Search Results (1,067)

The spectral variation hypothesis (SVH) posits that the complexity of spectral information in remote sensing imagery can serve as a proxy for regional biodiversity. However, the relationship between spectral diversity (SD) and biodiversity differs for different environmental conditions. Previous SVH studies often overlooked these differences. We utilized species data from field surveys in Inner Mongolia and drone-derived multispectral imagery to establish a quantitative relationship between SD and biodiversity. A geographically weighted regression (GWR) model was used to describe the SD–biodiversity relationship and map the biodiversity indices in different experimental areas in Inner Mongolia, China. Spatial autocorrelation analysis revealed that both SD and biodiversity indices exhibited strong and statistically significant spatial autocorrelation in their distribution patterns. Among all spectral diversity indices, the convex hull area exhibited the best model fit with the Margalef richness index (Margalef), the coefficient of variation showed the strongest predictive performance for species richness (Richness), and the convex hull volume provided the highest explanatory power for Shannon diversity (Shannon). Predictions for Shannon achieved the lowest relative root mean square error (RRMSE = 0.17), indicating the highest predictive accuracy, whereas Richness exhibited systematic underestimation with a higher RRMSE (0.23). Compared to the commonly used linear regression model in SVH studies, the GWR model exhibited a 4.7- to 26.5-fold improvement in goodness-of-fit. Despite the relatively low R² value (≤0.59), the model yields biodiversity predictions that are broadly aligned with field observations. Our approach explicitly considers the spatial heterogeneity of the SD–biodiversity relationship. The GWR model had significantly higher fitting accuracy than the linear regression model, indicating its potential for remote sensing-based biodiversity assessments. Full article

As economically important sympatric species in the Northwest Pacific, the Japanese sardine (Sardinops melanostictus) and Chub mackerel (Scomber japonicus) exhibit significant biological interactions. Understanding the impact of interspecies competition on their habitat dynamics can provide crucial insights for the sustainable development and management of these interconnected species resources. This study utilizes fisheries data of S. melanostictus and S. japonicus from the Northwest Pacific, collected from June to November between 2017 and 2020. We integrated various environmental parameters, including temperature at different depths (0, 50, 100, 150, and 200 m), eddy kinetic energy (EKE), sea surface height (SSH), chlorophyll-a concentration (Chl-a), and the oceanic Niño index (ONI), to construct interspecific competition species distribution model (icSDM) for both species. We validated these models by overlaying the predicted habitats with fisheries data from 2021 and performing cross-validation to assess the models’ reliability. Furthermore, we conducted correlation analyses of the habitats of these two species to evaluate the impact of interspecies relationships on their habitat dynamics. The results indicate that, compared to single-species habitat models, the interspecific competition species distribution model (icSDM) for these two species exhibit a significantly higher explanatory power, with R² values increasing by up to 0.29; interspecific competition significantly influences the habitat dynamics of S. melanostictus and S. japonicus, strengthening the correlation between their habitat changes. This relationship exhibits a positive correlation at specific stages, with the highest correlations observed in June, July, and October, at 0.81, 0.80, and 0.88, respectively; interspecific competition also demonstrates stage-specific differences in its impact on the habitat dynamics of S. melanostictus and S. japonicus, with the most pronounced differences occurring in August and November. Compared to S. melanostictus, interspecific competition is more beneficial for the expansion of the optimal habitat (HIS ≥ 0.6) for S. japonicus and, to some extent, inhibits the habitat expansion of S. melanostictus. The variation in migratory routes and predatory interactions (with larger individuals of S. japonicus preying on smaller individuals of S. melanostictus) likely constitutes the primary factors contributing to these observed differences. Full article

