Search Results (21)

Existing origin-destination (OD) forecasting models struggle to jointly capture local topology and global flow patterns in urban mobility. Therefore, we developed a multi-view spatio-temporal network (MVSTN), a novel dual-branch spatio-temporal model that integrates a graph convolutional network-based local spatial relationship module for static and dynamic graph modeling, and a self-attention-based global similarity module for learning latent mobility similarities. MVSTN achieves superior performance on multiple real-world datasets, particularly in long-term forecasts, highlighting its practical value for intelligent transportation systems. Full article

The rapid development of China’s high-speed railways (HSRs) and the implementation of revenue management policies have promoted the marketization of railway passenger transport, which is mainly reflected in the gradual transformation from a seller’s market dominated by operating companies to a buyer’s market dominated by passenger demand. Passenger travel needs are becoming increasingly diverse. In order to improve the quality of HSR services and attract more passengers, this paper starts from passenger satisfaction and considers the heterogeneity of travel preferences of passengers with different travel distances. Based on the passenger travel data of the Nanning-Guangzhou (NG) HSR line, the K-means clustering method is used to classify passengers into three categories: short-distance, medium-distance, and long-distance travel. A structural equation modeling–multinomial logit (SEM-MNL) model integrating both explicit and latent variables was constructed to analyze passenger travel origin-destination (OD) choices. Stata software was used to estimate passenger preferences for perceived satisfaction functions across different travel distances. Finally, considering constraints such as load factor, departure capacity, and spatiotemporal passenger flow demand, a line planning optimization model was constructed with the goal of minimizing train operating costs and maximizing passenger travel satisfaction. An improved subtraction optimizer algorithm was designed for the solution. Using the NG Line as a case study, the proposed method achieved a reduction in train operating costs while enhancing overall passenger satisfaction. Full article

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

Background: Glioblastoma (GBM) is among the most aggressive and morphologically heterogeneous brain tumors. Beyond static imaging biomarkers, its structural organization can be viewed as a nonlinear dynamical system. Characterizing morphodynamic attractors within such a system may reveal latent stability patterns of morphological change and potential indicators of morphodynamic organization. Methods: We analyzed 494 subjects from the multi-institutional BraTS 2020 dataset using a fully automated computational pipeline. Each multimodal MRI volume was encoded into a 16-dimensional latent space using a 3D convolutional autoencoder. Synthetic morphological trajectories, generated through bidirectional growth–shrinkage transformations of tumor masks, enabled training of a contraction-regularized Neural Ordinary Differential Equation (Neural ODE) to model continuous-time latent morphodynamics. Morphological complexity was quantified using fractal dimension (DF), and local dynamical stability was measured via a Lyapunov-like exponent (λ). Robustness analyses assessed the stability of DF–λ regimes under multi-scale perturbations, synthetic-order reversal (directionality; sign-aware comparison) and stochastic noise, including cross-generator generalization against a time-shuffled negative control. Results: The DF–λ morphodynamic phase map revealed three characteristic regimes: (1) stable morphodynamics (λ < 0), associated with compact, smoother boundaries; (2) metastable dynamics (λ ≈ 0), reflecting weakly stable or transitional behavior; and (3) unstable or chaotic dynamics (λ > 0), associated with divergent latent trajectories. Latent-space flow fields exhibited contraction-induced attractor-like basins and smoothly diverging directions. Kernel-density estimation of DF–λ distributions revealed a prominent population cluster within the metastable regime, characterized by moderate-to-high geometric irregularity (DF ≈ 1.85–2.00) and near-neutral dynamical stability (λ ≈ −0.02 to +0.01). Exploratory clinical overlays showed that fractal dimension exhibited a modest negative association with survival, whereas λ did not correlate with clinical outcome, suggesting that the two descriptors capture complementary and clinically distinct aspects of tumor morphology. Conclusions: Glioblastoma morphology can be represented as a continuous dynamical process within a learned latent manifold. Combining Neural ODE–based dynamics, fractal morphometry, and Lyapunov stability provides a principled framework for dynamic radiomics, offering interpretable morphodynamic descriptors that bridge fractal geometry, nonlinear dynamics, and deep learning. Because BraTS is cross-sectional and the synthetic step index does not represent biological time, any clinical interpretation is hypothesis-generating; validation in longitudinal and covariate-rich cohorts is required before prognostic or treatment-monitoring use. The resulting DF–λ morphodynamic map provides a hypothesis-generating morphodynamic representation that should be evaluated in covariate-rich and longitudinal cohorts before any prognostic or treatment-monitoring use. Full article

