Search Results (116)

Pedestrian trajectory prediction is crucial for autonomous systems navigating human-populated environments. However, existing methods face fundamental challenges including spurious correlations induced by confounding social environments, passive uncertainty modeling that limits prediction diversity, and bias coupling during feature interaction that contaminates trajectory representations. To address these issues, we propose a novel Causal Intervention and Counterfactual Reasoning (CICR) framework that shifts trajectory prediction from associative learning to a causal inference paradigm. Our approach features a hierarchical architecture having three core components: a Multisource Encoder that extracts comprehensive spatio-temporal and social context features; a Causal Intervention Fusion Module that eliminates confounding bias through the front-door criterion and cross-attention mechanisms; and a Counterfactual Reasoning Decoder that proactively generates diverse future trajectories by simulating hypothetical scenarios. Extensive experiments on the ETH/UCY, SDD, and AVD datasets demonstrate superior performance, achieving an average ADE/FDE of 0.17/0.24 on ETH/UCY and 7.13/10.29 on SDD, with particular advantages in long-term prediction and cross-domain generalization. Full article

We propose a novel meta-learning enhanced 3D CNN-LSTM framework for durability prediction. The framework integrates 3D microstructural data from micro-CT scanning with environmental time-series data through a dual-branch architecture: a 3D CNN branch extracts spatial degradation patterns from volumetric data, while an LSTM network processes temporal environmental factors. To address data scarcity, we incorporate a prototypical network-based meta-learning module that learns class prototypes from limited support samples and generalizes predictions to new corrosion scenarios through distance-based probability estimation. Additionally, we develop a dynamic feature fusion mechanism that adaptively combines spatial, environmental, and mechanical features using trainable attention coefficients, enabling context-aware representation learning. Finally, an interface damage visualization component identifies critical degradation zones and propagation trajectories, providing interpretable engineering insights. Experimental validation on laboratory specimens demonstrates superior accuracy (74.6% in 1-shot scenarios) compared to conventional methods, particularly in aggressive corrosion environments where data scarcity typically hinders reliable prediction. The visualization system generates interpretable 3D damage maps with an average Intersection-over-Union of 0.78 compared to ground truth segmentations. This work establishes a unified computational framework bridging microstructure analysis with macroscopic durability assessment, offering practical value for infrastructure maintenance decision-making under uncertainty. The modular design facilitates extension to diverse interface types and environmental conditions. Full article

As vehicle-centric perception struggles with occlusion and dense traffic, vehicle-infrastructure cooperative perception (VICP) offers a viable route to extend sensing coverage and robustness. This study proposes a feature-level VICP framework that fuses vehicle- and roadside-derived visual features via V2X communication. The model integrates four components: regional feature reconstruction (RFR) for transferring region-specific roadside cues, context-driven channel attention (CDCA) for channel recalibration, uncertainty-weighted fusion (UWF) for confidence-guided weighting, and point sampling voxel fusion (PSVF) for efficient alignment. Evaluated on the DAIR-V2X-C benchmark, our method consistently outperforms state-of-the-art feature-level fusion baselines, achieving improved ${AP}_{3D}$ and ${AP}_{BEV}$ (reported settings: 16.31% and 21.49%, respectively). Ablations show RFR provides the largest single-module gain +3.27% ${AP}_{3D}$ and +3.85% ${AP}_{BEV}$, UWF yields substantial robustness gains, and CDCA offers modest calibration benefits. The framework enhances occlusion handling and cross-view detection while reducing dependence on explicit camera calibration, supporting more generalizable cooperative perception. Full article

Japanese Encephalitis (JE) is a mosquito-borne viral infection that causes acute brain inflammation. First identified in Japan in 1871, the disease gained renewed global attention in 2025 after emerging in a non-endemic region, raising significant healthcare concerns. Vaccination remains the most effective strategy for preventing outbreaks. However, low- and middle-income countries (LMICs) face considerable challenges in implementing vaccination programs due to geographical, economic, and regulatory barriers. Most existing studies on JE vaccines (JEVs) have been conducted in higher-income countries, leaving critical gaps in data on efficacy and safety in LMIC settings. Furthermore, uncertainties surrounding cost-effectiveness make funding decisions more complex. This narrative review evaluates the current evidence on JE vaccination in LMICs, based on a literature search in PubMed and ScienceDirect covering 2005–2025. The review examines vaccine efficacy, safety, cost-effectiveness, and policy implementation. Findings show that JEVs demonstrate high efficacy and strong safety profiles, with mild adverse effects, most commonly fever. The live attenuated SA 14-14-2 vaccine (LAJEV) is particularly cost-effective, offering substantial economic benefits by reducing healthcare expenditures in endemic regions. To ensure sustainability, vaccination programs in LMICs require tailored policies and targeted financial support. Policy frameworks must be adapted to local contexts, enabling focused, effective, and equitable implementation. Full article

