Search Results (154)

Urban growth models often prioritize environmental and accessibility factors while underestimating behavioral and functional dynamics. This study develops a POI-enhanced Cellular Automata (CA) framework to simulate urban expansion by incorporating three semantic indicators derived from Point-of-Interest (POI) data—density (PD), diversity (PDI), and functional centrality (FC). Taking Yan’an, China, as a case, the model integrates these indicators with terrain and infrastructure variables via logistic regression to estimate land-use transition probabilities. To ensure robustness, spatial block cross-validation was adopted to reduce spatial autocorrelation bias. Results show that the POI-based model outperforms the baseline in both Kappa and Figure of Merit metrics. High-density and mixed-function POI zones correspond with compact infill growth, while high-centrality zones predict decentralized expansion beyond administrative cores. These findings highlight how functional semantics sharpen spatial prediction and uncover latent behavioral demand. Policy implications include using POI-informed maps for adaptive zoning, ecological buffer protection, and growth hotspot management. The study contributes a transferable workflow for embedding behavioral logic into spatial simulation. However, limitations remain: the model relies on static POI data, omits vertical (3D) development, and lacks direct comparison with alternative models like Random Forest or SVM. Future research could explore dynamic POI trajectories, integrate 3D building forms, or adopt agent-based modeling for richer institutional representation. Overall, the approach enhances both the accuracy and interpretability of urban growth modeling, providing a flexible tool for planning in functionally evolving and ecologically constrained cities. Full article

Given the importance of relationship satisfaction and the detrimental effects of its decline in romantic couples, it is crucial to understand how relationship satisfaction develops over time in long-term stable relationships and to identify predictors that explain such long-term changes. Building upon previously identified subgroups with distinct trajectories of relationship satisfaction, our objective was to examine whether two types of relationship skills—dyadic coping and communication—predict subgroup trajectories. We followed 300 mixed-gender couples over 10 years in annual assessments and applied Dyadic Latent Class Growth models with predictors. Our results suggest that subgroups of relationship satisfaction trajectories can be differentiated by both baseline levels and changes in relationship skills. Couples with high and relatively stable satisfaction were distinguished from those with declining satisfaction primarily by baseline negative communication (women’s report) and a deterioration in dyadic coping. Couples with the lowest initial satisfaction exhibited the least beneficial relationship skills but increased their satisfaction over time, likely due to observed improvements in their skills. These findings have important public health implications, as modifiable relationship skills can be targeted in prevention, counseling, or therapy to help couples develop and sustain improvements in their relationship skills to protect their relational well-being in the long term. Full article

Agenda 2030, embodied by the United Nations’ Sustainable Development Goals (SDGs), represents a global commitment to advancing transparency, accountability, and sustainable development. This study examines whether the introduction of the SDGs in 2015 is associated with changes in environmental, social, and governance (ESG) performance trajectories among major multinational corporations. The analysis uses a piecewise latent trajectory model to examine the ESG trajectories of 320 Global Fortune 500 firms, spanning both the manufacturing and service sectors across developed and developing economies, over the period of 2010–2021. The time frame is deliberately segmented into a pre-SDG period (2010–2015) and one post-SDG implementation (2016–2021) to capture how ESG practices evolved following the launch of the SDGs as a global policy milestone. Our results highlight significant governance improvements in developed economies, especially within manufacturing, driven by regulatory changes and mandatory reporting, while environmental performance trends are more variable and social factors lag in some regions. These findings yield actionable insights for policymakers and managers by pinpointing industrial and regional disparities, thereby informing targeted strategies to advance SDG-aligned ESG practices and harmonize future reporting frameworks. Full article

Fine-grained modeling of driving styles is critical for decision making in autonomous driving. However, existing methods are constrained by the high cost of manual labeling and a lack of interpretability. This study proposes an unsupervised disentanglement framework based on a variational autoencoder (VAE), which, for the first time, enables the automatic extraction of interpretable driving style representations from car-following trajectories. The key innovations of this work are threefold: (1) a dual-decoder VAE architecture is designed, leveraging driver identity as a proxy label to guide the learning of the latent space; (2) self-dynamics and interaction dynamics features are decoupled, with an attention mechanism employed to quantify the influence of the lead vehicle; (3) a bidirectional interpretability verification framework is established between latent variables and trajectory behaviors. Evaluated on a car-following dataset comprising 25 drivers, the model achieves a Driver Identification accuracy of 98.88%. Mutual information analysis reveals the physical semantics encoded in major latent dimensions. For instance, latent dimension z₂₂ is strongly correlated with the minimum following distance and car-following efficiency. One-dimensional latent traversal further confirms that individual dimensions modulate specific behavioral traits: increasing z₂₂ improves safety margins by 18% but reduces efficiency by 23%, demonstrating that it encodes a trade-off between safety and efficiency. This work provides a controllable representation framework for driving style transfer in autonomous systems and offers a more granular approach for analyzing driver behavior in car-following scenarios, with potential for extension to broader driving contexts. Full article