Fault diagnosis of rolling bearings is crucial for ensuring the maintenance and reliability of industrial equipment. Existing cross-domain diagnostic methods often struggle to maintain performance under evolving mechanical and environmental conditions. This limits their robustness in long-term real-world deployments. To address this, we propose a novel online learning framework that continuously adapts to distribution shifts using streaming vibration data. Specifically, the proposed framework consists of three core modules: the Feature Extraction Module that encodes raw vibration signals into low-dimensional latent representations; the Fault Sample Generation Module (comprising a generator and discriminator network) that synthesizes diverse fault samples conditioned on normal-condition data; and the Classification Module that incrementally adapts by leveraging both synthesized fault samples and streaming normal-condition signals. We also introduce a domain-shift indicator ScoreODS to dynamically control the transition between prediction and fine-tuning phases during deployment. Extensive experiments on both public and private datasets demonstrate that the proposed method outperforms the most competitive method, achieving about a 4% improvement in diagnostic accuracy and enhanced robustness for long-term fault diagnosis under distribution shifts. Full article

Accurate path travel time prediction is often hindered by sparse and heterogeneous traffic data. This paper proposes FusionODE-TT, a novel model designed to address these challenges by modeling traffic as a continuous-time process. The model features a Recurrent Neural Network encoder that processes multi-source time-series data to initialize a latent state vector, which then evolves over the prediction horizon using a Neural Ordinary Differential Equation (NODE). The core innovation is a guided fusion mechanism that leverages sparse but high-fidelity Automatic Vehicle Identification (AVI) data to apply strong, event-based corrections to the model’s continuous latent state, mitigating error accumulation in the prediction process. Experiments were conducted on a real-world dataset comprising AVI, GPS, and point sensor data from a major urban expressway. The experimental results demonstrate that the proposed model achieves superior accuracy, outperforming a suite of baseline models in terms of prediction accuracy and robustness. Furthermore, a comprehensive ablation study was performed to validate the efficacy of our design. The study quantitatively confirms that both the continuous-time dynamics modeled by the NODE and the guided fusion mechanism are essential components, each providing a significant and independent contribution to the model’s overall performance. Full article

Solid–liquid phase-change materials (PCMs) have attracted considerable attention in heat energy storage due to their appropriate phase-transition temperatures and high thermal storage density. The primary issues that need to be addressed in the wide application of traditional PCMs are easy leakage during solid–liquid phase transitions, low thermal conductivity, and poor energy conversion function. The heat transfer properties of PCMs can be improved by compounding with carbon materials. Carbon nanotubes (CNTs) are widely used in PCMs for heat storage because of their high thermal conductivity, strong electrical conductivity, and high chemical stability. This study investigates the thermal properties of 1-octadecanol (OD) modified with different diameters and amounts of CNTs using the melt blending method and the ultrasonic dispersion method. The aim is to enhance thermal conductivity while minimizing latent heat loss. The physical phase, microstructure, phase-change temperature, phase-transition enthalpy, thermal stability, and thermal conductivity of the OD/CNTs CPCMs were systematically studied using XRD, FTIR, SEM, DSC, and Hot Disk. Moreover, the heat charging and releasing performance of the OD/CNTs CPCMs was investigated through heat charging and releasing experiments, and the relationship among the composition–structure–performance of the CPCMs was established. Full article

Origin–destination (OD) flows are essential for urban studies, yet their acquisition is often hampered by high costs and privacy constraints. Prevailing inference methodologies inadequately address latent spatial dependencies between non-contiguous and distant areas, which are useful for understanding modern transportation systems with expanding regional interactions. To address these challenges, this paper propose a hybrid learning model with the Global–Local Graph Attention Network and XGBoost (GLGAT-XG) to infer OD flows from both global and local geographic contextual information. First, we represent the study area as an undirected weighted graph. Second, we design the GLGAT to encode spatial correlation and urban feature information into the embeddings within a multitask setup. Specifically, the GLGAT employs a graph transformer to capture global spatial correlations and a graph attention network to extract local spatial correlations followed by weighted fusion to ensure validity. Finally, OD flow inference is performed by XGBoost based on the GLGAT-generated embeddings. The experimental results of multiple real-world datasets demonstrate an 8% improvement in RMSE, 7% in MAE, and 10% in CPC over baselines. Additionally, we produce a multi-scale OD dataset in Xian, China, to further reveal spatial-scale effects. This research builds on existing OD flow inference methodologies and offers significant practical implications for urban planning and sustainable development. Full article

