Search Results (131)

Background/Objectives: Alzheimer’s disease (AD) remains a progressive neurodegenerative disorder with limited therapeutic options. This study aimed to develop an integrative multi-omics computational pipeline to identify diagnostic biomarkers and prioritize druggable therapeutic targets for AD. Methods: We integrated transcriptomic data from 1047 samples (547 AD, 500 controls) using weighted gene co-expression network analysis (WGCNA) and three machine learning algorithms (LASSO, Random Forest, SVM) with strict separation of training, feature selection, and evaluation. Single-cell RNA sequencing of 48,481 nuclei from entorhinal cortex, two-sample Mendelian randomization (MR) with Bayesian colocalization, and structure-based molecular docking with triplicate 500 ns molecular dynamics (MD) simulations were also employed. Results: Machine learning identified 10 consensus biomarker genes involved in synaptic vesicle cycling, ion transport, and calcium homeostasis (internal test AUC = 0.891, 95% CI: 0.836–0.946; external validation on GSE48350: AUC = 0.847, 95% CI: 0.798–0.896). Covariate-adjusted differential expression and MR with Bayesian colocalization converged on eight immune-related therapeutic targets including APOE, TREM2, and TYROBP ($p<0.05$; Bonferroni-corrected threshold $p<0.00625$). Single-cell analysis revealed oligodendrocyte expansion in AD (28.5% versus 24.8%), with target genes predominantly expressed in microglia and astrocytes. Virtual screening of 2634 FDA-approved drugs prioritized 10 exploratory repurposing candidates; indomethacin–TREM2 and celecoxib–CSF1R are primary exploratory candidates given structurally validated binding pockets. Triplicate MD simulations (15 $\mathsf{\mu }$s aggregate) showed force-field-consistent structural stability (RMSD ≤ 3.2 Å). A quantitative multi-omics convergence framework identified four Tier 1 targets (APOE, TREM2, TYROBP, CX3CR1) supported by ≥5 analytical layers ($P_{\mathrm{perm}}=0.0003$; note: three of five layers share the same transcriptomic input). Conclusions: These findings provide a multi-evidence computational framework linking diagnostic biomarkers and druggable neuroinflammatory targets for AD. All predictions require experimental validation in biochemical and cellular models before clinical conclusions can be drawn. Full article

Road traffic safety is central to socially resilient and sustainable cities, yet many middle-income countries lack harmonized subnational data on exposure, infrastructure, and enforcement. This study examines whether routinely available demographic composition can serve as a practical structural baseline for provincial traffic accident rates and as a diagnostic layer for richer safety models. Using official province–year data from Türkiye (2008–2019 and 2022–2024; n = 1215), demographic shares by sex, education, and age were treated as compositional inputs and transformed using isometric log-ratio (ILR) methods, with GDP per person included as a scalar covariate. A Tabular Residual Network (ResNet) was trained on the historical panel and evaluated on a post-period calibration/evaluation window (2022–2024), which was used for checkpoint selection and seed screening rather than as an independent held-out test set. Among the evaluated specifications, the ResNet seed-ensemble achieved the strongest performance on the 2022–2024 calibration/evaluation period (R² = 0.5717), outperforming the best single-seed model (R² = 0.5539), a province-specific last-value-carried-forward temporal heuristic based on 2019 values (R² = 0.4779), tree-based tabular benchmarks (Random Forest: R² = 0.1328; XGBoost: R² = 0.0706), and pooled statistical reference models (linear: R² = 0.1375; negative binomial: R² = 0.0686; Poisson: R² = −0.0634). Year-wise diagnostics indicated gradual temporal drift, suggesting that periodic recalibration or the inclusion of additional policy-relevant covariates is needed to preserve calibration. Overall, ILR-based compositional geodemography provides a scalable and interpretable baseline for traffic safety monitoring and prioritization in data-constrained settings. Full article

