Search Results (768)

To address the limitations of existing vehicle trajectory prediction methods, including insufficient modeling of dynamic inter-vehicle interactions, weak temporal continuity of complex driving intentions such as lane-changing, and high uncertainty in future trajectory prediction, this paper proposes a vehicle trajectory prediction method that integrates Dynamic Graph Neural Networks (DyGNN) with Transformer. Specifically, a time-varying interaction graph is constructed to model the dynamically evolving topological interaction relationships among vehicles, while a Transformer encoder is employed to extract temporal dependency features from historical trajectory sequences. In this way, the joint representation of spatial interaction information and temporal evolution information is achieved, thereby improving the accuracy and continuity of driving intention recognition in complex traffic scenarios. On this basis, driving intention is further introduced into the trajectory prediction process as a prior constraint, which effectively reduces the uncertainty of future trajectory prediction. Comparative experiments on real-world traffic datasets demonstrate that the proposed method maintains low prediction errors across different prediction horizons, showing good effectiveness and robustness. Full article

Driving behavior primitives serve as fundamental building blocks for modeling and semantically interpreting time-series driving behavior. Extracting behavior primitives is challenging due to the high dimensionality and complex interdependencies among behavioral variables, as well as the rich temporal dynamics of real-world driving maneuvers. This paper proposes an unsupervised two-stage framework that optimizes time-series segmentation and segment clustering to yield interpretable and context-aware behavior primitives. First, a Hierarchical Bayesian Model-based Agglomerative Sequence Segmentation (H-BMASS) method is introduced that decouples longitudinal and lateral driving behaviors and performs hierarchical segmentation. This design mitigates under-segmentation by ensuring that change points reflect genuine behavioral transitions. Second, to cluster driving segments of varying durations into a finite set of primitive types, an Integrating Numerical and Trend Discretization Latent Dirichlet Allocation (INT-LDA) model is developed. The model combines variables’ temporal trend discretization with numerical discretization to create symbolic representations of driving data, thereby preserving the essential time dependency of driving behavior and improving segment clustering accuracy. Evaluated on naturalistic driving data collected from a high-fidelity simulator, the proposed framework identifies five distinct behavior primitives with clear physical interpretations. The resulting primitives provide a compact, semantically rich representation of driving behavior, facilitating driver modeling, decision prediction, and scenario-based testing for autonomous vehicles. Full article

The transition to autonomous driving is creating mixed traffic environments in which human-driven vehicles, partially automated vehicles, and autonomous vehicles must continuously interact, adapt, and respond to one another. This paper presents a comprehensive review of driver behavior in mixed traffic with autonomous vehicles, with emphasis on the sociotechnical nature of human–machine coexistence. The review synthesizes recent evidence on behavioral adaptation in car-following and tactical decision-making, trust calibration, situational awareness, takeover performance, internal and external human–machine interface design, surrogate safety metrics, vehicle-to-vehicle communication, operational design domains, and data-driven scenario generation. The literature shows that drivers do not respond to autonomous vehicles uniformly. Instead, behavior varies by driving style, perceived predictability of the automated vehicle, interface transparency, and traffic context. The review also emphasizes that these interaction patterns are context-dependent and may differ substantially across regions, particularly in dense mixed traffic environments. While some adaptations can improve stability and safety, others can encourage opportunistic maneuvers, overtrust, confusion, or degraded takeover quality. The review also highlights that crash data alone are insufficient to assess safety in mixed traffic, and that near-miss analysis, surrogate conflict metrics, and scenario-based evaluation are essential for understanding safety-critical interactions. Across the literature, a central inference emerges: adaptation to autonomous vehicles is real, but it is not automatically stabilizing. Safe deployment therefore depends not only on technical vehicle performance but also on behavioral legibility, transparent communication, calibrated trust, and robust evaluation under diverse real-world conditions. The paper concludes by identifying major research gaps, including the lack of longitudinal studies, incomplete standardization of surrogate metrics, limited understanding of vehicle conspicuity effects, and the need for integrated frameworks that jointly assess driver behavior, system design, and scenario-based safety. Full article