This study investigates the interpretation of hand gestures in nonverbal communication, with particular attention paid to cases where gesture form does not reliably convey the intended meaning. Hand gestures are a key medium for expressing impressions, complementing or substituting verbal communication. For example, the “Thumbs Up” gesture is generally associated with approval, yet its interpretation can vary across contexts and individuals. Using participant-generated descriptive words, sentiment analysis with the VADER method, and fuzzy membership modeling, this research examines the variability and ambiguity in gesture–intention mappings. Our results show that Negative gestures, such as “Thumbs Down,” consistently align with Negative sentiment, while Positive and Neutral gestures, including “Thumbs Sideways” and “So-so,” exhibit greater interpretive flexibility, often spanning adjacent sentiment categories. These findings demonstrate that rigid, category-based classification systems risk oversimplifying nonverbal communication, particularly for gestures with higher interpretive uncertainty. The proposed fuzzy logic-based framework offers a more context-sensitive and human-aligned approach to modeling gesture intention, with implications for affective computing, behavioral analysis, and human–computer interaction. Full article

Real-time distribution system state estimation is hampered by limited observability, frequent topology changes, and measurement errors. Neural networks can capture the nonlinear characteristics of power-grid operation through a data-driven approach that possesses important theoretical value and is promising for engineering applications. In that context, we develop a deep learning framework that leverages General Attributed Multiplex Heterogeneous Network Embedding to explicitly encode the multiplex, heterogeneous structure of distribution networks and to support inductive learning that adapts to dynamic topology. A cross-modal attention mechanism further models fine-grained interactions between input measurements and node/edge attributes, enabling the capture of nonlinear correlations essential for accurate state estimation. To ensure physical feasibility, soft power-flow residuals are incorporated into training as a physics-constrained regularization, guiding predictions toward consistency with grid operation. Extensive studies on IEEE/CIGRE 14-, 70-, and 179-bus systems show that the proposed method surpasses conventional weighted least squares and representative neural baselines in accuracy, convergence speed, and computational efficiency while exhibiting strong robustness to measurement noise and topological uncertainty. Full article

The scarcity of explicit feedback data is a major challenge in the design of recommender systems. Although such data are of a high quality due to users’ voluntary provision of numerical ratings, collecting a sufficient amount in real-world service environments is typically infeasible. As an alternative, implicit feedback data are extensively used. However, because implicit feedback represents observable user actions rather than direct preference statements, it inherently suffers from ambiguity as a signal of true user preference. To address this issue, this study reinterprets the ambiguity of implicit feedback signals as a problem of epistemic uncertainty regarding user preferences and proposes a latent factor model that incorporates this uncertainty within a Bayesian framework. Specifically, the behavioral vector of a user, which is learned from implicit feedback, is restructured within the embedding space using attention mechanisms applied to the user’s interaction history, forming an implicit preference representation. Similarly, item feature vectors are reinterpreted in the context of the target user’s history, resulting in personalized item representations. This study replaces the deterministic attention scores with stochastic attention weights treated as random variables whose distributions are modeled using a Bayesian approach. Through this design, the proposed model effectively captures the uncertainty stemming from implicit feedback within the vector representations of users and items. The experimental results demonstrate that the proposed model not only effectively mitigates the ambiguity of preference signals inherent in implicit feedback data but also achieves better performance improvements than baseline models, particularly on datasets characterized by high user–item interaction sparsity. The proposed model, when integrated with an attention module, generally outperformed other MLP-based models in terms of NDCG@10. Moreover, incorporating the Bayesian attention mechanism yielded an additional performance gain of up to 0.0531 compared to the model using a standard attention module. Full article

The metal-free polymeric semiconductor graphitic carbon nitride (g-C₃N₄) has emerged as a promising material for photocatalytic applications due to its responsiveness to visible light, adjustable electronic structure, and stability. This review systematically summarizes recent advances in preparation strategies, including thermal polycondensation, solvothermal synthesis, and template methods. Additionally, it discusses modification approaches such as heterojunction construction, elemental doping, defect engineering, morphology control, and cocatalyst loading. Furthermore, it explores the diverse applications of g-C₃N₄-based materials in photocatalysis, including hydrogen (H₂) evolution, carbon dioxide (CO₂) reduction, pollutant degradation, and the emerging field of piezoelectric photocatalysis. Particular attention is given to g-C₃N₄ composites that are rationally designed to enhance charge separation and light utilization. Additionally, the synergistic mechanism of photo–piezocatalysis is examined, wherein a mechanically induced piezoelectric field facilitates carrier separation and surface reactions. Despite significant advancements, challenges persist, including limited visible-light absorption, scalability issues, and uncertainties in the multi-field coupling mechanisms. The aim of this review is to provide guidelines for future research that may lead to the development of high-performance and energy-efficient catalytic systems in the context of environmental and energy applications. Full article

