Search Results (2,243)

Attention Deficit Hyperactivity Disorder (ADHD) is a prevalent neurodevelopmental condition commonly assessed through clinical interviews, behavioral observation, and rating scales. Although electroencephalography (EEG) has emerged as a promising complementary tool for ADHD assessment, robust, subject-independent classification remains challenging due to inter-subject variability, limited datasets, and the need for interpretable computational models. This work introduces EEG-TACT, a compact end-to-end deep learning architecture for identifying ADHD subjects from EEG epochs. The proposed model integrates an EEGNet-inspired convolutional embedding, a Transformer encoder operator, and an attention-based pooling mechanism. Together, these components capture local spatiotemporal EEG patterns, contextual temporal dependencies, and task-relevant latent representations. EEG-TACT was evaluated on a publicly available EEG dataset using strict, subject-independent stratified group partitions, ensuring no data leakage across subjects in the training, validation, and test subsets. Learned temporal filter responses, class-conditioned self-attention maps, and latent-space projections provide model interpretability. An ablation study quantifies the contribution of each architectural component. Performance analysis includes evaluation at the fold, subject, and epoch levels, together with statistical significance comparisons against representative state-of-the-art architectures. EEG-TACT achieved competitive performance among the contrasted models, reaching subject-level accuracy of 87.5%, recall of 96.0%, and precision of 82.8%, while requiring only a few thousand trainable parameters. By exhaustively repeating the initialization, the proposed model demonstrated improved labeling reliability and achieved the best average ranking among the evaluated architectures. The reported results therefore support evidence that EEG-TACT provides a compact, stable, and interpretable model for EEG-based ADHD identification under subject-independent evaluation settings. They also motivate further validation on larger, multi-site, and medication-controlled datasets. Full article

Predicting the evolution of microstructure and field quantities under varying processing and loading conditions is a central challenge in computational materials science and metal additive manufacturing (AM). While deep learning (DL) methods offer ultra-fast prediction capabilities post-training, existing models often struggle with poor spatial and temporal extrapolation, high parameter burdens, and an inability to effectively integrate diverse conditioning parameters alongside high-dimensional input fields. To address these bottlenecks, we propose a novel conditional generative adversarial network (CPGAN), which is designed to seamlessly ingest both initial fields and governing condition parameters. The CPGAN framework offers three distinct advantages: (1) it accurately maps the combined effects of initial states and process conditions onto evolved fields; (2) it demonstrates robust extrapolation capabilities across diverse spatial and temporal scales, including the unique ability to natively generate high-resolution rectangular domains; and (3) it achieves superior predictive accuracy and training stability compared to standard convolutional baselines by effectively suppressing spurious artifacts. We validate CPGAN’s performance against rigorous physics-based ground truths across three representative engineering applications: porosity evolution in selective laser sintering (SLS), spatial distribution of 2D von Mises stress fields in solid structures, and the spatiotemporal evolution of grain growth. The results confirm that CPGAN is a highly adaptable and efficient surrogate model, capable of simulating continuous structural and morphological evolutions even when driven by highly non-uniform spatial or temporal kinetics. Full article

Early fault detection in microsatellite thermal control systems (TCS) faces fundamental challenges: high-dimensional redundant telemetry channels, overlapping multi-scale periodicities that obscure anomaly signatures, and severely limited daily data downlink (1–2 passes per day) that restricts the temporal window for diagnosis. Existing data-driven approaches either rely on supervised learning, requiring labeled fault data that are scarce in practice, or employ univariate analysis that fails to capture inter-sensor spatial correlations. To address these limitations, this paper introduces a hybrid framework integrating information-theoretic feature selection and spatiotemporal deep learning. The Generalized Maximum Information Coefficient (GMIC) quantifies nonlinear dependencies between temperature channels for key channel selection, reducing dimensionality by 82% while preserving diagnostic information. A dual-level Seasonal Trend Decomposition (STL) method disentangles orbital-periodic dynamics from diurnal cycles, effectively isolating distinct thermal characteristics at multiple timescales. Each decomposed component is modeled using Convolutional Neural Network–Long Short-Term Memory (CNN-LSTM) networks to capture spatiotemporal dependencies for accurate temperature prediction. An adaptive threshold-based weighted error fusion mechanism enables early fault detection within a single day of telemetry data. Experimental validation on real satellite telemetry data demonstrates that the proposed framework achieves high-precision fault detection across multiple fault types using a minimal set of temperature channels, significantly outperforming existing benchmarks in both prediction accuracy and detection reliability. Full article

