Search Results (233)

Personalized itinerary planning for large-scale passengers under resource constraints is a critical challenge in enhancing the operational efficiency and service quality of cruise tourism. Traditional clustering methods, which primarily rely on geometric similarity, often fail to address the intricate coupling between passenger preferences and finite venue capacities, lacking predictive capability for the ultimate planning quality. To overcome these limitations, this study proposes a novel bio-inspired data-driven hybrid optimization framework for the cruise itinerary planning task unit partition. The framework innovatively integrates a Genetic Balanced Clustering Algorithm (GBCA) for multi-objective passenger grouping, Kernel Principal Component Analysis (KPCA) for feature extraction from preference data, an improved Adaptive Spiral Flying Sparrow Search Algorithm (ASFSSA) for hyperparameter optimization, and a Kernel Extreme Learning Machine (KELM) for data-driven prediction of itinerary planning quality. This synergy enables the framework to dynamically allocate venue capacities based on group preferences and optimize partitioning towards maximizing overall benefits, ensuring load balance and fairness. Extensive experiments on simulated cruise scenarios demonstrate that the proposed framework significantly outperforms conventional methods, improving segmentation quality by at least 40% while exhibiting superior convergence speed and stability. This work provides a scalable, intelligent solution for complex resource-constrained scheduling problems, showcasing the effective application of bio-inspired data-driven methodologies in engineering optimization. Full article

Plastic pollution poses a major environmental threat to coastal ecosystems, particularly in enclosed and semi-enclosed seas where limited water exchange promotes debris accumulation. This study presents a high-resolution spatial analysis of coastal plastic debris along the Khachmaz coastline in the western Caspian Sea. The analysis integrates unmanned aerial vehicle (UAV) imagery, YOLO-based deep learning detection, and spatial statistical methods. High-resolution UAV orthophotos enabled the automated detection of individual plastic debris items, which were converted into spatial point data for further analysis. Spatial patterns were assessed using areal density estimation, nearest neighbor analysis, kernel density estimation, and Ripley’s L-function to examine clustering across multiple spatial scales. A total of 2389 plastic debris items were identified within 0.0439 km², corresponding to an average density of 54,382 items per km². The results show that plastic debris is unevenly distributed, forming distinct clusters with four primary accumulation hotspots. Significant clustering occurs at spatial scales up to 20 m, with the strongest aggregation observed at distances below 5 m. Spatial overlay analysis indicates a strong association between plastic debris, reed-dominated coastal vegetation, and proximity to the shoreline, suggesting the potential role of localized retention processes and shoreline dynamics in debris accumulation. The combined use of UAV-based deep learning and spatial statistical analysis provides an integrated application framework for monitoring coastal plastic debris and supports targeted, sustainability-oriented coastal management strategies in the Caspian Sea region. Full article

With the increasing constraints of resource and environmental factors and the prominent issues of regional development imbalance, how to scientifically measure the level of agricultural sustainable development and reveal its spatial-temporal differentiation patterns has become a key scientific question that urgently needs to be addressed in optimizing land use layout and promoting rural revitalization. This study takes the human-land spatial systems coupling theory as the core framework and constructs an evaluation index system for agricultural sustainable development covering five dimensions: economy, society, resources, ecology, and technology. Based on provincial panel data in China from 2001 to 2024, the entropy method is employed to measure agricultural sustainable development, while Dagum’s Gini coefficient, kernel density estimation, and convergence models are applied to analyze its spatial–temporal evolution. Furthermore, the fuzzy-set qualitative comparative analysis (fsQCA) method is introduced to identify multi-factor configurational driving pathways. The results indicate that the overall level of agricultural sustainable development in China shows a steady upward trend, exhibiting a regional gradient pattern characterized by “central region leading, eastern region steadily advancing, and western region gradually catching up”. The overall disparity presents a weak convergence trend, with inter-regional differences as the primary source, although their contribution is gradually declining. The development structure has evolved from regional fragmentation to a more complex spatial interaction pattern. The overall distribution shifts rightward with evident stage-based differentiation, accompanied by significant positive spatial dependence, with “high–high” and “low–low” clustering coexisting over the long term. Convergence analysis shows that σ-convergence exists at the national level. After accounting for spatial effects, significant absolute β-convergence is observed in the eastern and western regions, while the central region does not exhibit significant convergence. Conditional β-convergence further confirms the existence of regional convergence trends, although the convergence speeds vary. The fsQCA results indicate that agricultural sustainable development is not driven by a single factor but by multiple configurational pathways formed through the interaction of various conditions. These findings provide empirical evidence for optimizing agricultural spatial layout, strengthening land factor support, and promoting regionally coordinated agricultural sustainable development. Full article