Underwater vessel localization using passive magnetic anomaly sensing is a challenging problem due to the variability in vessel magnetic signatures and operational conditions. Data-based approaches may fail to generalize even to slightly different conditions. Thus, we propose an Attentive Neural Process (ANP) approach, in order to take advantage of its few-shot capabilities to generalize, for robust localization of underwater vessels based on magnetic anomaly measurements. Our ANP models the mapping from multi-sensor magnetic readings to position as a stochastic function: it cross-attends to a variable-size set of context points and fuses these with a global latent code that captures trajectory-level factors. The decoder outputs a Gaussian over coordinates, providing both point estimates and well-calibrated predictive variance. We validate our approach using a comprehensive dataset of magnetic disturbance fields, covering 64 distinct vessel configurations (combinations of varying hull sizes, submersion depths (water-column height over a seabed array), and total numbers of available sensors). Six magnetometer sensors in a fixed circular arrangement record the magnetic field perturbations as a vessel traverses sinusoidal trajectories. We compare the ANP against baseline multilayer perceptron (MLP) models: (1) base MLPs trained separately on each vessel configuration, and (2) a domain-randomized search (DRS) MLP trained on the aggregate of all configurations to evaluate generalization across domains. The results demonstrate that the ANP achieves superior generalization to new vessel conditions, matching the accuracy of configuration-specific MLPs while providing well-calibrated uncertainty quantification. This uncertainty-aware prediction capability is crucial for real-world deployments, as it can inform adaptive sensing and decision-making. Across various in-distribution scenarios, the ANP halves the mean absolute error versus a domain-randomized MLP (0.43 m vs. 0.84 m). The model is even able to generalize to out-of-distribution data, which means that our approach has the potential to facilitate transferability from offline training to real-world conditions. Full article

This article presents a hybrid approach that combines Laguerre orthonormal functions with deep neural networks (DNN) for effective approximation of impulse responses of dynamic systems. Attention is given to key limitations in approximation with Laguerre functions, such as the selection of the optimal scaling factor, the number of functions used, and computational complexity. By training compact DNNs that directly predict the decomposition coefficients, increased functionality is achieved, as well as greater flexibility and efficiency in the context of implementing MPC. The proposed architecture provides good scalability, robustness, and computational efficiency, making it applicable in tasks related to system approximation and identification under uncertainty and noise conditions. Full article

Digital transformation (DT) requires organizations to navigate complex technological and organizational changes, often under conditions of uncertainty. While agile methodologies are widely adopted to address the iterative and cross-functional nature of DT, limited attention has been paid to identifying critical success factors (CSFs) from a socio-technical systems (STS) perspective. This study addresses that gap by integrating and prioritizing CSFs as interdependent elements within a layered socio-technical framework. Drawing on a systematic review of 17 empirical and conceptual studies, we adapt Chow and Cao’s agile success model and validate a set of 14 CSFs across five domains—organizational, people, process, technical, and project—through a Delphi-informed Analytic Hierarchy Process (AHP). The findings reveal that organizational and people-related enablers, particularly management commitment, team capability, and organizational environment, carry the greatest weight in agile-based DT contexts. These results inform a three-layered framework—comprising organizational readiness, agile delivery, and project artefacts—which reflects how social, technical, and procedural factors interact systemically. The study contributes both theoretically, by operationalizing STS theory in the agile DT domain, and practically, by providing a prioritized CSF model to guide strategic planning and resource allocation in transformation initiatives. Full article

Existing nighttime visibility enhancement methods primarily focus on improving overall brightness under low-light conditions. However, nighttime road images are also affected by glare, glow, and flare from complex light sources such as streetlights and headlights, making it challenging to suppress locally overexposed regions and recover fine details. To address these challenges, we propose a Nighttime Road Glare Suppression Network (NRGS-Net) for glare removal and detail restoration. Specifically, to handle diverse glare disturbances caused by the uncertainty in light source positions and shapes, we designed a gated positional attention (GPA) module that integrates positional encoding with local contextual information to guide the network in accurately locating and suppressing glare regions, thereby enhancing the visibility of affected areas. Furthermore, we introduced an improved Uformer backbone named LCAtransformer, in which the downsampling layers adopt efficient depthwise separable convolutions to reduce computational cost while preserving critical spatial information. The upsampling layers incorporate a residual PixelShuffle module to achieve effective restoration in glare-affected regions. Additionally, channel attention is introduced within the Local Context-Aware Feed-Forward Network (LCA-FFN) to enable adaptive adjustment of feature weights, effectively suppressing irrelevant and interfering features. To advance the research in nighttime glare suppression, we constructed and publicly released the Night Road Glare Dataset (NRGD) captured in real nighttime road scenarios, enriching the evaluation system for this task. Experiments conducted on the Flare7K++ and NRGD, using five evaluation metrics and comparing six state-of-the-art methods, demonstrate that our method achieves superior performance in both subjective and objective metrics compared to existing advanced methods. Full article