Traditional meteorological data spatial interpolation methods often rely on linear or static assumptions, which are inadequate for complex terrain and fail to exploit continuous spatiotemporal variation information. This paper proposes a Spatiotemporal Graph Network with Adaptive Temporal Decay (DG) that integrates a learnable graph convolution module and a temporal attenuation mechanism, enabling accurate precipitation estimation for target stations or regions at consecutive time steps. The method is evaluated using daily precipitation data from nine stations in Longnan City, Gansu Province, China, along with ERA5 (0.25°) and GPCP (0.5°) gridded reanalysis products. In the station-to-station interpolation scenario, DG significantly outperforms ordinary Kriging (OK), reducing the average RMSE from 1.4 mm/day to 1.2 mm/day, with a 28.6% improvement at mountainous stations. The DG model also exhibits superior performance in grid-to-station interpolation, achieving an average RMSE of 1.9 mm/day (OK: 2.5 mm/day). On heavy precipitation days (≥20 mm/day), DG reduces the RMSE nearly by half (11.7 mm/day) compared to OK (23.2 mm/day). A temporal-only LSTM baseline and three ablation variants (spatial-only OSI, temporal-only OTI and dgcn-only OD) are also compared, and DG consistently outperforms them, confirming the essential role of spatiotemporal integration. Additional baselines including IDW and Co-Kriging further validate the superiority of DG. The proposed method offers a promising new approach for high-precision spatiotemporal interpolation of meteorological elements in complex terrain. Full article

This systematic review examined the validity and reliability of wearable inertial sensor systems to quantify spatiotemporal gait parameters in post-stroke adults, a population in which gait asymmetry and altered motor control challenge accurate measurement. Sixteen studies involving 300 participants were included. Spatial parameters gait speed, cadence, and step/stride length showed consistently good-to-excellent agreement with reference systems (ICC 0.85–0.98; 95% LoA ±0.03–0.08 m/s for gait speed, ±4–10 steps/min for cadence, and ±3–8 cm for step/stride length) and high test–retest reliability. Temporal parameters demonstrated greater heterogeneity, with larger errors and lower concordance (ICC 0.40–0.85; LoA ±0.04–0.12 s), particularly for swing time (ICC 0.40–0.70; LoA up to ±0.15 s). Paretic-side measurements showed 10–20% lower concordance and 30–50% wider limits of agreement compared with the non-paretic side, although within-subject reliability remained moderate to high. No consistent influence of sensor number on measurement accuracy was observed. Overall, wearable inertial sensors provide robust estimates of spatial gait parameters, whereas temporal outcomes especially swing time remain limited due to challenges in gait event detection under stroke-related biomechanical alterations. These findings highlight the need for standardized protocols and improved algorithms to enhance comparability across studies and support broader clinical adoption. Full article

As extreme weather events increasingly threaten global food systems, accurately assessing climate risks and predicting regional crop yields remains a critical challenge. Conventional prediction models often rely on direct weather-to-yield relationships, bypassing continuous crop physiological responses and limiting their capacity to capture fine-grained temporal impacts of meteorological anomalies. To address this, we propose a novel two-stage spatiotemporal functional framework that integrates high-resolution daily weather trajectories with satellite-derived indicators, utilizing the Enhanced Vegetation Index (EVI) and Land Surface Water Index (LSWI) to represent canopy structural vigor and hydraulic status, respectively. In the first stage, a Historical Functional Linear Model (HFLM) dynamically maps daily meteorological trajectories (temperature, precipitation, and solar radiation) onto continuous physiological curves under strict temporal causality constraints. This generates bivariate coefficient surfaces that reveal dynamic windows of vulnerability and capture divergent, lagged physiological responses to climate stress. In the second stage, a spatially heterogeneous functional additive model integrates these weather-shaped physiological trajectories alongside raw meteorological dynamics as joint predictors for county-level yields. By extracting functional principal components and modeling flexible non-linear biological responses while accounting for continuous spatial heterogeneity, this dual-channel frameworkcaptures key aspects of both chronic physiological stress and acute meteorological shocks. Validated across a 25-year (2000–2024) U.S. Corn Belt panel, the proposed DC-FAM achieves a mean weighted mean squared prediction error (WMSPE) of 242.33 (bu/acre)² and a median out-of-sample $R_{\mathrm{cv}}^2$ of 0.422, outperforming all benchmarks including a random forest. Attribution of the 2012 flash drought further demonstrates the framework’s capacity to mechanistically trace the complete disaster propagation chain from anomalous spring warming to mid-summer hydraulic failure. The proposed framework provides a transparent, biophysically grounded tool for decoding dynamic climate stress trajectories and disaster propagation chains, offering potential implications for adaptive farm management and precision agricultural insurance. Full article