Background: Emergency department evaluation of suspected urolithiasis increasingly relies on non-contrast CT, yet not all patients require imaging. Existing clinical prediction rules help stratify stone probability, but by converting continuous measurements into fixed binary indicators, they offer little insight into why a particular patient is at risk or how much uncertainty remains after each testing stage—questions that bear directly on individualized diagnostic decisions. Methods: We retrospectively analyzed 1000 ED patients with suspected urolithiasis who underwent non-contrast CT (stone prevalence 85.0%). A gradient boosting classifier was trained on 17 continuous clinical and laboratory features and compared against binary-thresholded counterparts and an established scoring system; the 17-feature model achieved AUC 0.771 (95% CI 0.726–0.813) versus 0.723 (95% CI 0.675–0.771) for the reference score on this cohort (DeLong p = 0.001). Individual predictions were explained using an interventional Shapley value approach, and a Shannon entropy-based framework was applied to quantify the marginal diagnostic contribution of each sequential testing stage. Results: Held-out permutation importance identified red blood cell count on microscopy, age, pain duration, and prior stone history as the most influential predictors. Several features showed non-linear contributions that diverged from conventional binary thresholds: creatinine effect crossed zero near 0.90 mg/dL and pain duration peaked between 2 and 5 h. C-reactive protein, absent from existing scoring systems, emerged as a meaningful negative predictor. Sequential entropy analysis showed that dipstick urinalysis provided the largest marginal information gain among non-history stages (6.1% of prior entropy), while physical examination contributed 2.3%. A prevalence sensitivity analysis projected that the framework’s threshold behavior would differ substantially in lower-prevalence populations, underscoring that the cohort-specific cut-points are not portable decision rules. We therefore position the framework as a reasoning aid that complements clinical judgment and imaging, not as a stand-alone triage tool. Conclusions: Explainable machine learning can address questions that aggregate discrimination metrics cannot: which features drive risk for a given patient, how those effects behave across the continuous measurement range, and how much diagnostic uncertainty each testing stage resolves. The Shapley-based explanations and entropy framework developed here offer a structured approach to individualized diagnostic reasoning in the ED evaluation of suspected urolithiasis, functioning as an interpretive adjunct to, rather than a replacement for, existing clinical tools and CT imaging. Full article

The requirement of sustainable mobility and a clean environment has accelerated the development and adoption of electric vehicles (EVs) and hybrid electric vehicles (HEVs) as an alternative, practical and promising solution against conventional vehicles globally. Such alternative energy vehicles not only provide a critical solution to mitigate fossil fuel dependency and reduce greenhouse gas emissions, but also contribute to producing an energy-efficient transportation system. However, the operational performance, efficiency, and cost-effectiveness of EVs and HEVs are hugely dependent on their powertrain architectures, selection of traction motors and associated control techniques. This paper systematically compares major hybrid architectures: series, parallel, and series–parallel, plug-in, as well as battery and fuel cell electric vehicle platforms, highlighting trade-offs in component sizing, cost, and system integration complexity. The paper critically analyses traction motor technologies with respect to torque–speed characteristics, efficiency behavior, material constraints, and power density. A detailed comparative assessment of traction motor technologies is presented. Furthermore, classical and advanced motor control strategies, including field-oriented control (FOC), direct torque control (DTC), model predictive control (MPC) and AI-enhanced control frameworks, are evaluated with respect to transient performance, robustness, computational requirements, and scalability. The review identifies key technological milestones, emerging next-generation drive technologies, existing limitations, and unresolved research challenges. Finally, critical research gaps and future development pathways are articulated to support the advancement of high-efficiency, reliable, and cost-effective EV/HEV powertrain systems. Full article

The rapid growth of hiking tourism presents a critical challenge for balancing visitor safety with the sustainable management of ecologically fragile mountain environments. Traditional models developed in urban settings struggle to capture the highly non-linear, heterogeneous, and zero-inflated characteristics of wilderness trekking behavior. In order to quantify the nonlinear and threshold-based effects of environmental variables on hikers’ spatial decisions in unstructured wilderness and to identify distinct behavioral regimes for segmented management, this study introduces an explainable machine learning framework to reconstruct hikers’ spatial decision-making in a complex mountainous system in Inner Mongolia, China. Random Forest (RF), XGBoost, and LightGBM were compared in predicting trail density and the Euclidean distance to the nearest trail. Results show that transforming behavioral traces into continuous proximity surfaces dramatically improves model performance, with XGBoost achieving the highest predictive accuracy for Trail_Dist. By integrating the SHapley Additive exPlanations framework, this study moves beyond black-box prediction to reveal the nonlinear mechanisms driving hiker behavior. Key findings include: (1) Nighttime light range exhibits a U-shaped threshold effect as the primary anthropogenic attractor. (2) Elevation shows an exponential inhibitory trend above 1238 m. (3) Strong spatial coupling exists between elevation and slope, alongside a landscape compensation effect where high Normalized Difference Vegetation Index (NDVI) areas attract off-trail movements. This research provides a robust methodological pathway for predicting behavior in unstructured outdoor environments. It offers a scientific foundation for smart scenic area management, including optimized route planning, precise ecological protection zoning, and targeted emergency rescue preparedness. Full article