The formation mechanism of Virtual Reality (VR) Immersive Experience (VRIE) is notably complex; this study aimed to dynamically decode its underlying drivers by innovatively integrating Flow Theory and Privacy Calculus Theory, focusing on Perceptual-Interactive Fidelity (PIF), Consumer Willingness to Immerse in Technology (CWTI), and the applicability of Loss Aversion Theory. To achieve this, we analyzed approximately 30,000 user reviews from Amazon using Latent Semantic Analysis (LSA) and regression analysis. The findings reveal that user attention’s impact on VRIE is non-linear, suggesting an optimal threshold, and confirm PIF as a central influencing mechanism; furthermore, CWTI significantly moderates users’ privacy calculus, thereby affecting VRIE, while Loss Aversion Theory showed limited explanatory power in the VR context. These results provide a deeper understanding of VR user behavior, offering significant theoretical guidance and practical implications for future VR system design, particularly in strategically balancing user cognition, PIF, privacy concerns, and individual willingness. Full article

Land urbanization enables a thorough perspective to explore the decoupling of land use environmental efficiency (LUEE) and energy use, thereby supporting the shift into low-carbon land use by emphasizing energy conservation and reducing carbon emissions. This paper first calculates LUEE from 2011 to 2021 by using the EBM-DEA model in China. The geographical detector model is used to examine the driving factors of land use environmental efficiency. The results show the following: (1) China’s LUEE is high in general but shows a clear pattern of spatial differentiation internally, with the highest values in the eastern region represented by Beijing, Jiangsu, and Zhejiang, while the central and western regions show lower LUEE because of their irrational industrial structure and lagging green development. (2) Energy consumption, economic development, industrial upgrading, population size, and urban expansion are the driving factors. Their explanatory power for the spatial stratification heterogeneity of land use environmental impacts varies. (3) Urban expansion has the greatest impact on the spatial differentiation of land use environmental effects, while energy consumption also shows significant explanatory strength. In contrast, economic development and population size exhibit relatively weaker explanatory effects. (4) The interaction of the two driving factors has a greater impact on LUEE than their individual effects, and the interaction is a two-factor enhancement. Finally, we make targeted recommendations to help improve land use environmental efficiency. Full article

This study is the first to systematically integrate supervised machine learning (decision tree) and association rule mining techniques to analyze accident data from the Taipei Metro system, conducting a large-scale data-driven investigation into both passenger injury and train malfunction events. The research demonstrates strong novelty and practical contributions. In the passenger injury analysis, a dataset of 3331 cases was examined, from which two highly explanatory rules were extracted: (i) elderly passengers (aged > 61) involved in station incidents are more likely to suffer moderate to severe injuries; and (ii) younger passengers (aged ≤ 61) involved in escalator incidents during off-peak hours are also at higher risk of severe injury. This is the first study to quantitatively reveal the interactive effect of age and time of use on injury severity. In the train malfunction analysis, 1157 incidents with delays exceeding five minutes were analyzed. The study identified high-risk condition combinations—such as those involving rolling stock, power supply, communication, and signaling systems—associated with specific seasons and time periods (e.g., a lift value of 4.0 for power system failures during clear mornings from 06:00–12:00, and 3.27 for communication failures during summer evenings from 18:00–24:00). These findings were further cross-validated with maintenance records to uncover underlying causes, including brake system failures, cable aging, and automatic train operation (ATO) module malfunctions. Targeted preventive maintenance recommendations were proposed. Additionally, the study highlighted existing gaps in the completeness and consistency of maintenance records, recommending improvements in documentation standards and data auditing mechanisms. Overall, this research presents a new paradigm for intelligent metro system maintenance and safety prediction, offering substantial potential for broader adoption and practical application. Full article

