with 53.73 ± 49.00 for FedAvg and 53.77 ± 48.92 for FedProx. The results do not establish universal superiority or a universally optimal stage order: competing methods remain stronger in selected stable and attack-shift settings. The framework is therefore presented as a bounded, server-assisted robustness-oriented training strategy for heterogeneous IoT/edge intrusion detection. Full article

Large-scale administrative hospital discharge data is a key resource for secondary health systems research, yet reuse is constrained by barriers of access, quality, interoperability, and semantic comparability. This paper presents and validates a reproducible, declarative, loss-aware harmonization framework for public discharge data that avoids full migration to a comprehensive common data model. The framework comprises a lightweight 14-field canonical model, versioned JSON crosswalks, a shared execution engine, a resilient file reader, schema validation, idempotency tests, value-domain checks, and an information-loss map. It was evaluated on public record-level discharge data from five jurisdictions on three continents (Korea, Brazil, Mexico, Chile, and New York State), comprising 561,966,231 harmonized records from 2001 to 2025. Validation demonstrated conformance to the declared source profiles for 82 of 99 files and full canonical conformance for 39, idempotency across all 99 files, 99.99% conformance with permitted value domains under an explicitly stated aggregation, and detection of source-level defects such as truncated files, malformed rows, and completeness anomalies. A marker-condition query for ischemic stroke (ICD-10 I63) showed that a single case definition executes consistently on the four sources retaining raw ICD-10 codes. The results show that, for heterogeneous administrative data, the key value lies not in scale alone but in the auditability of transformations, explicit loss documentation, and reproducibility of the harmonization process. Full article

LiDAR SLAM relies on reliable geometric constraints to estimate sensor motion and maintain consistent maps in complex three-dimensional environments. Planar features are commonly used for LiDAR registration, but repeatedly fitting local planes from neighboring points brings extra computation and may be sensitive to noisy observations. Voxel-plane maps address this issue by storing planar structures in voxel cells, yet most existing methods still construct planes and assign points to voxels according to the nominal point coordinates. When LiDAR measurement noise and pose prediction errors are ignored, plane parameters may be biased and points may be associated with unsuitable voxels. This paper presents UVP-LIO, an uncertainty-aware voxel-plane mapping method for LiDAR-inertial odometry. The measurement uncertainty of each LiDAR point and the uncertainty from state estimation are jointly propagated to the world frame to obtain a point-wise covariance. This covariance is then used in uncertainty-aware voxel association and covariance-weighted incremental plane updating. Plane thickness is further introduced to weight point-to-plane residuals during registration. Experiments in a LiDAR-only configuration on KITTI and in a LiDAR-inertial configuration on M3DGR show that UVP-LIO improves trajectory consistency and mapping robustness, especially in scenes with weak or ambiguous geometric constraints, while maintaining real-time performance. Full article

Accurate finite element models are essential for structural condition assessment, yet nominal material properties and idealized boundary conditions can produce systematic discrepancies between numerical and measured dynamics. This study proposes a physics-constrained sparse response-surface framework that combines Elastic Net basis selection, mechanically prescribed monotonicity, adaptive sample enrichment, and identifiability-aware uncertainty assessment within a transparent finite element model-updating procedure. A scaled steel truss was tested using millimeter-wave radar, and the first three vertical natural frequencies were identified by stochastic subspace identification. The resulting sparse polynomial surrogate was independently validated before bounded inversion and ANSYS back-substitution. The mean frequency error decreased from 5.55% to 0.82%. Jacobian and bootstrap analyses further showed that several combinations of material and boundary parameters can reproduce similar modal responses, so the updated parameters are best interpreted as a coupled equivalent calibration state rather than unique direct measurements. The proposed framework therefore improves physical consistency and computational efficiency while explicitly retaining the uncertainty associated with weakly identifiable parameter directions. Full article

Accurate State-of-Health (SOH) prediction is essential for deploying retired electric vehicle batteries into reliable second-life energy storage systems. However, this task is challenged by sparse and noisy operational data from onboard Battery Management Systems (BMS). This study systematically evaluates a spectrum of deep learning architectures for SOH forecasting under BMS-style data constraints derived from laboratory cycling data: a BiLSTM on aggregated cycle statistics (Model A), preliminary zero-shot transfer to a single unseen cell (Model B), a waveform BiLSTM with full intra-cycle voltage, current, and temperature trajectories (Model C), a baseline TCN (Model D) and a probabilistic TCN-GPR hybrid (Model E). All models are constrained to identical low-fidelity BMS-style variables extracted from the NASA battery aging dataset. Model C achieves the lowest point accuracy error of 0.46% ± 0.18% MAE across five random seeds, demonstrating that high-resolution waveform inputs capture degradation signatures, notably voltage plateau morphology, transient dynamics, and implicit SOC information, that aggregated features irreversibly lose. Model D using the same waveform inputs and evaluation protocol as Model C, achieves a MAE of 2.99% at a single seed, providing direct architectural comparison evidence that the BiLSTM’s position-sensitive temporal summarization outperforms GlobalAveragePooling1D under these conditions. Model E achieves a higher MAE of 2.12% ± 0.33% but uniquely provides calibrated predictive distributions of 99.4% ± 1.2% coverage, NLL = −1.877 ± 0.038, with approximately uniform 95% predictive intervals (mean width 19.83% SOH across 34 test cycles at seed = 42), reflecting the near-constant posterior variance produced by the large optimized GPR length-scale under the frozen two-stage training design. A paired t-test confirms that Model C statistically significantly outperforms Model E on point accuracy (p < 0.01). Isotonic regression recalibration reduces mean calibration error from 0.138 to 0.010, demonstrating that shape-level miscalibration is correctable post hoc. The central implication for second-life battery deployment is a clear accuracy–uncertainty trade-off: Model C is preferred when point estimates suffice, while Model E is essential for risk-aware decisions requiring confidence intervals. Full article