(1) Background: Most studies including health data have relied on reducing all variables to manifest scores, ignoring the latent nature of variables. Moreover, relying only on manifest variables is a limitation of longitudinal studies where identical measures cannot be collected at each time point. (2) Objective: This scoping review aims to identify latent variable statistical methods for longitudinal studies of multi-dimensional health and educational data investigating early health predictors of long-term educational outcomes and developmental trajectories that lead to better or worse than expected outcomes. (3) Eligibility criteria: We included peer-reviewed health and education journal articles, doctoral theses, and book chapters of longitudinal studies of children under 12 years of age that adopted latent variable, multivariate analysis of three or more waves of data. We only included full-text-available, English-written articles, without restriction on date of publication. (4) Sources of evidence: We searched five databases, Scopus, MEDLINE, PsycINFO, ERIC, and Web of Science, and identified 4836 publications for screening. (5) Results: After title, abstract, and full-text screening, nine studies were included in the review, reporting seven statistical methods. These methods were categorised into two groups—variable-oriented modelling and person-oriented modelling. (6) Conclusions: Variable-oriented modelling methods are useful for determining predictors of long-term educational outcomes. Person-oriented modelling methods are effective in detecting trajectories to better or worse than expected outcomes. (7) Registration: Open Science Framework. Full article

Market indices, such as the S&P 500, serve as compressed representations of complex constituent-level dynamics. This study proposes a zero-shot forecasting framework capable of predicting index-level trajectories without direct supervision from index data. By leveraging a Variational AutoEncoder (VAE), the model learns a latent mapping from constituent-level price movements and macroeconomic factors to index behavior, effectively bypassing the need for aggregated index labels during training. Using hourly OHLC data of S&P 500 constituents, combined with the U.S. 10-Year Treasury Yield and the CBOE Volatility Index, the model is trained solely on disaggregated inputs. Experimental results demonstrate that the VAE achieves superior accuracy in index-level forecasting compared to models trained directly on index targets, highlighting its effectiveness in capturing the implicit generative structure of index formation. These findings suggest that constituent-driven latent representations can provide a scalable and generalizable approach to modeling aggregate market indicators, offering a robust alternative to traditional direct supervision paradigms. 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

Understanding asymmetric interactions among heterogeneous traffic participants is essential for managing congestion and enhancing safety at urban signalized intersections. This study proposes a cellular automaton modeling framework that captures the spatial and behavioral asymmetries among vehicles, bicycles, and pedestrians, with a particular focus on right-of-way hierarchies and conflict anticipation. Beyond simulation, the framework integrates a behavior pattern mining module that applies unsupervised trajectory clustering to identify recurrent interaction patterns emerging from mixed traffic flows. Simulation experiments are conducted under varying demand levels to investigate the propagation of congestion and the structural distribution of conflicts. The results reveal distinct asymmetric behavior patterns, such as right-turn vehicle blockage, non-lane-based bicycle overtaking, and pedestrian-induced disruptions. These patterns provide interpretable insights into the spatiotemporal dynamics of intersection performance and offer a data-driven foundation for optimizing signal control and multimodal traffic flow separation. The proposed framework demonstrates the value of combining microscopic modeling with data mining techniques to uncover latent structures in complex urban traffic systems. Full article

Active inference offers a unified framework in which agents can exhibit both goal-directed and epistemic behaviors. However, implementing policy search in high-dimensional continuous action spaces presents challenges in terms of scalability and stability. Our previously proposed model, T-GLean, addressed this issue by enabling efficient goal-directed planning through low-dimensional latent space search, further reduced by conditioning on prior habituated behavior. However, the lack of an epistemic term in minimizing expected free energy limited the agent’s ability to engage in information-seeking behavior that can be critical for attaining preferred outcomes. In this study, we present EFE-GLean, an extended version of T-GLean that overcomes this limitation by integrating epistemic value into the planning process. EFE-GLean generates goal-directed policies by inferring low-dimensional future posterior trajectories while maximizing expected information gain. Simulation experiments using an extended T-maze task—implemented in both discrete and continuous domains—demonstrate that the agent can successfully achieve its goals by exploiting hidden environmental information. Furthermore, we show that the agent is capable of adapting to abrupt environmental changes by dynamically revising plans through simultaneous minimization of past variational free energy and future expected free energy. Finally, analytical evaluations detail the underlying mechanisms and computational properties of the model. Full article