E-waste, a form of solid waste, contains many recyclable metals, but improper disposal can make it very harmful. Therefore, the recycling of e-waste is very important, and the willingness of residents to participate is crucial in e-waste recycling. Taking Jiangsu Province, China as an example, we used the theory of reasoned action (TRA) to construct a research model to investigate the factors influencing residents’ willingness to participate in e-waste recycling. The paper introduces impression management motivation and further reveals the application of the Hawthorne effect in e-waste recycling. The paper also introduces the awareness of benefits, which encompasses personal economic benefits, physical health benefits, and environmental benefits, with physical health benefits being ignored by most of the previous literature. In addition, knowledge and convenience are also introduced in this paper. A total of 400 valid responses were used to test the hypotheses of the structural equation model. It was found that all factors positively influenced residents’ willingness to engage in e-waste recycling. Attitude has a mediating role in the effects of convenience, knowledge, and awareness of benefits on willingness, and subjective norms have a mediating role in the effects of impression management motivation on willingness. The model explains 82.9% of the variance in residents’ willingness to recycle e-waste, surpassing the original TRA model’s explanatory power and confirming the strength of the extended framework. The study provides valuable policy implications for the government to promote e-waste recycling. Full article

Background: Patients with primary angle-closure disease (PACD), those with no history of acute angle-closure glaucoma or laser iridotomy, rarely present with prominent corneal endothelial cell density (CECD) loss. To identify factors associated with decreased CECD in PACD, anterior segment parameters were compared in patients with PACD and normal CECD and patients with PACD and decreased CECD, using anterior segment optical coherence tomography (AS-OCT). Patients and Methods: Ten patients with PACD and CECD of less than 1500/mm² without a history of cataract surgery, acute angle-closure glaucoma, or prior laser glaucoma procedures were identified at the Kyorin Eye Center from January 2018 to July 2023. Patients with an obvious corneal guttata or apparent corneal edema were also excluded. Seventeen patients with PACD and normal CECD (normal CECD group) were used as the control. Simultaneous biometry of all anterior segment structures, including the cornea, anterior chamber, and iris, were assessed using a swept-source AS-OCT system. Results: Corneal curvature radius was significantly larger in the decreased CECD group compared with the corneal refractive power in the normal CECD group (p = 0.022, Mann–Whitney test). However, no significant differences were detected in other anterior segment morphology parameters. Multiple regression analysis with CECD as the dependent variable revealed that a large corneal curvature radius was a significant explanatory variable associated with corneal endothelial loss. Conclusions: Flattened corneal curvature may be a risk factor for corneal endothelial loss in patients with PACD. Full article

Background: The global increase in type 2 diabetes mellitus (T2DM) cases necessitates the need for early detection of metabolic changes. This study investigated variations in liver enzymes, renal markers, electrolytes, and lipid profiles among T2DM patients stratified by hemoglobin A1c (HbA1c) categories to support early identification and better management of diabetes-related complications. Methods: A retrospective observational study at King Khalid University Hospital (KKUH), Riyadh, included 621 adult patients diagnosed with T2DM categorized into four HbA1c groups: normal (<5.7%), prediabetes (5.7–6.4%), controlled diabetes (6.5–7.9%), and uncontrolled diabetes (≥8.0%). Biochemical parameters included the liver profile: alkaline phosphatase (ALP) and bilirubin, renal profile: creatinine, blood urea nitrogen (BUN), glucose, sodium, and chloride, and lipid profile: cholesterol, high-density lipoprotein (HDL), low-density lipoprotein (LDL), and triglycerides. Regression models identified predictors of ALP, cholesterol, and LDL. Results: ALP was higher in uncontrolled diabetes (89.0 U/L, Q1–Q3: 106.3–72.0) than in the prediabetes group (75.0 U/L, Q1–Q3: 96.8–62.3). Sodium and chloride were lower in uncontrolled diabetes (Na: 138.3 mmol/L, Q1–Q3: 140.3–136.4; Cl: 101.1 mmol/L, Q1–Q3: 102.9–99.4) compared to the normal group (Na: 139.5 mmol/L, Q1–Q3: 142.4–136.9; Cl: 103.5 mmol/L, Q1–Q3: 106.1–101.7). LDL was lower in uncontrolled diabetes (2.1 mmol/L, Q1–Q3: 2.8–1.7) than in the normal group (2.8 mmol/L, Q1–Q3: 3.7–2.2), while triglycerides were higher in patients with uncontrolled diabetes compared to the normal group (1.45 mmol/L, Q1–Q3: 2.02–1.11 vs. 1.26 mmol/L, Q1–Q3: 1.44–0.94). Regression models showed low explanatory power (R² = 2.1–7.3%), with weight, age, and sex as significant predictors of select biochemical markers. Conclusions: The study observed biochemical variations across HbA1c categories in T2DM patients, likely reflecting insulin resistance. Monitoring these markers in conjunction with HbA1c can enhance early detection and improve the management of complications. Full article