Fast charging of lithium-ion battery packs involves a compromise between charging speed, temperature rise, and aggressive current profiles that may accelerate battery degradation. This paper presents a current-stress-aware fuzzy logic control framework for safe fast charging of series-connected lithium-ion battery cells. The proposed controller uses a physically interpretable two-input, one-output fuzzy structure in which the highest cell-voltage difference, $V_d$, and the lowest single-cell voltage, $V_B$, are used to determine the charging-current command, $I_{\mathrm{charge}}$. Unlike conventional fuzzy charging approaches that rely on manually selected membership functions or weighted single-objective tuning, the proposed method simultaneously optimizes the Gaussian membership-function parameters and the input/output scaling gains using a Pareto-based multi-objective optimization framework. The resulting design vector contains 21 decision variables, including 18 membership-function parameters and three scaling gains. Three conflicting objectives are minimized: the time required to reach 95% state of charge, the maximum temperature rise above the reference temperature, and a normalized current-stress index based on the integral of the squared charging current. The framework is implemented in MATLAB/Simulink using a three-cell Panasonic NCR18650PF lithium-ion battery pack model. The obtained Pareto front reveals the expected trade-off between fast charging and battery protection. The fastest solution reaches 95% SOC in 5440 s but produces the highest temperature rise and current-stress index, whereas the selected knee-point controller reaches the target in 6880 s while reducing the maximum temperature rise and current-stress index compared with the fastest solution. Robustness tests under variations in initial SOC, cell imbalance, initial temperature, capacity scaling, and internal-resistance scaling show that the knee-point controller maintains stable charging behavior and satisfies the imposed thermal safety constraint. The results demonstrate that the proposed current-stress-aware Pareto-optimized fuzzy controller provides a systematic and interpretable approach for balancing charging speed, thermal safety, and battery stress in lithium-ion battery fast charging. Full article

Spatio-temporal epidemic forecasting aims to predict future outbreak trajectories across interconnected regions from historical epidemiological observations and meteorological covariates. However, existing approaches often fail to preserve historically salient epidemic states or to fully exploit delayed and region-varying meteorological associations, leading to unstable temporal representations and insufficient meteorological-context-aware spatio-temporal context for prediction at later forecast horizons. In this paper, we propose CASRL, a Climate-Aware Self-Retrospective Representation Learning network for stable and meteorological-context-aware spatio-temporal epidemic forecasting. CASRL first employs a Self-Retrospective Epidemic Encoder (SREE) to retrospectively aggregate historically salient epidemic states through query-guided weighting and adaptive gating, thereby preserving informative historical epidemic states within the look-back window. It then introduces a Climate-Adaptive Graph Message Passing (CAGMP) module that breaks away from traditional passive feature concatenation. Instead, it constructs a separate meteorological-view predictive graph conditioned on the static spatial prior and adaptively fuses it with the incidence-associated topology to model complex cross-regional predictive associations. By integrating self-retrospective epidemic representations with meteorological-view spatio-temporal interactions, CASRL produces forecasts with improved predictive stability at later forecast horizons. Extensive experiments on two public influenza benchmarks show that CASRL is competitive at shorter forecast horizons and provides clearer advantages at later forecast horizons, particularly in phase-alignment-related evaluation and 15-week-ahead forecasting. Full article

Temporal action localization (TAL) requires a detector to recognize action categories and estimate temporal boundaries in untrimmed videos. Mamba supports linear-complexity long-sequence modeling, yet a uniform allocation of state-space operators does not explicitly differentiate the context requirements associated with temporal scales and prediction branches. We present Multi-Scale Decoupled Routing Mamba (MSDR-Mamba), a multi-scale branch-decoupled routing state-space detector. The method combines a phase-dilated multi-rate Mamba temporal pyramid, multi-band state-time initialization, level-wise local–global gating guided by duration priors, and a branch role-decoupled head. The final head uses CNNs for classification and center-offset estimation, with Mamba used for class-specific start/end boundary neighbor modeling. With frozen InternVideo2-6B features on THUMOS14, MSDR-Mamba achieves a five-threshold mAP of 73.09%, exceeding TriDet by 0.43 percentage points. Supplementary experiments on ActivityNet-1.3 and P²ANet further evaluate the complete configuration under longer-duration and dense short action distributions. The results support scale- and branch-aware state-space modeling as a practical design strategy for TAL. Full article