Search Results (681)

Background/Objectives: Glioblastoma (GBM) exhibits heterogeneous, nonlinear invasion patterns that challenge conventional modeling and radiomic prediction. Most deep learning approaches describe the morphology but rarely capture the dynamical stability of tumor evolution. We propose an AI framework that approximates a latent attractor landscape of GBM morphodynamics—stable basins in a continuous manifold that are consistent with reproducible morphologic regimes. Methods: Multimodal MRI scans from BraTS 2020 (n = 494) were standardized and embedded with a 3D autoencoder to obtain 128-D latent representations. Unsupervised clustering identified latent basins (“attractors”). A neural ordinary differential equation (neural-ODE) approximated latent dynamics. All dynamics were inferred from cross-sectional population variability rather than longitudinal follow-up, serving as a proof-of-concept approximation of morphologic continuity. Voxel-level perturbation quantified local morphodynamic sensitivity, and proof-of-concept control was explored by adding small inputs to the neural-ODE using both a deterministic controller and a reinforcement learning agent based on soft actor–critic (SAC). Survival analyses (Kaplan–Meier, log-rank, ridge-regularized Cox) assessed associations with outcomes. Results: The learned latent manifold was smooth and clinically organized. Three dominant attractor basins were identified with significant survival stratification (χ² = 31.8, p = 1.3 × 10⁻⁷) in the static model. Dynamic attractor basins derived from neural-ODE endpoints showed modest and non-significant survival differences, confirming that these dynamic labels primarily encode the morphodynamic structure rather than fixed prognostic strata. Dynamic basins inferred from neural-ODE flows were not independently prognostic, indicating that the inferred morphodynamic field captures geometric organization rather than additional clinical risk information. The latent stability index showed a weak but borderline significant negative association with survival (ρ = −0.13 [−0.26, −0.01]; p = 0.0499). In multivariable Cox models, age remained the dominant covariate (HR = 1.30 [1.16–1.45]; p = 5 × 10⁻⁶), with overall C-indices of 0.61–0.64. Voxel-level sensitivity maps highlighted enhancing rims and peri-necrotic interfaces as influential regions. In simulation, deterministic control redirected trajectories toward lower-risk basins (≈57% success; ≈96% terminal distance reduction), while a soft actor–critic (SAC) agent produced smoother trajectories and modest additional reductions in terminal distance, albeit without matching the deterministic controller’s success rate. The learned attractor classes were internally consistent and clinically distinct. Conclusions: Learning a latent attractor landscape links generative AI, dynamical systems theory, and clinical outcomes in GBM. Although limited by the cross-sectional nature of BraTS and modest prognostic gains beyond age, these results provide a mechanistic, controllable framework for tumor morphology in which inferred dynamic attractor-like flows describe latent organization rather than a clinically predictive temporal model, motivating prospective radiogenomic validation and adaptive therapy studies. Full article

Understanding the impact of human disturbance on urban vegetation is a key issue in urban sustainability, particularly in complex urban ecosystems. Using the COVID-19 lockdown as a quasi-natural experiment, this study examined vegetation responses to varying disturbance intensities across a university campus, comparing a low-disturbance phase (April 2022) with short-term recovery (July 2022, when human activity resumed) and long-term recovery (April 2024). Human disturbance was quantified based on activity restriction, duration, and population density, while vegetation responses were assessed using the Normalized Difference Vegetation Index (NDVI) and Fractional Vegetation Cover (FVC) across woodlands, lawns, and greenways. Results revealed significant spatial and temporal variability: High-intensity zones showed rapid but short-lived recovery, driven by seasonal phenology and the structural filling of exposed surfaces, but failed to sustain these gains over the long term. In contrast, moderate- and low-intensity areas exhibited more stable, long-term recovery, consistent with the Intermediate Disturbance Hypothesis. Woodlands demonstrated strong ecological stability, lawns maintained consistent recovery under regular management, and greenways showed greater resilience in enclosed segments. These findings indicate that regulated human activity can coexist with ecological resilience, providing evidence-based insights for differentiated management of urban green spaces and sustainable recovery strategies. Full article