The Permian Wargal Formation of the western Salt Range preserves a shallow marine carbonate-ramp succession, in which heterogeneity reflects coupled depositional architecture, facies-selective diagenesis, and deformation-related structural compartmentalisation of the Wargal interval. This study integrates balanced restoration with stratigraphic logging, microfacies analysis, paragenetic reconstruction, and quantitative pore-network topology to evaluate how stratigraphic packaging and diagenetic overprint govern connected pathway development within a structurally partitioned fold–thrust setting. Balanced restoration of a representative transect yields 1.1336 km of minimum tectonic shortening (18.7%) and indicates shortening shared between thrust slip and distributed folding, providing an admissible geometric framework for assessing compartmentalisation. The Wargal succession is ~130 m thick and organised into three carbonate packages bounded by laterally persistent argillaceous marker intervals (~21–23 m and ~98–105 m), with grain-supported shoal to shoal-margin facies dominating intervening units. Diagenesis is strongly facies-selective; grain-supported microfacies record progressive calcite cementation that occludes pore throats, whereas mud-supported facies retain microporosity but are preferentially modified by neomorphism, compaction, and pressure-solution fabrics. Image-based analysis of 20 thin-section fields of view shows that pore connectivity varies systematically among microfacies and that a connectivity-weighted index ($I_{\mathrm{conn}}$) covaries more closely with skeleton-derived connectivity than with segmented areal porosity (${\varphi }_{2D}=0.124$–9.750%). The combined results quantify the decoupling between pore volume and connectivity and provide a basis for predicting reservoir-quality evolution from facies architecture, diagenetic sequence, and structural segmentation, with direct relevance to subsurface characterisation of marine carbonate successions in hydrocarbon systems. Full article

Understanding how migratory waterbird species co-vary through time can reveal guild structure and guide monitoring in dynamic coastal wetlands, yet seasonal phenology can inflate simple co-occurrence signals. Here, we used standardized monthly bird counts from Yongan Wetland, Taiwan (36 survey months across two survey blocks: November 2014 and January–August 2015, and October 2016–December 2018) to infer de-seasonalized interspecific associations. We analyzed 50 regularly recorded species and a focal subset of 13 shorebirds and ducks. For each species, we transformed raw counts to monthly anomalies that remove recurrent seasonal patterns, then quantified pairwise Spearman correlations and controlled multiple testing using Benjamini–Hochberg FDR (q ≤ 0.05) to construct association networks. The anomaly-based network revealed strong guild structure: positive links were concentrated within dabbling ducks and within shorebirds, consistent with shared habitat use and foraging regimes, whereas negative links were fewer and suggested potential niche partitioning or spatiotemporal segregation. Robustness analyses (moving-block bootstrap stability, a circular-shift null comparison, and log-transformed anomaly sensitivity) supported that the main network patterns were unlikely to arise from chance alignment. Our framework provides a transparent, time-series–based approach for disentangling phenology from association inference, offering a practical framework for wetland monitoring and hypothesis generation about waterbird community dynamics. Full article