The quality of the processed products in CNC machining centers is a critical factor in manufacturing equipment. The anomaly detection and predictive maintenance functions are essential for improving efficiency and reducing time and costs. This study aims to strengthen service competitiveness by reducing quality assurance costs and implementing AI-based predictive maintenance services, as well as establishing a predictive maintenance system for CNC manufacturing equipment. The proposed system integrates preventive maintenance, time-based maintenance, and condition-based maintenance strategies. Using continuous learning based on long short-term memory (LSTM), the system enables anomaly detection, failure prediction, cause analysis, root cause identification, remaining useful life (RUL) prediction, and optimal maintenance timing decisions. In addition, this study focuses on roller-cutting devices that are essential in packaging processes, such as food, pharmaceutical, and cosmetic production. When rolling pins are machining with CNC equipment, a sensor system is installed to collect acoustic data, analyze failure patterns, and apply RUL prediction algorithms. The AI-based predictive maintenance system developed ensures the reliability and operational efficiency of CNC equipment, while also laying the foundation for a smart factory monitoring platform, thus enhancing competitiveness in intelligent manufacturing environments. Full article

Background: Research is limited regarding the relationship between adolescent substance use and polysubstance use (SU/PSU) as well as their outcomes later in adolescence, while accounting for early risk factors. This study explored substance-related and psychosocial outcomes at age 17 associated with SU/PSU developmental trajectories in a population-representative cohort from Quebec, Canada (N = 1593; 48.4% male), while controlling for preadolescent individual, familial, and social risk factors. SU/PSU included concurrent use of alcohol (AL), cannabis (CA), and other illicit drugs (ODs). Methods: Self-reported substance use data were collected at ages 12, 13, 15, and 17. Latent growth modeling identified five trajectories: Non-Users (12.8%) and four SU/PSU classes (5.8–37.5%) with varying severity based on onset, frequency, and substance type. Multinomial regression, using non-users as the reference group, assessed trajectory associations with age-17 outcomes. Individual, familial, and social risk factors assessed at ages 10–12 served as control variables. Results: Adolescents in high-risk SU/PSU classes showed the most negative substance-related and psychosocial outcomes compared to non-users and lower-risk SU/PSU classes. Lower-risk SU/PSU classes showed higher maladjustment than non-users. Conclusions: The findings highlight a dose–response relationship between SU/PSU trajectories and late-adolescent outcomes, independent of preadolescent risk factors. Results emphasize the importance of longitudinal studies that incorporate multiple substances to better capture the complexity of teenagers’ involvement in substance use throughout adolescence. Full article

With the development of transportation networks, countless trajectory data are accumulated, and understanding human mobility from traffic data could be helpful for smart cities, urban computing, and urban planning. Extracting valuable insights from traffic data, such as taxi trajectories, can significantly improve residents’ daily lives. There are many studies on spatiotemporal data mining. As we know, arrival prediction or regional function detection encompasses important tasks for traffic management and urban planning. However, trajectory data are often mutilated because of personal privacy and hardware limitations, i.e., we usually can only obtain partial trajectory information. In this paper, we develop an embedding method to predict the next arrival using the origin–destination (O-D) pair trajectory information and point of interest (POI) data. Moreover, the embedding information contains region latent features; thus, we also detect the regional function in this paper. Finally, we conduct a comprehensive experimental study on a real-world trajectory dataset. The experimental results demonstrate the benefit of predicting arrivals, and the embedding vectors can detect the regional function in a city. Full article

Objectives: The aim of this study is to validate a uniform method for measuring perineal descent which can be used for different imaging methods, to establish cut-off values for this measurement, and to assess diagnostic test accuracy (DTA) of imaging techniques using these cut-off values. Secondly, the study aims to correlate perineal descent to symptoms, signs and imaging findings in women with obstructed defaecation syndrome (ODS) to assess its clinical relevance. Methods: Cross-sectional study of 131 women with symptoms of ODS. Symptoms and signs were assessed using validated methods. These women underwent evacuation proctography (EP), magnetic resonance imaging (MRI), transperineal ultrasound (TPUS) and endovaginal ultrasound (EVUS). Perineal descent was measured on EP and MRI as the position of anorectal junction (ARJ) with respect to the pubococcygeal line (PCL) at rest (i.e., static descent) and during evacuation (i.e., descent at Valsalva). Dynamic perineal descent was measured on all four imaging techniques as the difference between the position of the ARJ at rest and Valsalva. DTA of dynamic perineal descent was estimated using Latent Class Analysis in the absence of a reference standard. Results: Interobserver agreement of dynamic perineal descent measurements was good for MRI and EVUS (ICC 0.86 and 0.85) and moderate for EP and TPUS (ICC 0.61 and 0.59). The systematic differences in measurements between imaging techniques show the need for individual cut-off values. New established cut-off values for dynamic descent are for EP 20 mm, MRI 35 mm, TPUS 15 mm and EVUS 15 mm. Sensitivity was moderate for EP (0.78) and MRI (0.74), fair for TPUS (0.65) and poor for EVUS (0.58). Specificity was similar for all imaging techniques (0.73–0.77). Static perineal descent correlated with symptoms of pelvic organ prolapse (POP) (r = 0.19), prolapse of all three compartments (r = 0.19–0.36), presence of levator ani muscle avulsion (p = 0.01) and increased hiatal area (r = 0.51). Dynamic perineal descent correlated with excessive straining (r = 0.24) and use of laxatives (r = 0.24). Classic symptoms of ODS (incomplete evacuation and digitation) did not correlate with perineal descent measurements. Static and dynamic perineal descent were associated with presence of rectocele, enterocele, intussusception, and absence of anismus. Conclusions: Dynamic perineal descent is a reliable measurement that can be applied to different imaging techniques to allow standardisation. Static descent is more often present in women with POP and dynamic descent is more often present in women with constipation. Perineal descent does not correlate with typical symptoms of ODS. Specificity of TPUS and EVUS is comparable to EP and MRI, hence ultrasound could be used for the initial assessment of pelvic floor dysfunction. Full article