Trajectory prediction under multimodal information is critical for autonomous driving, necessitating the integration of dynamic vehicle states and static high-definition (HD) maps to model complex agent–scene interactions effectively. However, existing methods often employ static scene encodings and unstructured latent spaces, limiting their ability to capture evolving spatial contexts and produce diverse yet contextually coherent predictions. To tackle these challenges, we propose MS-SLV, a novel generative framework that introduces (1) a time-aware scene encoder that aligns HD map features with vehicle motion to capture evolving scene semantics and (2) a structured latent model that explicitly disentangles agent-specific intent and scene-level constraints. Additionally, we introduce an auxiliary lane prediction task to provide targeted supervision for scene understanding and improve latent variable learning. Our approach jointly predicts future trajectories and lane sequences, enabling more interpretable and scene-consistent forecasts. Extensive evaluations on the nuScenes dataset demonstrate the effectiveness of MS-SLV, achieving a 12.37% reduction in average displacement error and a 7.67% reduction in final displacement error over state-of-the-art methods. Moreover, MS-SLV significantly improves multi-modal prediction, reducing the top-5 Miss Rate (${\mathrm{MR}}_5$) and top-10 Miss Rate (${\mathrm{MR}}_{10}$) by 26% and 33%, respectively, and lowering the Off-Road Rate (ORR) by 3%, as compared with the strongest baseline in our evaluation. Full article

Technology roadmapping is conducted by systematic mapping of technological evolution through patent analytics to inform innovation strategies. This study proposes an integrated framework combining hierarchical Latent Dirichlet Allocation (LDA) modeling with multiphase technology lifecycle theory, analyzing 113,449 Derwent patent abstracts (2008–2022) across three dimensions: technological novelty, functional applications, and competitive advantages. By segmenting innovation stages via logistic growth curve modeling and optimizing topic extraction through perplexity validation, we constructed dynamic technology roadmaps to decode latent evolutionary patterns in AI-powered programmable manipulators (B25J classification) within an innovation trajectory. Key findings revealed: (1) a progressive transition from electromechanical actuation to sensor-integrated architectures, evidenced by 58% compound annual growth in embedded sensing patents; (2) application expansion from industrial automation (72% early stage patents) to precision medical operations, with surgical robotics growing 34% annually since 2018; and (3) continuous advancements in adaptive control algorithms, showing 2.7× growth in reinforcement learning implementations. The methodology integrates quantitative topic modeling (via pyLDAvis visualization and cosine similarity analysis) with qualitative lifecycle theory, addressing the limitations of conventional technology analysis methods by reconciling semantic granularity with temporal dynamics. The results identify core innovation trajectories—precision control, intelligent detection, and medical robotics—while highlighting emerging opportunities in autonomous navigation and human–robot collaboration. This framework provides empirically grounded strategic intelligence for R&D prioritization, cross-industry investment, and policy formulation in Industry 4.0. Full article

Background: A single measurement or a summary of a limited number of measurements of CA125 was considered in the prediction of clinical outcomes for patients with ovarian cancer. We aimed to identify the classes of patients with advanced ovarian cancer based on their CA125 trajectory and to investigate the heterogeneity of clinical outcomes among the patients in the different classes. Methods: CA125 trajectory classes were identified by latent-class mixed models based on values collected within 3 and 6 months post-treatment for 819 women with advanced ovarian cancer enrolled in a randomized trial. Results: Based on their CA125 values during the first 6 months of treatment, the patients with low CA125 levels at baseline that remained low during treatment had the best clinical outcome (a median survival of 83 months and a progression-free survival of 34 months). In contrast, the patients with high CA125 values at baseline with a modest decrease during treatment had the highest risk of death and progression (hazard ratio [95% confidence interval]: 4.83 [3.56, 6.54] for overall survival and 5.15 [3.87, 6.87] for progression-free survival). Conclusions: Longitudinal trajectories of CA125 may provide more direct information for the prognoses of patients with advanced ovarian cancer undergoing chemotherapy treatment. Full article