Propagating easterly waves (EW) are analyzed here, within the dynamical environment of the Caribbean Low-Level Jet (CLLJ) using radiosondes from the Organization of Tropical East Pacific Convection (OTREC) field campaign, ERA5 reanalysis, and lightning from the World Wide Lightning Location Network (WWLLN) over $5^{\circ }$–${20}^{\circ }$ N, ${60}^{\circ }$–${100}^{\circ }$ W during 21 August–30 September 2019. Radiosondes resolve the vertical structure of the waves at San Andrés (Colombia), Limón and Santa Cruz–Guanacaste (Costa Rica), while ERA5 provides spatial–temporal continuity and vertically integrated diagnostics—namely, the vertically integrated moisture flux divergence (VIMFD) and the vertically integrated geopotential flux divergence (VIGFD). Lightning from WWLLN and precipitation from ERA5 and the Integrated Multi-satellite Retrievals for the Global Precipitation Measurement mission (GPM IMERG) offer independent convective proxies to track disturbances. Mean profiles from radiosondes and ERA5 show strong agreement at Limón and Guanacaste and some differences at San Andrés, yet all datasets capture coherent, phase-locked anomalies in zonal wind, meridional wind, temperature, humidity, vertical velocity and vorticity used to diagnose EW–CLLJ interactions. VIMFD, VIGFD, lightning and precipitation exhibit westward-propagating cores that align with the above anomalies, indicating that organized convection is coupled to the disturbances, whereas the mean state preconditions the environment to enable wave-induced upward motion. A robust vertical adjustment of the CLLJ is documented: the core shifts from near 925 hPa over the Caribbean Sea to about 700 hPa over the Eastern Tropical Pacific ($\Delta p\sim 150$ hPa). This feature is reproduced by a 30-year ERA5 climatology, consistent with jet-exit forcing and enhanced boundary-layer coupling over land. Conditions favorable for barotropic instability using the Rayleigh–Kuo criterion, were present over most of the period. A qualitative barotropic conversion proxy, computed from the eddy momentum covariance $⟨u^{\prime }{v}^{\prime }⟩$, shows positive values in the lower troposphere at Guanacaste and in the layer 850–700 hPa at San Andrés, suggesting mean-to-eddy momentum transfer, whereas the signal at Limón is weaker. Together, these results provide a physically consistent view of EW–CLLJ interactions across the IAS; therefore, a schematic of those mechanisms is proposed here. The results highlight the need for high-resolution modeling and full energy-budget analyses. Full article

Smart energy networks, including electricity distribution and district heating, are increasingly operated as sensor-enabled infrastructures where maintenance decisions must be made under heterogeneous and time-varying operating conditions. In these settings, time-to-event data are rarely complete; preventive actions and limited observation horizons routinely introduce censoring and truncation, so models and validation procedures must account for partially observed lifetimes to avoid biased inference and misleading performance estimates. This review surveys survival models for predictive maintenance (PdM) and remaining useful life (RUL) estimation, spanning non-parametric, semi-parametric, parametric, and learning-based approaches, with emphasis on censoring-aware formulations and the use of static and time-varying covariates derived from sensor, inspection, and contextual information. A structured taxonomy and a systematic mapping of model families to data types, core assumptions (proportional hazards versus parametric distributional structure), and decision-oriented outputs such as risk ranking, horizon failure probabilities, and RUL distributions are presented. Evaluation practice is also synthesized by covering discrimination metrics, censoring-aware RUL accuracy measures, and probabilistic assessment via proper scoring rules, including the time-dependent Brier score and Integrated Brier Score (IBS). The review provides researchers and practitioners with a practical guide to selecting, fitting, and evaluating survival models for risk-informed maintenance planning in smart energy networks. Full article

Background: Previous research has found that mindfulness-based techniques are beneficial for reducing stress in heavy-drinking individuals. However, the underlying neurobiology of these stress-reducing effects are unclear. Moreover, much of the research examining neurobiological correlates of mindfulness has used static functional connectivity, suggesting that brain activity goes unchanged for the entire length of an MRI scan. Methods: In the current study, we used a state-based dynamic functional connectivity model to examine brain states during either a 10 min mindfulness session or resting control that followed an individually tailored stress imagery task. Using a hidden semi-Markov model (HSMM), six brain states and the associated dynamics of state traversal were estimated for a population of moderate-to-heavy drinkers (N = 32). We modeled the 36 Schaefer atlas regions spanning the salience and default mode networks, and the HSMM characterized each state by its distinct multivariate pattern of activity and covariance structure. Group differences in dwell times, transition behavior, and overall state dynamics were evaluated using permutation tests and mixed-effects models. Results: Participants that experienced the mindfulness session had more transitions and longer time spent in states in which the salience network was more active. Participants assigned to the control group had more transitions and increased time spent in states in which nodes of the default mode network were more active. Moreover, for control participants, increased occupancy time to SN-dominant states was associated with lower perceived stress. Conclusions: Using HSMM provided a unique insight into network connectivity during mindful states; we believe it offers a novel approach to testing and optimizing mindful-based therapies. Full article