Parkinson’s disease (PD) is a progressive neurodegenerative disorder characterized by motor control, balance, and gait impairments that significantly elevate fall risk. Traditional gait analysis focuses on spatiotemporal parameters, while gait variability, asymmetry, and balance measures offer more sensitive indicators of PD-related motor deficits. Machine learning studies using wearable gait data frequently report high classification accuracy but lack biomechanical interpretability and methodological rigor. Using the PhysioNet Gait in Parkinson’s Disease database, 93 individuals with PD and 72 healthy controls were analyzed during level-ground walking. Key biomechanical differences were identified: stride time coefficient of variation was significantly higher in PD bilaterally (left p = 0.001; right p = 0.003); swing-phase time was significantly reduced in both limbs (left p = 0.003; right p = 0.001); anterior–posterior center of pressure (COP) variability was significantly lower in PD for both limbs (p < 0.001); and COP path symmetry index was the most prominent asymmetry marker, significantly elevated in PD relative to controls (p = 0.003). A machine-learning analysis pipeline identified HistGradientBoosting as the best-performing classifier (AUC = 0.992; accuracy = 97.6%), but leave-one-study-out evaluation exposed substantial cross-protocol heterogeneity (AUC: 0.500–1.000), indicating that the model relied partly on dataset-specific patterns and may not generalize to independent acquisition protocols. Shapley Additive Explanations (SHAP) analysis showed classification was driven by a multimodal combination of clinical severity measures and biomechanical gait features rather than wearable metrics alone. A pre-specified gait-only sensitivity analysis that excluded clinical severity variables (UPDRS, UPDRSM, Hoehn and Yahr) confirmed that biomechanical features alone retained moderate, but substantially reduced, discriminative ability (gait-only holdout AUC = 0.844), supporting the interpretation that the headline performance reflects multimodal clinical separation rather than a stand-alone wearable-gait biomarker. These findings indicate that Parkinsonian gait impairment is characterized by timing instability and constrained forward COP progression. The combination of biomechanical analysis with interpretable predictive modeling represents a structured analysis pipeline for gait-based PD assessment; however, external validation in independent cohorts and prospective testing across acquisition protocols are required before such a pipeline can be deployed as a clinically generalizable digital biomarker. Full article

A quantitative analysis of larch-dominated Siberian forest regions was conducted to evaluate wildfire characteristics in relation to Fire Radiative Power (FRP), long-term meteorological dynamics, and FRP range ratios. The results were validated against empirical stand mortality data spanning the period 2001–2024, obtained from the Global Forest Change dataset. Spatiotemporal burn characteristics were derived from the standard MODIS burned area product, while FRP data were extracted from the corresponding thermal anomalies product. Increasing trends in extreme FRP values were observed (4.5–17.9% of annual fire pixels), indicating that high-intensity fires progressively drive tree stand mortality statistics (R² = 0.58, p < 0.01). Seasonal anomalies of the Duff Moisture Code (DMC), surface soil and litter moisture, and the Standardized Precipitation Evapotranspiration Index (SPEI) were the primary predictors of both wildfire intensity and tree cover mortality. Spatiotemporal analysis of FRP and tree cover mortality revealed that the most pronounced positive trends were concentrated in the central and northeastern forest regions of Siberia, which also exhibit high mean FRP values. These regions also experienced intensifying drought, as evidenced by the analysis of meteorological data. Consequently, under projected regional climate change, an escalating prevalence of high-intensity forest fires is anticipated to induce severe, potentially irreversible degradation of these forest stands and ecosystems. Full article