Background/Objectives: Alcohol misuse among medical students is commonly attributed to academic stress, yet the specific role of coping mechanisms in this relationship has received limited attention. We investigated whether substance use coping, rather than stress exposure itself, drives alcohol use risk in Romanian medical students, and whether distinct coping-based subgroups can be identified through cluster analysis. Methods: We conducted a cross-sectional survey among 244 medical students (mean age 21.95 ± 3.27 years; 67.2% female) at the University of Medicine and Pharmacy of Craiova, Romania. Alcohol use was measured with the AUDIT and coping strategies with the Brief COPE. Analyses included Mann–Whitney U tests, Spearman correlations, multiple linear and binary logistic regression, and k-means clustering. Results: At-risk drinking (AUDIT ≥ 8) was identified in 19.7% of participants. The tendency to use substances to cope with stress (substance use coping) was the strongest predictor of AUDIT scores in both linear regression (B = 2.090, p < 0.001, R² = 0.513) and logistic regression (OR = 2.026, p < 0.001). Male sex independently predicted at-risk status (OR = 2.572, p = 0.025), while planning was protective in both models (B = −0.657, p = 0.005; OR = 0.691, p = 0.029). Humor also emerged as a significant risk factor (OR = 1.638, p = 0.005). K-means analysis (k = 5) revealed five coping profiles with significantly different AUDIT distributions (Kruskal–Wallis H = 47.26, p < 0.001). The Substance-Oriented cluster (13.1% of students) had a mean AUDIT of 12.66, compared with 3.00–4.13 in other clusters. Conclusions: In a subgroup of medical students, alcohol use appears integrated into the coping repertoire rather than merely being a consequence of stress. The identified coping profiles should be interpreted as prototypical configurations with overlapping boundaries rather than discrete categorical types, given the low silhouette coefficient (0.094) of the cluster solution. The strong predictive effect of substance use coping should be interpreted with the caveat that the Brief COPE Substance Use subscale and the AUDIT share content related to alcohol use behavior, which may inflate the observed association. These findings point to the need for coping-specific interventions. Planning skills training and a more nuanced understanding of humor’s role in drinking contexts may offer avenues for prevention. However, the logistic model’s sensitivity of 50.0% indicates that coping-based identification alone would miss approximately half of at-risk students, underscoring the need for further refinement before clinical application. Full article

This paper introduces a rigorous class of two-dimensional Markov-switching autoregressive moving-average (2D MS-ARMA) models for spatial lattice data exhibiting regime-dependent dynamics. The switching mechanism is governed by a latent causal Markov random field that drives spatial transitions between regime-specific autoregressive and moving-average structures. We provide sufficient conditions for the existence of a strictly stationary solution through the top Lyapunov exponent associated with a sequence of random matrices obtained from a state-space representation constructed along the lexicographic order. For the first-order bidirectional specification, we derive explicit spectral conditions linking stationarity to the regime-dependent spectral radii. Sufficient conditions ensuring the existence of finite second-order moments are also provided. Parameter estimation is carried out using a variational expectation–maximization (VEM) algorithm based on a mean-field approximation of the posterior distribution of the hidden regimes. The E-step yields closed-form coordinate ascent updates, while the M-step relies on gradient-based numerical optimization with derivatives computed via recursive differentiation. Under increasing-domain asymptotics, we discuss the consistency and asymptotic behavior of the variational estimator. The proposed framework fills a methodological gap between classical one-dimensional Markov-switching ARMA models and spatial autoregressive structures by extending regime-switching theory to multi-indexed processes with rigorous probabilistic foundations. It provides a comprehensive basis for statistical inference, model diagnostics, and prediction in spatially heterogeneous environments. Full article