Background: Disability progression in multiple sclerosis (MS) is increasingly recognized as a consequence of large-scale brain network disruption rather than isolated regional damage. Although diffusion tensor imaging (DTI) is the reference method for assessing structural connectivity, its limited availability restricts widespread clinical application. There is therefore a critical need for alternative approaches capable of capturing network-level alterations using routinely acquired MRI data. Objective: This study aimed to determine whether synthetic structural connectivity matrices derived from standard regional volumetric MRI can capture clinically meaningful network alterations in MS and predict subsequent functional progression, particularly upper limb decline. Methods: Regional brain volumetry was obtained from routine T1-weighted MRI using an automated, clinically approved volumetric pipeline. Synthetic structural connectivity matrices were generated by integrating principles of structural covariance, distance-dependent connectivity, and disease-specific vulnerability patterns. Graph-theoretical network metrics were extracted to characterize global and regional topology. Machine learning models including logistic regression, support vector machines, random forests, and gradient boosting were trained to predict clinical progression defined by worsening on the 9-Hole Peg Test. Dimensionality reduction was performed using principal component analysis, and model performance was evaluated using balanced accuracy, AUC-ROC, and resampling-based validation. Feature importance analyses were conducted to identify network vulnerability patterns. Results: Synthetic connectivity networks exhibited biologically plausible properties, including preserved but attenuated small-world organization. Global efficiency showed a strong inverse correlation with disability severity (EDSS). Patients with clinical progression demonstrated marked reductions in network integration and segregation, alongside increased characteristic path length. Machine learning models achieved robust prediction of upper limb functional decline, with ensemble-based methods performing best (balanced accuracy > 80%, AUC-ROC up to 0.85). A limited subset of connections accounted for a disproportionate share of predictive power, predominantly involving frontoparietal associative networks, thalamocortical pathways, and inter-hemispheric connections. In a longitudinal subset, network-level alterations preceded measurable clinical deterioration by several months. Conclusions: Synthetic structural connectivity derived from routine volumetric MRI captures clinically relevant network-level disruption in multiple sclerosis and enables accurate prediction of functional progression. By bridging network neuroscience with widely accessible imaging data, this framework provides a pragmatic alternative for connectomic analysis when diffusion imaging is unavailable and supports a network-based understanding of disease evolution in MS. Full article

We develop and evaluate a deep contextual bandit framework for multivariate off-policy evaluation within a controlled simulation-based validation setting. Using real covariate distributions from the Adult, Boston Housing, and Wine Quality datasets, we construct synthetic treatment assignments and multivariate potential outcomes to enable rigorous benchmarking under known data-generating processes. We compare CNN-LSTM, LSTM, and Feed-forward Neural Network (FNN) architectures as nonlinear action-value estimators. To examine representation learning under structured dependence, an $AR\left(1\right)$ feature augmentation scheme is employed, while multivariate outcomes are standardized using empirical copula transformations to preserve cross-dimensional dependence. Policy values are estimated using Stabilized Importance Sampling (SIPS) and doubly robust (DR) estimators with bootstrap inference. Although the decision problem is strictly one-step, empirical results indicate that CNN-LSTM architectures provide competitive action-value calibration under temporal augmentation. Across all datasets, the DR estimator demonstrates substantially lower variance and greater stability than SIPS, consistent with its theoretical variance-reduction properties. Diagnostic analyses—including propensity overlap assessment, cumulative oracle regret (with oracle values known by construction), calibration evaluation, and sensitivity analysis—support the reliability of the proposed evaluation framework. Overall, the results demonstrate that combining copula-normalized multivariate outcomes with doubly robust off-policy evaluation yields a statistically principled and variance-efficient approach for offline policy learning in high-dimensional simulated environments. Full article