Safety signs in innovative manufacturing environments fail to match dynamic risks due to the separation of perception, semantics, and decision-making. Existing methods lack closed-loop integration of IoT sensor streams, knowledge graph reasoning, and adaptive signage control. This paper proposes a framework that fuses dynamic graph attention networks with hierarchical temporal knowledge graphs and reinforcement learning optimization. The framework extracts spatiotemporal dependencies from multi-source sensors, traces risk propagation paths on an industrial knowledge graph, and generates adaptive signage actions. Experimental results demonstrate that the proposed method achieves 96.7% risk identification accuracy, a 91.3% risk propagation F1 score, a 94.2 semantic matching score, and 43.65 milliseconds response latency. Real-world validation on an aerospace workshop confirms the method’s effectiveness. This work provides a closed-loop solution from physical perception to adaptive semantic expression for intelligent manufacturing safety. Full article

To address the key challenges in GB-RAR monitoring of super-tall buildings—namely, complex noise interference (transient pulse disturbances coupled with high-frequency random fluctuations), the difficulty of distinguishing normal wind-induced vibrations from hazardous deformations, and the propensity of single-algorithm prediction models to converge prematurely—this paper proposes an integrated monitoring data processing workflow that combines status assessment and deformation early warning, using Wuhan Greenland Center as a case study. A denoising method combining Median Absolute Deviation outlier removal and Savitzky–Golay filtering was designed for preprocessing, quantitatively validated through signal-to-noise ratio analysis. Based on filtered data, a spatio-temporal trajectory model was established to visualize and evaluate building movement. Furthermore, a GB-RAR-oriented residual-driven warning framework was developed by coupling a PSO-GA-BP deformation prediction model with adaptive sliding-window thresholding and finite-state warning decisions. Simulation results demonstrate that the PSO-GA-BP model outperforms other neural network models in prediction accuracy, and the derived early warning system exhibits strong feasibility and sensitivity. This workflow proves suitable for GB-RAR deformation monitoring of super-tall buildings, offering valuable reference for future research. Full article

Urban planners need scalable ways to monitor pedestrian conditions across heterogeneous cities, but conventional Level-of-Service (LOS) methods are often locally calibrated and difficult to transfer. This study proposes a city-adaptive framework for pedestrian LOS mapping using spatio-temporal graph models and few-shot transfer learning. Pedestrian count data from Melbourne, Dublin, and Zurich were converted into six ordinal LOS classes using city-specific percentile thresholds computed from the training data, yielding a relative congestion measure rather than an absolute cross-city standard. We developed a spatio-temporal graph transformer with an ordinal prediction head and evaluated it under in-domain, zero-shot, few-shot, and domain-adaptive settings. The results show strong in-domain performance in Melbourne (accuracy 79.7%; Acc ± 1 99.1%) and effective adaptation to the city-adaptive ordinal classification task. Few-shot fine-tuning with only 5% labeled target city data recovered 95–99% of in-domain performance, suggesting that small amounts of local supervision can substantially reduce calibration requirements in data-scarce environments. KernelSHAP analysis indicates that short-term temporal lag features dominate predictions across cities, whereas spatial and contextual features vary more strongly with local urban structure. The findings suggest that few-shot transfer learning can support pedestrian LOS estimation in cities with limited labeled data; however, the proposed LOS formulation should be interpreted as a city-specific relative indicator rather than an absolute measure of pedestrian comfort, crowding, or service quality. While the framework was evaluated across three cities, additional validation in diverse urban contexts and against perceptual measures of pedestrian experience remains necessary. Overall, the study contributes a city-adaptive framework for transferable relative LOS prediction rather than a universal cross-city LOS standard. Full article

Rapid detection of foodborne pathogenic and spoilage microorganisms is critical for ensuring food safety and quality in liquid matrices. While Raman tweezers spectroscopy (RTS) enables label-free single-cell analysis, its application in high-throughput inline inspection faces a fundamental bottleneck: high flow rates required for efficiency induce severe motion blur and low signal-to-noise ratios (SNR), which blind automated control systems and destabilize optical trapping. To overcome this, we present a Spatiotemporal Video-Enhanced Raman Tweezers (SVERT) system integrating a deceleration-optimized microfluidic chip with a deep learning-based visual feedback loop. We propose a Local–Global Unified Denoising Network (LGU-Net) tailored to recover high-fidelity bacterial structures from low-SNR video streams, achieving a deterministic processing latency of ~0.49 ms. Experimental results demonstrate that SVERT improves the optical trapping success rate from 21.27% ± 2% to 91.47% ± 1.8% compared to raw video input, enabling a four-fold increase in spectral acquisition efficiency. Leveraging the acquired high-quality dataset, we achieved a classification accuracy of 96.74% across four bacterial species of relevance to food safety and quality. Crucially, we validated the system’s practical robustness by successfully isolating and tracking trace E. coli in an unpurified commercial beverage. This capability to effectively mitigate natural background interference demonstrates the system’s promising potential to be expanded for broader applications in liquid food safety screening. Full article