This study re-examines two geologically and geotechnically similar geosynthetic-reinforced soil walls with modular block facings (GRS-MBs) that exhibited markedly different seismic performances during the 1999 Chi-Chi earthquake (M_L = 7.3). Integrating a multi-wedge failure mechanism that captures soil–facing–reinforcement interactions with a nonlinear hyperbolic soil model representing shear stress–displacement behavior along the slip surface, the Force–equilibrium-based Finite Displacement Method (FFDM) provides consistent and robust displacement evaluations over a wide range of input seismic inertial forces. A systematic sensitivity investigation confirms that the FFDM framework responds to parameter variations in a physically meaningful manner, and that displacement predictions remain stable with respect to reasonable uncertainties in soil, reinforcement, and facing properties. The analysis clarifies why two similar GRS-MBs responded so differently during strong shaking and demonstrates the broader applicability of FFDM for displacement-based seismic assessment, including under shaking levels (e.g., k_h ≈ 0.3) that would drive conventional limit–equilibrium calculations to F_s < 1.0, a physically impossible state requiring shear resistance greater than the soil’s ultimate strength. A comparative evaluation of seismic displacement predictions using the Newmark method and FFDM shows that FFDM successfully generates displacement-based seismic resisting curves and reproduces field-observed displacements. In contrast, the Newmark method yields order-of-magnitude variability in predicted movements and may be unsuitable for displacement-sensitive engineered slopes where deformations on the order of several 10⁻³–10⁻² m are practically significant. For interaction-rich GRS-MBs with high values of k_hc, beyond the predictive capability of Newmark’s equation, FFDM offers a practical and physically grounded tool for seismic displacement assessment of reinforced soil structures. Full article

Four-dimensional (4D) printing integrates additive manufacturing with stimuli-responsive materials to fabricate biomedical implants and functional healthcare devices that undergo programmed, time-dependent changes in shape or function. Unlike static 3D-printed constructs, 4D-printed systems can respond to clinically relevant stimuli such as temperature, hydration, pH, light (including near-infrared), magnetic fields, or electrical inputs. These triggers drive defined actuation mechanisms, most commonly thermomechanical shape-memory recovery, swelling-induced morphing, and magnetothermal activation. This review synthesizes the principal material platforms used for biomedical 4D printing, including shape-memory polymers and alloys, hydrogels, liquid-crystal elastomers, and responsive composites, and links material choice to device behavior and translational feasibility. Applications are discussed across self-expanding stents, cardiac occluders, tissue-engineered constructs, implantable drug delivery systems, and adaptive wearables. Key translational challenges include sterilization compatibility, manufacturing reproducibility and quality control, safe stimulus delivery, predictable biodegradation and long-term biocompatibility, and regulatory pathway definition. Full article

The use of millimeter-wave spectrum in fifth-generation (5G) systems is increasing the need for accurate prediction of received power and coverage in real deployment scenarios. In this context, ray tracing (RT) is a promising approach for site-specific analysis, although its reliability depends on how accurately different tools reproduce measurements in complex urban environments. This work presents a comparative assessment at 27 GHz of three RT tools: in-house Exact tool based on Vertical Plane Launching (VPL), Matlab 5G and open-source Sionna RT based on Shooting and Bouncing Rays (SBR). The comparison relies on a large outdoor walk-test campaign, including about 14,725 measurement points collected in a real urban area around a 27 GHz mMIMO base station, using real operator-provided antenna radiation patterns. Measured and simulated power levels are compared using statistical metrics, including Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and a planning-oriented coverage-rate metric. The results show a reasonable agreement between simulations and measurements, with RMSE and MAE values around 10–12 dB, highlighting tool-specific behaviors related to boundary effects, interaction modeling, and high-power overestimation. This work confirms that RT is a flexible support for 5G preliminary network design, reducing the need for extensive drive tests. Full article

With the growing demand for hybrid and electric vehicles, the accurate prediction of NVH (Noise, Vibration, and Harshness) behavior in Permanent Magnet Synchronous Machines (PMSMs) has become a critical aspect of electric motor design. This paper presents a detailed modeling approach for electromagnetic-induced noise and vibrations in PMSMs, integrating both analytical and numerical methods. The model focuses on quantifying the contributions of radial and tangential electromagnetic forces, which are key drivers of vibro-acoustic responses. The analytical part employs curved beam theory and a simplified acoustic model, offering rapid insights during early design stages. In parallel, a detailed numerical model based on finite element analysis is developed using a physics-based approach that accounts for the actual geometry and material properties of the PMSM prototype. This allows for enhanced accuracy without relying on experimental material parameter identification. Moreover, the detailed model includes the fluid–structure interaction introduced by the channels of the cooling fluid of the electric machine, which, although poorly addressed by the existing literature, was found to play a key role in driving the vibrational behaviour of the structure. By combining analytical speed with numerical precision, the proposed approach enables consistent and physically-based NVH predictions across various design phases, ultimately supporting improved electric machine performance and reducing development time and costs. Validation against experimental data confirms the ability of the model to accurately predict both sound pressure levels and housing surface vibrations. The novelty of this work lies in its integration of fluid–structure interaction and material modeling without the need for empirical parameter tuning, offering a robust tool for NVH design in electric vehicle applications. Full article