Neighbourhood variation in socioeconomic deprivation is recognised as a small but meaningful determinant of adolescent mental health, yet the mechanisms through which the effects operate remain poorly understood. This study used #BeeWell survey data collected from adolescents in Greater Manchester (England) in 2021–2023 (life satisfaction: N = 27,009; emotional difficulties: N = 26,461). Through Latent Growth Mixture Modelling, we identified four non-linear trajectories of life satisfaction (Consistently High (71.0%), Improving (8.7%), Deteriorating (6.3%), and Consistently Low (13.9%); entropy = 0.66) and three non-linear trajectories of emotional difficulties (Low/Lessening (53.7%), Sub-Clinical (38.3%), and Elevated/Worsening (8.0%); entropy = 0.61). Using a multi-level mediation framework we assessed (1) whether neighbourhood deprivation predicted trajectory class membership and (2) the extent to which effects of deprivation operate through aspects of Community Wellbeing, as measured by the Co-op Community Wellbeing Index (CWI). Greater deprivation increased the odds of following Deteriorating (OR = 1.081, [1.023, 1.12]) and Consistently Low (OR = 1.084, [1.051, 1.119]) life satisfaction trajectories and reduced the odds of following a Sub-Clinical emotional difficulties trajectory (OR = 0.975, [0.954, 0.996]). Mediation analyses revealed that the effects of deprivation on Consistently Low life satisfaction partially operate through Equality (ab = 0.016, [0.002, 0.029]) and Housing, Space, and Environment (ab = −0.026, [−0.046, −0.006]). Further indirect effects were observed for Housing, Space, and Environment, which reduced likelihood of Sub-Clinical emotional difficulties for those living in deprived neighbourhoods (ab = −0.026, [−0.045, −0.008]). The findings highlight the distinct effects of neighbourhood deprivation on affective and evaluative domains of adolescent mental health and the protective effect of housing and related environmental factors in disadvantaged contexts, advancing our understanding of the mechanisms underpinning neighbourhood effects on dual-state adolescent mental health. Full article

Gait speed and grip strength are widely used measures of physical function in older adults and are predictive of disability, hospitalization, and mortality. However, there is a limited understanding of the long-term trajectories of these measures and which older adults are at the highest risk of functional decline. We used data from the National Health and Aging Trends Study (NHATS) to identify subgroups of community-dwelling older adults with distinct 10-year trajectories in gait speed and grip strength and to examine the baseline factors associated with these patterns. The sample included 4961 adults aged 65 years and older who completed gait speed and grip strength assessments in 2011 and at least one subsequent wave between 2013 and 2021. Using latent class growth analysis, we identified three trajectories for each measure: worsening, stable, and improving. More than one-third of participants were in the worsening group for at least one measure. In multinomial logistic regression models, lower income, Medicaid coverage, cognitive impairment, and multiple chronic conditions were associated with membership in worsening trajectory groups. These findings highlight the heterogeneity of physical aging and the importance of the early identification of older adults who may benefit from targeted interventions to maintain function and independence over time. Full article

This study explores the use of Life Cycle Assessments (LCAs), Total Sustainability Assessment, and Life Cycle Sustainability Assessment (LCSA) as tools to evaluate the environmental, social, and economic impacts in Agri-industry. It highlights the unique trajectory of LCA and LCSA implementation in Latin America, shaped by the region’s distinct environmental, social, and economic contexts, contrasted with global research trends. Evidence shows the importance of biodiversity, conservation, and deforestation mitigation in Latin American LCA applications, which differ from the urban-focused impacts seen in regions like Europe or North America. Furthermore, it emphasizes the significant role of LCSA in addressing socio-economic challenges unique to Latin America, such as inequality and labor conditions. The research reveals the benefits of LCA and LCSA methodologies in the agro-industrial sector, particularly in addressing social issues like land use rights and rural community welfare. Despite challenges such as limited access to high-quality data and the need for capacity building, the innovative application of these methodologies in Latin America offers valuable insights for the global community. Our work relies on Latent Dirichlet Allocation (LDA) to analyze the LCSA literature from 1990 to 2024, identifying evolving trends and research focal areas in sustainability. The analysis herein presented highlights the need for a multi-dimensional and holistic approach to sustainability research and practice. Our findings also emphasize the importance of developing comprehensive models and integrated methodologies to effectively address complex sustainability challenges. Environmental information remains crucial for policy processes, acknowledging uncertainties in estimations and the connection between land use change, agriculture, and emissions from the global food economy and bioenergy sectors. The research underscores the dynamic nature of LCSA and the importance of continually reassessing sustainability efforts to address pressing challenges. Full article