Classic machine learning and regime identification methods applied to financial time series lack theoretical guarantees and exhibit systematic failure modes: heavy-tails invalidate moment-based geometry, rendering distances and centroids dominated by extremes or unstable; jumps violate smoothness, destabilizing local regressions, kernel methods, and gradient-based learning; and non-stationarity disrupts neighborhood relations, so distances in classical feature spaces no longer reflect meaningful proximity. To address these challenges, we propose a topology-based machine-learning framework grounded on probabilistic reconstruction of state-space geometry, which replaces moment- and smoothness-dependent representations with deformation-stable summaries of state-space geometry, preserving neighborhoods, adjacency, and topology. The finite-sample validity of homeomorphic state-space reconstruction, required for topology-based machine learning, is assessed through numerical studies on synthetic data with heavy tails, jumps, and known ground-truth regimes. Further diagnostics of local invertibility and bounded geometric distortion quantify when embedding windows are consistent with local diffeomorphic behavior, enabling metric-sensitive, geometry-aware learning. Clustering of Hilbert-space summaries accurately recovers underlying market tail-risk regimes with robust results across selected filtrations. Temporal, feature-space, and cluster-label null tests confirm that topology-based clustering captures genuine topological structure rather than noise or artifacts, and encodes temporal dependencies at local, mesoscopic, and network levels associated with market regimes. Full article

This paper examines public architecture in Baghdad during the late nineteenth and early twentieth centuries, focusing on how public buildings contributed to the formation of urban centrality and how this process interacted with local architectural practices. Rather than approaching public construction solely through administrative or ideological frameworks, the study conceptualizes public buildings as structuring components in the reconfiguration of the urban fabric. Methodologically, the research adopts a two-stage, multi-scalar approach. First, public buildings in Beirut, Damascus, and Baghdad are identified and comparatively analyzed using QGIS-based spatial analysis, employing Kernel Density Estimation and DBSCAN clustering to examine patterns of spatial concentration, distribution, and relationships with major urban axes. This comparative stage establishes a comparative spatial framework for understanding urban centrality in provincial capitals. In the second stage, Baghdad is examined as a focused case study through building-scale architectural analysis, incorporating plan organization, construction techniques, material use, and environmental adaptation based on archival documents, historical maps, and visual sources. The results indicate that public buildings in Baghdad were not isolated institutional entities but integral components in the formation of new urban focal areas structured along river-oriented and infrastructural axes. Architecturally, these buildings exhibit a hybrid character, combining standardized public building programs with locally embedded materials, construction methods, and spatial adaptations. The study concludes that public architecture in late Ottoman Baghdad emerged through a negotiated process between centralized planning principles and local architectural knowledge, producing a distinct yet contextually grounded form of urban centrality. Full article

Industrial Quality Inspection (IQI) is a pivotal part of intelligent manufacturing, critical to ensuring product quality. Deep learning-based methods have attracted growing attention for their excellent feature extraction ability, outperforming traditional detection approaches. However, existing methods still face issues of insufficient efficiency and poor transferability, and this paper proposes a Fine-tuned Lightweight Faster RCNN (FLF-RCNN) framework designed to address key challenges in IQI, including the trade-off between accuracy and computational efficiency, and the insufficient adaptability of preset anchor box ratios. FLF-RCNN introduces a lightweight backbone network, LSNet, which enhances the receptive field through architectural optimization. Specifically, it uses a collaborative mechanism that combines large kernel convolutions for extracting contextual information and small kernel convolutions for capturing fine-grained details. This mechanism enables the model to efficiently and precisely represent defects. To enhance generalization in data-scarce industrial scenarios, the framework leverages transfer learning with pretrained weights. Furthermore, an Adaptive Anchor Box-Adjustment Module (AAB-AM) based on K-means clustering is introduced to improve detection across varied defect scales. Extensive experiments conducted on the Tianchi dataset show that FLF-RCNN achieves a mAP50 of 43.6%, outperforming detectors using MobileNet and EfficientNet backbones and surpassing the baseline Faster R-CNN by 7.9% in mAP50. Meanwhile, the proposed method reduces computational complexity by approximately 40%, reaching 98.65 GFLOPs, and decreases parameter count by around 30% to 28.2M. These results demonstrate that FLF-RCNN offers a feasibility and practical solution for IQI, achieving a superior accuracy-efficiency balance within the two-stage detection paradigm. Full article