This study investigated the application of nanophase change material emulsions (NPCMEs) for thermal management in high-capacity ternary lithium-ion batteries. We formulated an NPCME of n-octadecane (n-OD) and n-eicosane (n-E) with a mass fraction of 10%, whose phase change temperatures are 25.5 °C and 32.5 °C, respectively, with specific heat capacities 2.1 and 2.4 times greater than water. Experiments were conducted to evaluate the thermal control performance and latent heat utilization efficiency of these NPCMEs. The NPCMEs with an n-OD mass fraction of 10% (NPCME-n-OD), particularly reduced the battery pack’s maximum temperature and temperature difference to 41.6 °C and 3.72 °C under a 2 C discharge rate, lower than the water-cooled group by 1.3 °C and 0.3 °C. This suggests that nano emulsions with phase change temperatures close to ambient temperatures exhibit superior cooling performance. Increased flow rates from 50 mL/min to 75 mL/min significantly lowered temperatures, resulting in temperature reductions of 2.73 °C for the NPCME-n-OD group and 3.37 °C for the NPCME-n-E group. However, the latent heat utilization efficiency of the nano emulsions decreased, leading to increased system energy consumption. Also, it was found that the inlet temperature of the NPCMEs was very important for good thermal management. The right inlet temperatures make it easier to use phase change latent heat, while excessively high temperatures may make thermal management less effective. Full article

Natural killer (NK) cells are innate-like lymphocytes that belong to the family of type-1 innate lymphoid cells and rapidly respond to virus-infected and tumor cells. In this study, we have combined scRNA-seq data and bulk RNA-seq data to define the phenotypic and molecular characteristics of peripheral blood NK cells. While the role of NK cells in immune surveillance against virus infections and tumors has been well established, their contribution to protective responses to other intracellular microorganisms, such as Mycobacterium tuberculosis (Mtb), is still poorly understood. In this study, we have combined scRNA-seq data and bulk RNA-seq data to illuminate the molecular characteristics of circulating NK cells in patients with active tuberculosis (TB) disease and subjects with latent Mtb infection (LTBI) and compared these characteristics with those of healthy donors (HDs) and patients with non-TB other pulmonary infectious diseases (ODs). We show here that the NK cell cluster was significantly increased in LTBI subjects, as compared to patients with active TB or other non-TB pulmonary diseases and HD, and this was mostly attributable to the expansion of an NK cell population expressing KLRC2, CD52, CCL5 and HLA-DRB1, which most likely corresponds to memory-like NK2.1 cells. These data were validated by flow cytometry analysis in a small cohort of samples, showing that LTBI subjects have a significant expansion of NK cells characterized by the prevalence of memory-like CD52⁺ NKG2C⁺ NK cells. Altogether, our results provide some new information on the role of NK cells in protective immune responses to Mtb. Full article

The rapid development of industry has emphasized the importance of phase change materials (PCMs) with a high latent-heat storage capacity and good thermal stability in promoting sustainable energy solutions. However, the inherent low thermal conductivity and poor thermal-cycling stability of PCMs limit their application. In this study, we constructed three-dimensional (3D) hybrid graphene aerogels (GBA) based on synergistic assembly and cross-linking between GO and modified hexagonal boron nitride (h-BN). Highly thermally conductive GBA was utilized as the supporting optimal matrix for encapsulating OD, and further implied that composite matrix n-octadecane (OD)/GBA composite PCMs were further prepared by encapsulating OD within the GBA structure. Due to the highly thermally conductive network of GBA, the latent heat of the composite PCMs improved to 208.3 J/g, with negligible changes after 100 thermal cycles. In addition, the thermal conductivity of the composite PCMs was significantly enhanced to 1.444 W/(m·k), increasing by 738% compared to OD. These results sufficiently confirmed that the novel GBA with a well-defined porous structure served as PCMs with excellent comprehensive performance offer great potential for thermal energy storage applications. Full article