Remote sensing scene classification (RSSC) plays a crucial role in Earth observation. Current deep learning methods, while accurate, tend to focus on high-level semantic features and overlook complementary shallow details such as edges and textures. Moreover, conventional CNNs are limited by fixed receptive fields, whereas transformers incur high computational costs. To address these limitations, we propose the Lie Group lightweight multi-scale network (LGLMNet), a lightweight multi-scale network that integrates Lie Group covariance features. It employs a dual-branch architecture combining Lie Group machine learning (LGML) for shallow feature extraction and a deep learning branch for high-level semantics. In the deep branch, we design a parallel depthwise separable convolution block (PDSCB) for multi-scale perception and a spatial-channel collaborative attention mechanism (SCCA) for efficient global–local modeling. A cross-layer feature fusion block (CLFFB) effectively merges the two branches. Compared with state-of-the-art methods, the proposed LGLMNet achieves accuracy improvements of 2.14%, 2.32%, and 1.12% on UCM-21, AID, and NWPU-45 datasets, respectively, while maintaining a lightweight structure with only 2.6 M parameters. Full article

City-scale forecasting is essential for both electric-vehicle (EV) charging operations (e.g., peak management and resource allocation) and urban mobility management (e.g., road-network flow monitoring and incident response). Spatio-temporal graph neural networks (STGNNs) are a natural candidate for these problems, yet their performance often critically depends on the choice of a predefined graph prior and the availability/quality of exogenous signals. Importantly, we do not intentionally construct a poor graph; rather, we treat any predefined adjacency as a testable hypothesis and verify its alignment with the forecasting target via no-graph ablations and lightweight diagnostics ($\Delta corr$, $E_D$). In this work, we present a unified experimental pipeline based on a spatio-temporal graph convolutional network (STGCN) backbone and conduct systematic ablations on (i) whether and how a predefined static graph is used and (ii) how feature sets influence multi-step forecasting accuracy. We evaluate on two city-scale hourly datasets with heterogeneous node counts (UrbanEV: 275 nodes; CHARGED-AMS_remove_zero: 1388 nodes) and a 24 h input/6 h output setting. Across datasets, we find that a static graph can be beneficial only when it matches the true dependency structure; otherwise, it may degrade accuracy substantially. On UrbanEV, removing the graph component improves overall MAE from 116.21 ± 5.43 to 66.53 ± 1.71 (S = 5 seeds, 0–4), outperforming a persistence baseline (MAE 94.16). Feature ablations further analyze how occupancy and price signals affect UrbanEV accuracy (e.g., MAE 87.32 with all features under the evaluated feature setting). On CHARGED, the volume-only setting performs best among tested feature combinations (MAE 0.127), closely tracking a persistence baseline (MAE 0.139), while additional covariates may introduce noise under static modeling. We provide detailed multi-horizon results and discuss practical implications for when graph priors help or hurt in real deployments. Full article

Networked systems operating under uncertainty require decision making frameworks capable of balancing nominal efficiency and robustness against correlated risks. In this work, we study a distributionally robust weighted dominating set problem as a system-level model for robust network design, where node selection decisions are affected by uncertainty in costs and their correlation structure. We formulate the problem as a bi-objective optimization model that simultaneously minimizes the expected price and a risk measure derived from mean–covariance ambiguity. Rather than proposing new optimization algorithms, we conduct a systematic, methodological, and computational analysis of classical multiobjective solution approaches within this nonconvex and combinatorial setting. In particular, we compare weighted-sum, lexicographic, and $\epsilon$-constraint methods, highlighting their ability to reveal different structural properties of the Pareto Frontier. Our numerical results demonstrate that the methods that use scalarization allow us to obtain only partial insights for networked systems where robustness is inherent. However, the $\epsilon$-constraint method is highly efficient in recovering the full set of Pareto-optimal solutions. Once obtained, the Pareto Frontier exposes non-supported solutions and disruptive changes in its form. Notice that the latter is directly related to different configurations of dominating sets which are induced by the uncertainties. Consequently, these observations allow us to select from different subsets of relevant operating conditions for robust network designs that are significantly different for a decision maker. Full article