This paper focuses on the coordinated development and barrier factors of green logistics (GL) and regional economy (RE) in the Yellow River Basin (YRB). Based on data from 2014 to 2023, it constructs an index system covering the development foundation, benefits, potential and sustainability of GL, as well as regional economic structure, scale and potential. Using methods such as the entropy method, coupling coordination degree (CCD) model, kernel density estimation, Moran’s index and Obstacle degree model, it reveals that the average comprehensive CCD improved from 0.38 to 0.65 over the decade, but with significant regional differences. Eastern provinces like Shandong and Henan are ahead, while central and western provinces lag. The coupling coordination degree shows an overall upward trend, moving toward coordinated development with an expanding spatial pattern from east to west and narrowing regional gaps. Global Moran’s index (ranging from 0.356 to 0.524) indicates a spatial positive correlation, and local spatial autocorrelation analysis shows coexistence of high–high and low–low clusters. For Obstacle factors, GL is primarily constrained by low labor productivity (indicator B3, accounting for 23.1% to 44.7% of the total obstacle degree) and shortcomings in logistics industry benefits and scale, while RE is hindered by lagging economic structure optimization, weak foreign trade, and insufficient economic scale and vitality. This study provides a theoretical basis and decision-making reference for the high-quality coordinated development of GL and RE in the YRB, promoting regional coordination and sustainable development. Full article

Rapid eye movement (REM) sleep is increasingly understood as a heterogeneous state composed of two neurophysiologically distinct microstates: tonic REM and phasic REM. Phasic REM, defined by brief clusters of saccadic eye movements and transient cortical activation, has been linked to emotional memory consolidation, sensorimotor integration, and autonomic modulation. Despite its importance, automated quantification of phasic versus tonic REM remains uncommon, mainly because existing electrooculography (EOG) methods rely on fixed thresholds or generic wavelet families that do not accurately capture real saccade morphology in clinical polysomnography (PSG). This study introduces a fully automated framework for detecting phasic REM based on hybrid adaptive segmentation of a single EOG channel. The segmentation algorithm fuses median absolute deviation (MAD) amplitude-change detection with a morphology score derived from a custom saccade kernel built from manually verified EyeCon recordings. Segment boundaries are refined using local derivative extrema to improve temporal alignment. A supervised support vector machine (SVM) classifier further refines segment labels using features based on saccade morphology, including correlations with custom log-sigmoid templates and a morphology similarity measure. All segmentation and classification hyperparameters were optimized exclusively on controlled EyeCon datasets with precise ground-truth event markers. The final model was then applied without modification to 21 full-night clinical PSG recordings. Event-level analysis on EyeCon yielded 92.9% correct detections, with 5.3% fragmentation and 1.8% missed events. When aggregated into saccadic bursts, the resulting REM microstructure was physiologically consistent: phasic REM accounted for 31.8 ± 3.5% of REM duration, and tonic REM for 68.2 ± 3.5%. Additional EEG analysis confirmed increased beta and gamma power during phasic REM, supporting physiological validity. The proposed framework provides an interpretable, morphology-aware, and computationally efficient tool for large-scale REM microstructure research. Its single-channel design and external validation on clinical PSG recordings make it suitable for both retrospective analyses and future clinical applications. Full article

Background: Meal timing has emerged as a potential determinant of healthy aging; however, evidence linking temporal dietary patterns (TDPs) with frailty remains limited. We aimed to identify distinct TDPs among older adults and examine their associations with frailty and its components. Methods: In this cross-sectional study, 4184 adults aged ≥ 65 years from the Korea National Health and Nutrition Examination Survey (2016–2018) were analyzed. Temporal energy-intake trajectories from 24 h recalls were clustered using dynamic time warping-based kernel k-means. Frailty was defined using a modified Fried phenotype, and diet quality was assessed employing the Healthy Eating Index. Survey-weighted logistic regression and mediation analyses were performed. Results: Five distinct patterns were identified as follows: balanced (n = 1665, 38.8%), steady (n = 735, 17.8%), midday (n = 737, 18.0%), evening (n = 627, 15.2%), and morning–evening (n = 420, 10.2%). Among these, the evening-skewed (characterized by a disproportionate concentration of energy intake in the late evening; adjusted odds ratio [OR] = 1.48, 95% confidence interval [CI] = 1.03–2.10) and morning–evening (characterized by higher energy intake in both the morning and evening; OR = 1.43, 95% CI = 1.01–2.03) patterns were associated with higher frailty risk than the balanced pattern. Mediation analysis showed that higher total energy intake had a protective role in the evening-skewed pattern; however, this benefit was offset by the adverse impact of late-night eating, resulting in increased frailty risk. In the morning–evening pattern, both a direct association with frailty and an indirect pathway mediated by lower energy intake and poorer diet quality contributed to the increased frailty risk. Conclusions: Older adults with evening-skewed or morning–evening TDPs had greater frailty risk than those with balanced eating patterns. Optimizing meal timing—by reducing late-day energy loading and ensuring adequate overall intake and dietary quality—may represent a feasible chrono-nutrition strategy for frailty prevention. Full article