Snow cover fraction (SCF) records derived from optical satellite sensors such as AVHRR are systematically interrupted by cloud contamination and polar night conditions, leaving large spatiotemporal data gaps that limit their utility for climate and hydrological applications. This study presents a U-Net–based deep learning framework for reconstructing missing SCF values in Scandinavia over a 15-year period (2000–2014), using the ESA CCI L3C SCFV AVHRR v4.0 product as both partial input and training target. The model integrates physically meaningful auxiliary predictors (snow water equivalent (SWE), near-surface air temperature, elevation, and land cover) harmonized to a common 0.05° grid, enabling reconstruction in the complete absence of concurrent optical observations. Trained on a single year with extensive synthetic masking (91.5% of valid SCF pixels withheld), the U-Net achieves an R² of 0.9342 and RMSE of 0.1127, outperforming spatial interpolation, a SWE-based physical baseline, and pixel-wise machine learning baselines. Feature importance analysis confirms that SWE and temperature dominate predictive skill, with the observed SCF input contributing negligibly. Independent validation against ground station observations yields 86.7% binary classification accuracy and an F1 score of 88.0%, comparable to the 87.8% accuracy of the original satellite retrievals, demonstrating the viability of deep learning–based gap-filling for producing continuous SCF records under cloud cover and polar night. Full article

Recent advancements in Vision-Language Models (VLMs) have enabled robotic systems to leverage model-based understanding and reasoning over visual and linguistic inputs, offering a promising approach for interpreting user intent in human–robot interaction (HRI). In particular, deictic expressions commonly used in object handovers, such as “take this” and “give me that”, cannot be fully interpreted through language alone and require a comprehensive understanding of the speaker’s perspective and the environment. This study proposes a prompt-driven vision-language framework for deictic interpretation in human–robot handover. The system integrates a pre-trained VLM with a hierarchical prompt that decomposes reasoning into intent classification, spatio-temporal grounding, and output self-validation, enabling accurate identification of target objects and goal locations without model fine-tuning. Experimental results demonstrate 100% command interpretation accuracy across multiple interaction scenarios, including pick-and-place tasks, robot-to-human and human-to-robot handovers, and temporal deictic commands. Notably, the system operates under a prompt–command language mismatch, accurately interpreting Korean commands while being guided by English-based prompts. Analysis across progressive system configurations further demonstrates that structured prompting plays a critical role in reasoning performance. These results highlight the effectiveness of a prompt-driven approach for deictic interpretation and spatio-temporal grounding, providing a practical training-free framework for HRI. Full article

Understanding ecosystem carbon processes relies heavily on the reliable assessment of gross primary productivity (GPP) yet remains challenging in the Inner Mongolia grasslands due to data scarcity and high uncertainty among existing products. We developed a ConvTransformer-based framework that exploits complementary information from satellite observations and meteorological datasets to enhance the representation of complex spatiotemporal dependencies in grassland ecosystems. Grounded in leave-one-site-out cross-validation across six eddy covariance sites, the model achieved average performance metrics of R² = 0.59, RMSE = 1.40 g C m⁻² d⁻¹, Bias = −0.31 g C m⁻² d⁻¹, and KGE = 0.46, outperforming traditional machine learning models (RF, GBRT, and SVR) as well as the light use efficiency model (EC-LUE) in both accuracy and robustness. Using this framework, we generated a daily GPP dataset at spatial granularity of 1 km for the Inner Mongolia grasslands from 2003 to 2018. The results reveal a clear spatial gradient, with GPP decreasing from southeast to northwest. Comparisons with established products, including FLUXCOM, BESS V2, and PML V2, show strong spatial consistency and reduced discrepancies, supporting the reliability of the estimates. Overall, the proposed framework provides an effective approach for characterizing regional carbon dynamics and supports long-term ecological monitoring in semi-arid regions. Full article