This study employs k-means clustering to analyze local organizations responsible for land improvement in Greece, identifying four distinct groups with consistent geographic patterns but divergent financial and operational characteristics. By integrating unsupervised machine learning with spatial analysis, the research offers a novel perspective on irrigation water pricing and cost recovery. The findings reveal that organizations located on islands, despite high water costs due to limited rainfall and geographic isolation, tend to achieve relatively strong financial performance, indicating the presence of adaptive mechanisms that could inform broader policy strategies. In contrast, organizations managing extensive irrigable land or large volumes of water frequently show poor cost recovery, challenging assumptions about economies of scale and revealing inefficiencies in pricing or governance structures. The spatial coherence of the clusters underscores the importance of geography in shaping institutional outcomes, reaffirming that environmental and locational factors can offer greater explanatory power than algorithmic models alone. This highlights the need for water management policies that move beyond uniform national strategies and instead reflect regional climatic, infrastructural, and economic variability. The study suggests several policy directions, including targeted infrastructure investment, locally calibrated water pricing models, and performance benchmarking based on successful organizational practices. Although grounded in the Greek context, the methodology and insights are transferable to other European and Mediterranean regions facing similar water governance challenges. Recognizing the limitations of the current analysis—including gaps in data consistency and the exclusion of socio-environmental indicators—the study advocates for future research incorporating broader variables and international comparative approaches. Ultimately, it supports a hybrid policy framework that combines data-driven analysis with spatial intelligence to promote sustainability, equity, and financial viability in agricultural water management. Full article

This paper introduces the concept of degenerative affordances to explain how social media can unintentionally destabilise family-run influencer businesses. While affordance theory typically highlights the enabling features of technology, the researchers shift the focus to its unintended, risk-laden consequences, particularly within family enterprises where professional and personal identities are deeply entangled. Drawing on platform capitalism, family business research, and intersectional feminist critiques, the researchers develop a theoretical model to examine how social media affordances contribute to role confusion, privacy breaches, and trust erosion. Using a mixed-methods design, the researchers combine narrative interviews (n = 20) with partial least squares structural equation modelling (PLS-SEM) on survey data (n = 320) from family-based influencers. This study’s findings reveal a high explanatory power (R² = 0.934) for how digital platforms mediate entrepreneurial legitimacy through interpersonal trust and role dynamics. Notably, trust emerges as a key mediating mechanism linking social media engagement to perceptions of business legitimacy. This paper advances three core contributions: (1) introducing degenerative affordance as a novel extension of affordance theory; (2) unpacking how digitally mediated role confusion and privacy breaches function as internal threats to legitimacy in family businesses; and (3) problematising the epistemic assumptions embedded in entrepreneurial legitimacy itself. This study’s results call for a rethinking of how digital platforms, family roles, and entrepreneurial identities co-constitute each other under the pressures of visibility, intimacy, and algorithmic governance. The paper concludes with implications for influencer labour regulation, platform accountability, and the ethics of digital family entrepreneurship. Full article