Population ageing is intensifying pressure on elderly-care provision in megacity suburbs, but spatially explicit evidence on who benefits and where gaps persist remains limited. Using Daxing District, Beijing, as a case study, under the 15-min community living circle framework, we integrate cleaned elderly-care facility POIs from the municipal government portal (209 points), census-calibrated age-stratified WorldPop 100 m grids, and an OpenStreetMap road network to evaluate walking-based supply–demand matching. Kernel density estimation (KDE) characterizes facility agglomeration; the Gaussian Two-Step Floating Catchment Area (Ga2SFCA) method (1 km threshold) measures accessibility for two cohorts (60–80 and 80+); and global Moran’s I with bivariate LISA identifies spatial coupling between accessibility and elderly population density. The results indicate the following: (1) pronounced spatial imbalance—facilities are concentrated in the northwest and east but remain sparse in central and southern areas, while elderly population density follows a center–periphery gradient, peaking at 12,000 persons/km² in core areas (e.g., Jiugong and Huangcun); (2) clear accessibility stratification—overall accessibility is low and spatially clustered, yet the 80+ cohort (13.6% of the elderly population) exhibits markedly higher accessibility than the 60–80 cohort; and (3) differentiated coupling types—global bivariate Moran’s I = 0.773143 (p < 0.01), with LISA dominated by low-demand–low-accessibility (LL) areas and additional high-demand–low-accessibility (HL) shortage zones and low-demand–high-accessibility (LH) potential redundancy zones, while HH areas are scarce. These diagnostics support zone-specific gap filling to mitigate spatial inequities and age–structural mismatches. Full article

Deep learning–based pansharpening methods for remote sensing have advanced rapidly in recent years. However, current methods still face three limitations that directly affect reconstruction quality. Content adaptivity is often implemented as an isolated step, which prevents effective interaction across scales and feature domains. Dynamic multi-scale mechanisms also remain constrained, since their scale selection is usually guided by global statistics and ignores regional heterogeneity. Moreover, frequency and spatial cues are commonly fused in a static manner, leading to an imbalance between global structural enhancement and local texture preservation. To address these issues, we design three complementary modules. We utilize the Adaptive Convolution Unit (ACU) to generate content-aware kernels through local feature clustering, thereby achieving fine-grained adaptation to diverse ground structures. We also develop the Multi-Scale Receptive Field Selection Unit (MSRFU), a module providing flexible scale modeling by selecting informative branches at varying receptive fields. Meanwhile, we incorporate the Frequency–Spatial Attention Unit (FSAU), designed to dynamically fuse spatial representations with frequency information. This effectively strengthens detail reconstruction while minimizing spectral distortion. Specifically, we propose the Hybrid Attention Fusion Network (HAFNet), which employs the Hybrid Attention-Driven Residual Block (HARB) as the fundamental utility to dynamically integrate the above three specialized components. This design enables dynamic content adaptivity, multi-scale responsiveness, and cross-domain feature fusion within a unified framework. Experiments on public benchmarks confirm the effectiveness of each component and demonstrate HAFNet’s state-of-the-art performance. Full article

Promoting the synergistic development of green finance (GF) and green technology innovation (GTI) is crucial for achieving sustainable economic development. Based on the sample data of 30 provinces in China from 2010 to 2023, this study first investigates the theoretical mechanism of interactive coupling and then employs methods including Dagum Gini coefficient, spatial kernel density estimation, spatial correlation analysis, and a GTWR model to explore the spatiotemporal pattern, evolution trend, and driving factors of the coupling coordination between GF and GTI. The findings are as follows: (1) The coupling coordination degree (CCD) is about to transition from the moderate imbalance stage to the near imbalance stage, presenting a distinct spatial pattern of “higher levels and faster development in the east, and lower levels and slower development in the west”. (2) The Gini coefficient of the CCD shows an upward trend, with the degree of imbalance increasing year by year; the main sources of the overall differences follow this order: intra-regional disparity (G_w) > inter-regional disparity (G_b) > transvariation density (G_t). (3) The CCD between GF and GTI exhibits a positive spatial correlation, and the agglomeration degree is constantly increasing; the High-High Cluster areas are mainly concentrated in northern China. (4) Economic development level, financial development level, population scale, and urbanization level drive the coupling coordination between GF and GTI. This study provides new theoretical and empirical evidence for the complex coupling relationship and driving factors of GF and GTI and offers a key scientific basis for the Chinese government to formulate differentiated regional policies, thereby promoting the effective implementation of the green and low-carbon development strategy. Full article