In Internet of Things (IoT) systems, data collected by geographically distributed sensors is often incomplete due to device failures, harsh deployment conditions, energy constraints, and unreliable communication. Such data gaps can significantly degrade downstream data processing and decision-making, particularly when failures result in the loss of all locally redundant sensors. Conventional imputation approaches typically rely on historical trends or multi-sensor fusion within the same target environment; however, historical methods struggle to capture emerging patterns, while same-location fusion remains vulnerable to single-point failures when local redundancy is unavailable. This article proposes a correlation-aware, cross-location data fusion framework for data imputation in IoT networks that explicitly addresses single-point failure scenarios. Instead of relying on co-located sensors, the framework selectively fuses semantically similar features from independent and geographically distributed gateways using summary statistics-based and correlation screening to minimize communication overhead. The resulting fused dataset is then processed using a lightweight KNN with an Iterative PCA imputation method, which combines local neighborhood similarity with global covariance structure to generate synthetic data for missing values. The proposed framework is evaluated using real-world weather station data collected from eight geographically diverse locations across the United States. The experimental results show that the proposed approach achieves improved or comparable imputation accuracy relative to conventional same-location fusion methods when sufficient cross-location feature correlation exists and degrades gracefully when correlation is weak. By enabling data recovery without requiring redundant local sensors, the proposed approach provides a resource-efficient and failure-resilient solution for handling missing data in IoT systems. Full article

Multi-branch deep neural networks like AASIST3 achieve state-of-the-art comparable performance in audio anti-spoofing, yet their internal decision dynamics remain opaque compared to traditional input-level saliency methods. While existing interpretability efforts largely focus on visualizing input artifacts, the way individual architectural branches cooperate or compete under different spoofing attacks is not well characterized. This paper develops a framework for interpreting AASIST3 at the component level. Intermediate activations from fourteen branches and global attention modules are modeled with covariance operators whose leading eigenvalues form low-dimensional spectral signatures. These signatures train a CatBoost meta-classifier to generate TreeSHAP-based branch attributions, which we convert into normalized contribution shares and confidence scores ($C_b$) to quantify the model’s operational strategy. By analyzing 13 spoofing attacks from the ASVspoof 2019 benchmark, we identify four operational archetypes—ranging from “Effective Specialization” (e.g., A09, Equal Error Rate (EER) 0.04%, $C=1.56$) to “Ineffective Consensus” (e.g., A08, EER 3.14%, $C=0.33$). Crucially, our analysis exposes a “Flawed Specialization” mode where the model places high confidence in an incorrect branch, leading to severe performance degradation for attacks A17 and A18 (EER 14.26% and 28.63%, respectively). These quantitative findings link internal architectural strategy directly to empirical reliability, highlighting specific structural dependencies that standard performance metrics overlook. Full article

Reliable forecasting of karst spring discharge is critical for sustainable groundwater resource management under the dual pressures of climate change and intensified anthropogenic activities. This study proposes a Heterogeneous Spatiotemporal Graph Attention Network (H-STGAT) to predict spring discharge dynamics at Shentou Spring, Shanxi Province, China. Unlike conventional spatiotemporal networks that treat all relationships uniformly, our model derives its heterogeneity from a graph structure that explicitly categorizes spatial, temporal, and periodic dependencies as unique edge classes. Specifically, a dual-layer attention mechanism is designed to independently extract hydrological features within each relational channel while dynamically assigning importance weights to fuse these multi-source dependencies. This architecture enables the adaptive capture of spatial heterogeneity, temporal dependencies, and multi-year periodic patterns in karst hydrological processes. Results demonstrate that H-STGAT outperforms both traditional statistical and deep learning models in predictive accuracy, achieving an RMSE of 0.22 m³/s and an NSE of 0.77. The model reveals a long-distance recharge pattern dominated by high-altitude regions, a finding validated by independent isotopic evidence, and accurately identifies an approximately 4–6 month lag between precipitation and spring discharge, which is consistent with the characteristic hydrological lag identified through statistical cross-covariance analysis. This research enhances the understanding of complex mechanisms in karst hydrological systems and provides a robust predictive tool for sustainable groundwater management and ecological conservation, while offering a generalizable methodological framework for similar complex karst hydrological systems. Full article