Background/Objectives: The prognostic uncertainty of Mild Cognitive Impairment (MCI) imposes comprehensive neuropsychological evaluations beyond mere memory assessment. However, previous investigations into other cognitive domains, such as attention, have yielded divergent findings. Furthermore, while evidence suggests the presence of sex differences across the spectrum of dementia-related conditions, no study has systematically explored attentional disparities between genders within this context. The current study aims to investigate differences in the attentional subcomponents, i.e., alerting, orienting, and executive control, between patients with MCI and healthy older controls (HOCs), emphasizing interactions between biological sex and cognitive impairment. Methods: Thirty-six participants (18 MCI, and 18 HOCs) were evaluated using the Attention Network Test (ANT). Raw RTs as well as RTs corrected for general slowing were analyzed using Generalized Mixed Models. Results: Both health status and sex influenced ANT performance, when considering raw RTs. Nevertheless, after adjusting for the baseline processing speed, the effect of cognitive impairment was no longer evident in men, while it persisted in women, suggesting specific vulnerabilities in females not attributable to general slowing nor to the MCI diagnosis. Moreover, women appeared significantly slower and less accurate when dealing with conflicting information. Orienting and alerting did not differ between groups. Conclusions: To the best of our knowledge, this is the first study investigating sex differences in attentional subcomponents in the aging population. Our results suggest that previously reported inconsistencies about the decline of attentional subcomponents may be attributable to such diversities. Systematically addressing sex differences in cognitive decline appears pivotal for informing the development of precision medicine approaches. Full article

In the context of global climate governance and the International Maritime Organization’s (IMO) stringent carbon reduction targets, the transition to green shipping fuels faces systemic challenges in supply chain coordination. This study focuses on the strategic interactions between governments and enterprises in the construction of green fuel supply chains. By constructing a multidimensional scenario framework encompassing time, technological development, social attention, policy intensity, and market competition, and using evolutionary game models and system dynamics simulations, we reveal the dynamic evolution mechanism of government–enterprise decision making. System dynamics simulations reveal that (1) short-term government intervention accelerates infrastructure development but risks subsidy inefficiency; (2) medium-term policy stability and market-driven mechanisms are critical for sustaining enterprise investments; and (3) high social awareness and mature technologies significantly reduce strategic uncertainty. This research advances the application of evolutionary game theory in sustainable supply chains and offers a decision support framework for balancing governmental roles and market forces in maritime decarbonization. Full article

In the context of coal mine operations, the assurance of work safety relies heavily on efficient autonomous navigation for rescue robots, yet traditional path planning algorithms such as A and RRT exhibit significant deficiencies in a coal mine environment. Traditional path planning algorithms (such as Dijkstra and PRM) have certain deficiencies in dynamic Spaces and narrow environments. For example, the Dijkstra algorithm has A relatively high computational complexity, the PRM algorithm has poor adaptability in real-time obstacle avoidance, and the A* algorithm is prone to generating redundant nodes in complex terrains. In recent years, research on underground mine scenarios has also pointed out that there are many difficulties in the integration of global planning and local planning. This paper proposes an enhanced A* algorithm in conjunction with the Dynamic Window Approach (DWA) to enhance the efficiency, search accuracy, and obstacle avoidance capability of path planning by optimizing the target function and eliminating redundant nodes. This approach enables path smoothing to be performed. In order to ensure that the requirement of multiple target point detection is realized, an RRT algorithm is proposed to reduce the element of randomness and uncertainty in the path planning process, leading to an increase in the convergence rate and overall performance of the algorithm. The solution to the problem of determining the global optimal path is proposed to be simplified by means of the optimal path planning algorithm based on the gradient coordinate rotation method. In this study, we not only focus on the efficiency of mobile robot path planning and real-time dynamic obstacle avoidance capabilities but also pay special attention to the symmetry of the final path. The findings of simulation experiments conducted within the MATLAB environment demonstrate that the proposed algorithm exhibits a substantial enhancement in terms of three key metrics: path planning time, path length, and obstacle avoidance efficiency, when compared with conventional methodologies. This study provides a theoretical foundation for the autonomous navigation of mobile robots in coal mines. Full article