Pedestrian interaction remains a central safety challenge for autonomous driving, particularly under non-compliant or adversarial pedestrian behavior. Existing research and evaluations predominantly test against rule-following pedestrians, leaving a gap in understanding how learning-based agents handle worst-case interactions. We introduce the Jaywalkers Library, a novel configurable benchmark in CARLA with three adversarial pedestrian archetypes (Intruder, Indecisive Crosser, and Protester). We evaluate a DreamerV3 agent trained with sparse rewards, where the only pedestrian-specific signal is a terminal collision penalty. Evaluation employs a frozen-policy protocol with explicit train–test separation. Safety behavior is decomposed into endpoint outcomes, evasion dynamics, and efficiency costs. Under nominal conditions, the agent achieves high route completion and generalizes to an unseen town, whereas under adversarial exposure, an archetype-sensitive evasion strategy emerges. The agent swerves at speed against dynamic pedestrians but decelerates against the slow-moving Protester. Collision rates reveal a counterintuitive difficulty ordering in which the Protester is the hardest, followed by the Intruder, with the Indecisive Crosser as the most survivable. These findings show that a sparse terminal penalty suffices for emergent pedestrian avoidance in a world-model agent, but that effectiveness is bounded by the world model’s ability to predict pedestrian persistence. Full article

Trajectory planning in dynamic multi-vehicle interaction environments faces three critical challenges, including the difficulty of quantifying spatial risk distributions, the complexity of characterizing behavioral uncertainty arising from the multimodal maneuvers of surrounding vehicles, and the challenge of simultaneously optimizing multiple competing objectives such as safety, efficiency, comfort, and energy consumption. To address these challenges, this paper proposes an Improved Driving Risk Field-based Multi-objective Trajectory Optimization (IDRF-MTO) method. First, a joint spatiotemporal social attention mechanism achieves unified modeling of spatial interactions, temporal dependencies, and spatiotemporal coupling, combined with a lateral–longitudinal intent strategy for multimodal trajectory prediction. Second, an improved dynamic risk field model is constructed comprising three components: a vehicle risk field that incorporates spatial orientation and motion direction factors for anisotropic risk representation, along with a collision tendency factor that converts objective risk into effective risk; a predicted trajectory risk field that achieves anticipatory quantification of future risk from surrounding vehicles through confidence-weighted fusion; and a driving environment risk field that encapsulates road geometry, static obstacles, and environmental conditions. Finally, a multi-objective cost function embedding risk field gradients is formulated, and multi-objective coordinated optimization is realized through a three-dimensional spatiotemporal situation graph with adaptive safety sampling. Simulation results demonstrate that the proposed method enhances safety while simultaneously improving comfort and efficiency and reducing energy consumption, exhibiting excellent planning performance in complex dynamic environments. Full article

Flame residence time (FRT) is an important indicator of flaming duration and is closely related to local heat release and associated ecological effects. However, the intrinsic mechanisms through which fuel bed structure affects FRT remains insufficiently understood. Clarifying how fuel bed structure affects FRT under flat, wind-free conditions is important for prescribed burning and ecological restoration. This study investigated surface fuels from typical forest types in southwestern China through controlled laboratory experiments conducted under flat, wind-free conditions, with moisture content, loading, thickness, and bulk density systematically varied. The driving mechanisms of fuel bed structural characteristics on FRT were systematically analyzed. Coniferous forests and moso bamboo had significantly lower FRT than broadleaved forests. Moisture content was the most influential factor, followed by thickness and bulk density, whereas loading had a relatively limited effect. Prediction models developed using machine learning methods significantly outperformed traditional regression approaches. Fuel bed structure is a critical factor controlling FRT. The high-accuracy prediction models established in this study enhance the mechanistic understanding of FRT. The findings provide a theoretical basis and practical support for prescribed burning and fire behavior modeling and may contribute to improved forest fire management. Full article