To address clock drift arising from the absence of GPS synchronization during ocean-bottom seismic observations, we propose a time-offset correction and quality-control scheme that uses the correlation of P-wave empirical Green’s functions (EGFs) as the metric, and we demonstrate its efficacy in mitigating cross-correlation asymmetry caused by azimuthal noise in shallow-water environments. The method unifies the time delays of the four components into a single objective function, estimates per-node offsets via sparse weighted least squares with component-specific weights, applies spatial second-difference smoothing to suppress high-frequency oscillations, and performs spatiotemporally constrained regularized iterative optimization initialized by the previous day’s inversion to achieve a robust solution. Tests on a real four-component ocean-bottom node (4C-OBN) hydrocarbon exploration dataset show that, after conventional linear clock-drift correction of the OBN system, the proposed method can effectively detect millisecond-scale time jumps on individual nodes; compared with traditional noise cross-correlation time-shift calibration based on surface-wave symmetry, our four-component fusion approach achieves superior robustness and accuracy. The results demonstrate a marked increase in the coherence of the four-component cross-correlations after correction, providing a reliable temporal reference for subsequent multicomponent seismic processing and quality control. Full article

Satellite videos are widely applied for large-scale surveillance. Existing low-rank matrix decomposition-based methods produce promising results under simple and stationary backgrounds. However, these methods suffer a severe performance drop on satellite videos with complex and dynamic backgrounds. To address these challenges, we propose a matrix-based total variation regularized robust PCA (TV-RPCA) approach for moving-vehicle detection. Specifically, our TV-RPCA uses the partial sum of singular values to model the low-rank background. Moreover, a ${\mathit{\ell }}_p$ norm and a spatial–temporal TV regularization are adopted to encourage the spatial–temporal continuity of foregrounds. The optimization of our TV-RPCA is carried out using the augmented Lagrangian multiplier framework combined with the alternating direction minimization approach. Comprehensive experiments conducted on SkySat and Jilin-1 video data verify the effectiveness of the proposed approach. Full article

Accurate environmental prediction is crucial for ecological monitoring and disaster early warnings, but it remains challenging due to the spatiotemporal complexity of dynamic wireless sensor networks (WSNs). To this end, we propose a novel hybrid model that integrates a convolutional neural network (CNN), bidirectional long short-term memory (BiLSTM), and a black-winged kite algorithm (BKA). The CNN first extracts spatial features from multi-node sensor data to capture local environmental patterns. Subsequently, the BKA optimizes key CNN hyperparameters (learning rate, hidden layers, and regularization coefficients) to enhance the robustness of feature representation to noise and missing data. Subsequently, the BiLSTM processes the optimization features to model bidirectional long-term time dependencies (e.g., circadian rhythms, seasonal trends) to achieve accurate environmental predictions. Evaluation of the BKA-optimized CNN-BiLSTM model shows that our framework reduces prediction error by 19.3% to 32.7% compared to other models, achieving 89.4% accuracy in predicting extreme weather events. The synergy between BKA-driven CNN optimization and BiLSTM temporal dynamics modeling significantly improves the reliability of environmental prediction in resource-constrained sensor networks. Full article

Session-based recommender systems (SBRs) are critically impaired by exposure bias in observational training logs, causing models to overfit to logging policies rather than true user preferences. This bias distorts offline evaluation and harms generalization, particularly for long-tail items. To address this, we propose the Propensity- and Temporal-consistency Enhanced Graph Transformer (PTE-GT), a principled framework that enhances a recent interval-aware graph transformer backbone with two synergistic training-time modules. This Graph Neural Network -based architecture is adept at modeling the complex, graph-structured nature of session data, capturing intricate item transitions that sequential models might miss. First, we introduce a propensity-aware (PA) optimization objective based on the self-normalized inverse propensity scoring (SNIPS) estimator. This module leverages logs containing randomized exposure or logged behavior-policy propensities to learn an unbiased risk estimate, correcting for the biased data distribution. Second, we design a lightweight, view-free temporal consistency (TC) contrastive regularizer that enforces alignment between session prefixes and suffixes, improving representation robustness without computationally expensive graph augmentations, which are often a bottleneck for graph-based contrastive methods. We conduct comprehensive evaluations on three public session-based benchmarks—KuaiRand, the OTTO e-commerce challenge dataset (OTTO), and the YOOCHOOSE-1/64 split (YOOCHOOSE)—and additionally on the publicly available Open Bandit Dataset (OBD) containing logged bandit propensities. Our results demonstrate that PTE-GT significantly outperforms strong baselines. Critically, on datasets with randomized exposure or logged propensities, our unbiased evaluation protocol, using SNIPS-weighted metrics, reveals a substantial performance leap that is masked by standard, biased metrics. Our method also shows marked improvements in model calibration and long-tail item recommendation. Full article