Amid the normalization of flexible employment, labor dispatch, as a form of non-standard employment, has become an important component of China’s precarious labor market (PLM). Based on registration data of labor dispatch firms from 2002 to 2022, this paper analyzes the spatial distribution and evolutionary patterns of China’s PLM, using spatial autocorrelation, kernel density estimation, and Gini coefficient methods. Furthermore, it explores its driving mechanisms through a panel negative binomial regression model. The results show that (i) over the past two decades, China’s PLM has undergone four stages: initiation, acceleration, expansion, and adjustment. (ii) Spatially, it has evolved along the trend of “reinforced clustering with concurrent diffusion,” expanding from first-tier cities in eastern China to second- and third-tier cities in central and western China. (iii) Industrial upgrading, market competition, and the overall level of urban development have significantly promoted the growth of the PLM, while improvements in accessibility, proportion of migrant population, and public service provision have somewhat restrained its expansion. Overall, China’s PLM demonstrates both growth potential and structural vulnerability under institutional constraints and external shocks, offering valuable spatial insights for forging sustainable, high-quality employment and coordinated regional development. Full article

In photovoltaic (PV) power generation, the intermittency and uncertainty caused by meteorological factors pose challenges to grid operations. Accurate PV power prediction is crucial for optimizing power dispatching and balancing supply and demand. This paper proposes a PV power prediction model based on Density Peak Clustering Algorithm (DPCA)–Crested Porcupine Optimizer (CPO)–Random Forest (RF)–Gated Recurrent Unit (GRU)–Kolmogorov–Arnold Network (KAN). First, the DPCA is used to accurately classify weather conditions according to meteorological data such as solar radiation, temperature, and humidity. Then, the CPO algorithm is established to optimize the factor screening characteristic variables of the RF. Subsequently, a hybrid GRU model with a KAN layer is introduced for short-term PV power prediction. The Shapley Additive Explanation (SHAP) method values evaluating feature importance and the impact of causal features. Compared with other contrast models, the DPCA-CPO-RF-KAN-GRU model demonstrates better error reduction capabilities under three weather types, with an average fitting accuracy R² reaching 97%. SHAP analysis indicates that the combined average SHAP value of total solar radiation and direct solar radiation contributes more than 70%. Finally, the Kernel Density Estimation (KDE) is utilized to verify that the KAN-GRU model has high robustness in interval prediction, providing strong technical support for ensuring the stability of the power grid and precise decision-making in the electricity market. Full article

The deep integration of the health industry and the digital economy represents a crucial pathway toward a sustainable and resilient future, as it enhances the competitiveness and promotes the orderly expansion of the health sector. Utilizing provincial panel data of 30 provinces in China from 2011 to 2022, this study employs the entropy method and a coupling coordination model to quantify the coupling coordination degree between these sectors. Kernel density estimation and center of gravity–standard deviational ellipse analysis reveal spatiotemporal evolutionary patterns. Key findings include: ① Significant regional disparities exist in the development levels of both the health industry and the digital economy, with notable intra-regional variations among provinces. ② The coupling and coordination level of the health industry and digital economy development across China and within each region have shown a continuous growth trend. The regional levels are in the order of East > West > Central > Northeast, while the regional growth rates are East > Central > West > Northeast. Moreover, a polarization trend has emerged in the central and western regions. ③ The center of gravity of the spatial coupling coordination degree across the entire territory of China shows a clustering trend of moving towards the southeast. The spatial distribution pattern of the coupling coordination degree is in an east-northwest to west-southeast direction. The eastern and northeastern regions, respectively, show a dispersed and clustered trend of moving towards the southwest, while the central and western regions all show a clustered trend of moving towards the southeast. Based on this, policy suggestions are put forward for the deep integration and coordinated development of the health industry and the digital economy, with the aim of leveraging digital innovation to build a health sector that is socially inclusive, economically viable, and environmentally sustainable in the long term. Full article