Background/Objectives: Smartphone addiction (SA) and gaming addiction (GA) have become risk factors for individuals of all ages in recent years. Especially during adolescence, it has become very difficult for parents to control this situation. Physical activity and the effective use of free time are the most important factors in eliminating such addictions. This study aimed to test a new machine learning method by combining routine regression analysis with the gradient-boosting machine (GBM) and random forest (RF) methods to analyze the relationship between SA and GA with leisure time management (LTM) and the enjoyment of physical activity (EPA) among adolescents. Methods: This study presents the results obtained using our developed GBM + RF hybrid model, which incorporates LTM and EPA scores as inputs for predicting SA and GA, following the preprocessing of data collected from 1107 high school students aged 15–19 years. The results were compared with those obtained using routine regression results and the lasso, ElasticNet, RF, GBM, AdaBoost, bagging, support vector regression (SVR), K-nearest neighbors (KNN), multi-layer perceptron (MLP), and light gradient-boosting machine (LightGBM) models. In the GBM + RF model, probability scores obtained from GBM were used as input to RF to produce final predictions. The performance of the models was evaluated using the R², mean absolute error (MAE), and mean squared error (MSE) metrics. Results: Classical regression analyses revealed a significant negative relationship between SA scores and both LTM and EPA scores. Specifically, as LTM and EPA scores increased, SA scores decreased significantly. In contrast, GA scores showed a significant negative relationship only with LTM scores, whereas EPA was not a significant determinant of GA. In contrast to the relatively low explanatory power of classical regression models, ML algorithms have demonstrated significantly higher prediction accuracy. The best performance for SA prediction was achieved using the Hybrid GBM + RF model (MAE = 0.095, MSE = 0.010, R² = 0.9299), whereas the SVR model showed the weakest performance (MAE = 0.310, MSE = 0.096, R² = 0.8615). Similarly, the Hybrid GBM + RF model also showed the highest performance for GA prediction (MAE = 0.090, MSE = 0.014, R² = 0.9699). Conclusions: These findings demonstrate that classical regression analyses have limited explanatory power in capturing complex relationships between variables, whereas ML algorithms, particularly our GBM + RF hybrid model, offer more robust and accurate modeling capabilities for multifactorial cognitive and performance-related predictions. Full article

Under the dual pressures of global climate warming and rapid urbanization, the Yangtze River Basin, as the world’s largest urban agglomeration, is facing intensifying thermal environmental stress. Although river ecosystems demonstrate significant thermal regulation functions, their spatial thresholds of cooling effects and multiscale driving mechanisms have remained to be systematically elucidated. This study retrieved land surface temperature (LST) using the split window algorithm and quantitatively analyzed the changes in the river cold island effect and its driving mechanisms in the Yangtze River Basin by combining multi-ring buffer analysis and the optimal parameter-based geographical detector model. The results showed that (1) forest land is the main land use type in the Yangtze River Basin, with built-up land having the largest area increase. Affected by natural, socioeconomic, and meteorological factors, the summer temperatures displayed a spatial pattern of “higher in the east than the west, warmer in the south than the north”. (2) There are significant differences in the cooling magnitude among different land types. Forest land has the maximum daytime cooling distance (589 m), while construction land has the strongest cooling magnitude (1.72 °C). The cooling effect magnitude is most pronounced in upstream areas of the basin, reaching 0.96 °C. At the urban agglomeration scale, the Chengdu–Chongqing urban agglomeration shows the greatest temperature reduction of 0.90 °C. (3) Elevation consistently demonstrates the highest explanatory power for LST spatial variability. Interaction analysis shows that the interaction between socioeconomic factors and elevation is generally the strongest. This study provides important spatial decision support for formulating basin-scale ecological thermal regulation strategies based on refined spatial layout optimization, hierarchical management and control, and a “natural–societal” dual-dimensional synergistic regulation system. Full article