Time series and spatio-temporal forecasting are fundamental tasks for complex system modeling and intelligent decision-making, with broad applications in transportation, meteorology, finance, healthcare, and public safety. Compared with simple univariate time series, real-world spatio-temporal data exhibit rich temporal dynamics and intricate spatial interactions, leading to heterogeneity, non-stationarity, and evolving topologies. Addressing these challenges requires modeling frameworks that can simultaneously capture temporal evolution, spatial correlations, and cross-domain regularities. This survey provides a comprehensive synthesis of forecasting methods, spanning statistical algorithms, traditional machine learning approaches, neural architectures, and recent generative and causal paradigms. We review the methodological evolution from classical linear models to deep learning–based temporal modules and emphasize the role of attention-based Transformers as general-purpose sequence architectures. In parallel, we distinguish these architectural advances from pre-trained foundation models for time series and spatio-temporal data (e.g., large models trained across diverse domains), which leverage self-supervised objectives and exhibit strong zero-/few-shot transfer capabilities. We organize the review along both data-type and architectural dimensions—single long-term time series, Euclidean-structured spatio-temporal data, and graph-structured spatio-temporal data—while also examining advanced paradigms such as diffusion models, causal modeling, multimodal-driven frameworks, and pre-trained foundation models. Through this taxonomy, we highlight common strengths and limitations across approaches, including issues of scalability, robustness, real-time efficiency, and interpretability. Finally, we summarize open challenges and future directions, with a particular focus on the joint evolution of graph-based, causal, diffusion, and foundation-model paradigms for next-generation spatio-temporal forecasting. Full article

In Mexico, the Deaf community faces persistent communication barriers that restrict their integration and access to essential services, particularly in healthcare. Even though approximately two million individuals use Mexican Sign Language (MSL) as their primary form of communication, technological tools for supporting effective interaction remain limited. While recent research in sign-language recognition has led to important advances for several languages, work focused on MSL, particularly for healthcare scenarios, remains scarce. To address this gap, this study introduces a health-oriented dataset of 150 signs, with 800 synthetic video sequences per word, totaling more than 35 GB of data. This dataset was used to train recurrent neural networks with regularization and data augmentation. The best configuration achieved a maximum precision of 98.36% in isolated sign classification, minimizing false positives, which is an essential requirement in clinical applications. Beyond isolated recognition, the main contribution of this study is its exploratory evaluation of sequential narrative inference in MSL. Using short scripted narratives, the system achieved a global sequential recall of 45.45% under a realistic evaluation protocol that enforces temporal alignment. These results highlight both the potential of recurrent architectures in generalizing from isolated gestures to structured sequences and the substantial challenges posed by continuous signing, co-articulation, and signer-specific variation. While not intended for clinical deployment, the methodology, dataset, and open-source implementation presented here establish a reproducible baseline for future research. This work provides initial evidence, tools, and insights to support the long-term development of accessible technologies for the Deaf community in Mexico. Full article

Attention-Deficit/Hyperactivity Disorder (ADHD) is a highly prevalent neurodevelopmental condition that is typically identified through behavioral assessments and subjective clinical reports. However, electroencephalography (EEG) offers a cost-effective and non-invasive alternative for capturing neural activity patterns closely associated with this disorder. Despite this potential, EEG-based ADHD classification remains challenged by overfitting, dependence on extensive preprocessing, and limited interpretability. Here, we propose a novel neural architecture that integrates transformer-based temporal attention with Gaussian mixture functional connectivity modeling and a cross-entropy loss regularized through $\alpha$-Rényi mutual information, termed T-GARNet. The multi-scale Gaussian kernel functional connectivity leverages parallel Gaussian kernels to identify complex spatial dependencies, which are further stabilized and regularized by the $\alpha$-Rényi term. This design enables direct modeling of long-range temporal dependencies from raw EEG while enhancing spatial interpretability and reducing feature redundancy. We evaluate T-GARNet on a publicly available ADHD EEG dataset using both leave-one-subject-out (LOSO) and stratified group k-fold cross-validation (SGKF-CV), where groups correspond to control and ADHD, and compare its performance against classical and modern state-of-the-art methods. Results show that T-GARNet achieves competitive or superior performance (82.10% accuracy), particularly under the more challenging SGKF-CV setting, while producing interpretable spatial attention patterns consistent with ADHD-related neurophysiological findings. These results underscore T-GARNet’s potential as a robust and explainable framework for objective EEG-based ADHD detection. Full article

Financial fraud detection is critical to modern economic security, yet remains challenging due to collusive group behavior, temporal drift, and severe class imbalance. Most existing graph neural network (GNN) detectors rely on pairwise edges and correlation-driven learning, which limits their ability to represent high-order group interactions and makes them vulnerable to spurious environmental cues (e.g., hubs or temporal bursts) that correlate with labels but are not necessarily causal. We propose Causal-DHG, a dynamic hypergraph framework that integrates hypergraph modeling, causal intervention, and multi-view contrastive learning. First, we construct label-agnostic hyperedges from publicly available metadata to capture high-order group structures. Second, a Multi-Head Spatio-Temporal Hypergraph Attention encoder models group-wise dependencies and their temporal evolution. Third, a Causal Disentanglement Module decomposes representations into causal and environment-related factors using HSIC regularization, and a dictionary-based backdoor adjustment approximates the interventional prediction $P(Y\mid do(C\left)\right)$ to suppress spurious correlations. Finally, we employ self-supervised multi-view contrastive learning with mild hypergraph augmentations to leverage unlabeled data and stabilize training. Experiments on YelpChi, Amazon, and DGraph-Fin show consistent gains in AUC/F1 over strong baselines such as CARE-GNN and PC-GNN, together with improved robustness under feature and structural perturbations. Full article

Background: Wearable EEG devices offer an accessible and unobtrusive system for regular brain health monitoring outside clinical settings. However, due to the current lack of data available from wearable low-density EEG devices, we need to anticipate the extraction of biomarkers for brain health evaluation from available clinical datasets. Methods: This study evaluates multiclass dementia classification of Alzheimer’s disease, frontotemporal dementia, and healthy controls using features derived from low-density temporal EEG electrodes as a proxy for wearable EEG setups. The feature set comprises power-based metrics, including the 1/f spectral slope, and complexity metrics such as Hjorth parameters and multiscale sample entropy. Results: Our results show that multiclass differentiation of dementia, using low-density electrode configurations restricted to temporal regions, can achieve results comparable to a full-scalp configuration. Notably, electrode T5, positioned over the left temporo-posterior region, consistently outperformed other configurations, achieving a subject-level accuracy of 83.3% and an F1 score of 82.4%. Conclusions: These findings highlight the potential of single-site EEG measurement for wearable brain health devices. Full article