Exploring the action mechanisms and enhancement pathways of the resilience of agricultural product green supply chains is conducive to strengthening the system’s risk resistance capacity and providing decision support for achieving the “dual carbon” goals. Based on theories such as dynamic capability theory and complex adaptive systems, this paper constructs a resilience framework covering the three stages of “steady-state maintenance–dynamic adjustment–continuous evolution” from both single and multiple perspectives. Combined with 768 units of multi-agent questionnaire data, it adopts Structural Equation Modeling (SEM) and fuzzy-set Qualitative Comparative Analysis (fsQCA) to analyze the influencing factors of resilience and reveal the nonlinear mechanisms of resilience formation. Secondly, by integrating configurational analysis with machine learning, it innovatively constructs a resilience level prediction model based on fsQCA-XGBoost. The research findings are as follows: (1) fsQCA identifies a total of four high-resilience pathways, verifying the core proposition of “multiple conjunctural causality” in complex adaptive system theory; (2) compared with single algorithms such as Random Forest, Decision Tree, AdaBoost, ExtraTrees, and XGBoost, the fsQCA-XGBoost prediction method proposed in this paper achieves an optimization of 66% and over 150% in recall rate and positive sample identification, respectively. It reduces false negative risk omission by 50% and improves the ability to capture high-risk samples by three times, which verifies the feasibility and applicability of the fsQCA-XGBoost prediction method in the field of resilience prediction for agricultural product green supply chains. This research provides a risk prevention and control paradigm with both theoretical explanatory power and practical operability for agricultural product green supply chains, and promotes collaborative realization of the “carbon reduction–supply stability–efficiency improvement” goals, transforming them from policy vision to operational reality. Full article

Under the impetus of digital rural development and the rapid advancement of smart logistics, intelligent terminal delivery technologies are gradually expanding into rural areas. This study employs a three-phase mixed research approach to systematically investigate the factors influencing and mechanisms underlying rural residents’ willingness to adopt smart logistics in Hebei Province. In the first phase, grounded theory is employed to identify seven key perceived factors: perceived usefulness, perceived ease of use, sensitivity to collective evaluation, cultural conservatism, infrastructure quality, facilitating conditions, and technological trust. In the second phase, integrating the TAM and the UTAUT, this study incorporates context-specific variables and conducts empirical analysis using SEM and the bootstrap method on 451 valid questionnaire responses. The results indicate that all factors except infrastructure quality significantly influence adoption willingness, with cultural conservatism exerting a negative effect. In the third phase, fsQCA is applied to identify eight configurations that lead to high adoption willingness, further supplementing and enriching the explanatory power of the SEM results. This research expands the theoretical understanding of smart logistics technology adoption mechanisms in rural areas and offers practical guidance for the promotion and application of related technologies. Full article

The accurate early-stage estimation of environmental load (EL) and construction cost (CC) in road infrastructure projects remains a significant challenge, constrained by limited data and the complexity of construction activities. To address this, our study proposes a machine learning-based predictive framework utilizing artificial neural networks (ANNs) and deep neural networks (DNNs), enhanced by autoencoder-driven feature selection. A structured dataset of 150 completed national road projects in South Korea was compiled, covering both planning and design phases. The database focused on 19 high-impact sub-work types to reduce noise and improve prediction precision. A hybrid imputation approach—combining mean substitution with random forest regression—was applied to handle 4.47% missing data in the design-phase inputs, reducing variance by up to 5% and improving data stability. Dimensionality reduction via autoencoder retained 16 core variables, preserving 97% of explanatory power while minimizing redundancy. ANN models benefited from cross-validation and hyperparameter tuning, achieving consistent performance across training and validation sets without overfitting (MSE = 0.06, RMSE = 0.24). The optimal ANN yielded average error rates of 29.8% for EL and 21.0% for CC at the design stage. DNN models, with their deeper architectures and dropout regularization, further improved performance—achieving 27.1% (EL) and 17.0% (CC) average error rates at the planning stage and 24.0% (EL) and 14.6% (CC) at the design stage. These results met all predefined accuracy thresholds, underscoring the DNN’s advantage in handling complex, high-variance data while the ANN excelled in structured cost prediction. Overall, the synergy between deep learning and autoencoder-based feature selection offers a scalable and data-informed approach for enhancing early-stage environmental and economic assessments in road infrastructure planning—supporting more sustainable and efficient project management. Full article