This study presents an integrated and reproducible framework for within-tier screening of potential healthcare accessibility in Bangkok. Facilities in three service tiers (primary 294 units, regular 75, referral 29) are analyzed using point-pattern diagnostics, Voronoi geometric partitions, population-weighted allocation from subdistrict controls, and cumulative network travel-time isochrones. Spatial diagnostics indicate clustering among primary care units, a near-random configuration for regular units, and modest dispersion for referral hospitals, summarized by observed-to-expected nearest-neighbor ratios of approximately 0.77, 1.05, and 1.19, respectively. Voronoi partitions translate these distributions into geometric units that enlarge with increasing inter-facility spacing, while population-weighted assignments reveal higher population-per-partition-area burdens in the outer east and southwest. Isochrone maps (5–60 min rings) show central corridors with short travel times and peripheral areas where potential access declines. Interpreted against statutory planning intent, the maps indicate broad consistency of siting with high-intensity zones, alongside residual gaps at residential fringes. Framed as repeatable indicators of access and coverage, the workflow contributes to measuring and monitoring urban health sustainability under universal health coverage and routine planning cycles. The framework yields transparent indicators that support monitoring, priority setting, and incremental adjustments within each tier. Limitations include planar proximity assumptions, uniform areal weighting, single-mode modeled travel times without temporal variation, and the absence of capacity measures, motivating future work on capacity-weighted partitions, minimal dasymetric refinements, and time-dependent multimodal scenarios. Full article

Understanding the seasonal behaviour of sewer failures is essential for infrastructure reliability and sustainable asset management. This study presents a seasonality-centred, data-driven analysis of monthly sewer failures over a 15-year period (2010–2024) in a major city in south-eastern Poland. The assessment is based exclusively on operational failure records, allowing intrinsic temporal regularities to be extracted without the use of external meteorological covariates. Seasonal Decomposition of Time Series by LOESS (STL), Autocorrelation Function (ACF), Seasonal Index (SI) and the Winter–Summer Index (WSI) were applied to quantify periodicity, seasonal amplitude and long-term variability. The results confirm a pronounced annual cycle, with failures peaking around March and reaching minima in September, supported by a strong autocorrelation at a 12-month lag (r ≈ 0.45). The mean WSI value (1.05) indicates a nearly balanced but still winter-sensitive pattern, while annual WSI values ranged from 0.71 to 1.51. The STL seasonal amplitude remained structurally stable at ≈61 failures throughout the study period, while annual values showed a modest but statistically significant increasing tendency. Trend analysis showed no significant monotonic trend in the deseasonalized series (Z ≈ 0.89, p = 0.37), whereas the raw series exhibited a weak but significant upward trend (τ ≈ 0.33, p < 0.001), largely attributable to short-term operational variability rather than to changes in intrinsic failure rate. The study demonstrates that long-term operational data alone are sufficient to capture seasonal and long-term dynamics in sewer failures. The presented framework supports utilities in integrating seasonality diagnostics into preventive maintenance, resource allocation and resilience planning, even in the absence of detailed climatic datasets. Full article

Mine-induced surface subsidence threatens infrastructure and can trigger cascading geohazards, so accurate and computationally efficient monitoring and forecasting are essential for early warning. We integrate Persistent Scatterer InSAR (PS-InSAR) time series with a Bayesian-optimized CNN–LSTM designed for spatiotemporal prediction. The CNN extracts spatial deformation patterns, the LSTM models temporal dependence, and Bayesian optimization selects the architecture, training hyperparameters, and the most informative exogenous drivers. Groundwater level and backfilling intensity are encoded as multichannel inputs. Endpoint anchoring with affine calibration aligns the historical series and the forward projections. PS-InSAR indicates a maximum subsidence rate of 85.6 mm yr⁻¹, and the estimates are corroborated against nearby leveling benchmarks and FLAC^3D simulations. Cross-site comparisons show acceleration followed by deceleration after backfilling and groundwater recovery, which is consistent with geological engineering conditions. A symmetry-aware preprocessing step exploits axial regularities of the deformation field through mirroring augmentation and documents symmetry-breaking hotspots linked to geological heterogeneity. These choices improve generalization to shifted and oscillatory patterns in both the spatial CNN and the temporal LSTM branches. Short-term forecasts from the BO–CNN–LSTM indicate subsequent stabilization with localized rebound, highlighting its practical value for operational planning and risk mitigation. The framework combines automated hyperparameter search with physically consistent objectives, reduces manual tuning, enhances reproducibility and generalizability, and provides a transferable quantitative workflow for forecasting mine-induced deformation in complex goaf systems. Full article