Search Results (3,316)

Knowledge Graph Reasoning (KGR) aims to deduce missing or novel knowledge by learning structured information and semantic relationships within Knowledge Graphs (KGs). Despite significant advances achieved by deep neural networks in recent years, existing models typically extract non-linear representations from explicit features in a relatively simplistic manner and fail to fully exploit semantic heterogeneity of relation types and entity co-occurrence frequencies. Consequently, these models struggle to capture critical predictive cues embedded in various entities and relations. To address these limitations, this paper proposes a relation aware spectral decoupling attention network for KGR (RASD). First, a spectral decoupling attention network module projects joint embeddings of entities and relations into the frequency domain, extracting features across different frequency bands and adaptively allocating attention at the global level to model frequency specific information. Next, a relation-aware learning module employs relation aware filters and an augmentation mechanism to preserve distinct relational properties and suppress redundant features, thereby enhancing representation of heterogeneous relations. Experimental results demonstrate that RASD achieves significant and consistent improvements over multiple leading baseline models on link prediction tasks across five public benchmark datasets. Full article

Accurate maize yield forecasting under climate uncertainty remains a critical challenge for global food security, yet existing studies predominantly rely on single-model frameworks, limiting generalizability and actionable insights. This study selected three regions, specifically Dali, Lijiang, and Zhaotong, and collected data on 12 agronomic traits of 114 varieties, along with eight sets of meteorological data, covering the period from 2019 to 2023. We employed three machine learning models: Random Forest (RF), Support Vector Machine (SVM), and XGBoost. The results revealed a strong correlation between yield and multiple agronomic traits, particularly grain weight per spike (GWPS) and hundred-kernel weight (HKW). Notably, the XGBoost model emerged as the top performer across all three regions. The model achieved the lowest RMSE (0.22–191.13) and a good R² (0.98–0.99), demonstrating exceptional predictive accuracy for yield-related traits. The comparative analysis revealed that XGBoost exhibited superior accuracy and stability compared to RF and SVM. Through feature importance analysis, four critical determinants of yield were identified: GWPS, shelling percentage (SP), growth period (GP), and plant height (PH). Furthermore, partial dependence plots (PDPs) provided deeper insights into the nonlinear interactive effects between GWPS, SP, GP, PH, and yield, offering a more comprehensive understanding of their complex relationships. This study presents an innovative, data-driven methodology designed to accurately forecast corn yield across diverse locations. This approach offers valuable scientific insights that can significantly enhance precision agricultural practices by enabling the precise tailoring of fertilizer usage and irrigation strategies. The results highlight the importance of integrating agronomic and meteorological data in yield forecasting, paving the way for development of agricultural decision-support systems in the context of future climate change scenarios. This study presents an innovative, data-driven methodology designed to accurately forecast corn yield across diverse locations. This approach offers valuable scientific insights that can significantly enhance precision agricultural practices by enabling the precise tailoring of fertilizer usage and irrigation strategies. Full article

Today’s increasingly brittle, anxious, nonlinear, incomprehensible world of work calls for a socially and emotionally competent workforce. However, there is a clear gap in higher education settings regarding the assessment and promotion of students’ social and emotional competence (SEC). Our study aims to address the pressing need to evaluate and develop higher education students’ SEC by providing a tool to assess these skills, enabling researchers and practitioners to intervene and actively promote them. A sample of 767 higher education students (62.8% female, M = 22.88 years, SD = 7.30) enrolled in the study. Structural, discriminant and concurrent criterion validity, and reliability of the measure were assessed. A multiple hierarchical regression analysis tested the relation of SEC and well-being. Confirmatory Factor Analysis supported the hypothesized factorial structures. Coefficient omegas indicated adequate internal consistency. The results also supported the measure’s discriminant and criterion validities in relation to external measures. Multi-group invariance across gender and academic fields was attained. We found evidence of the predictive role of intrapersonal skills on students’ personal and academic well-being. This study bridges a gap in research and practice by introducing a psychometrically sound yet parsimonious instrument for assessing higher education students’ SEC. It also highlights the supportive role of SEC in promoting students’ well-being. Full article

It is particularly important to ensure the safety of engineering structures, such as aerospace vehicles and wind turbines, most of which are made of composite materials. A sudden failure of the structure may happen following the accumulation of structural damage. Since they are sensitive to tiny damage and can propagate through engineering structures over a long distance, Lamb waves have been widely explored to develop highly efficient damage detection theories and methodologies. During propagation, affected by the mechanical properties of the structure, a large amount of information and features related to structural states can be reflected and transmitted by Lamb waves, including the occurrence and extent of structural damage. By analyzing the effect of damage acting on Lamb waves, a multi-scale wavelet transform analysis is adopted to extract multi-feature parameters in the time–frequency domain of the acquired signals. With the help of the nonlinear mapping ability of a neural network, a damage assessment model for composite structures is constructed to realize the evaluation of typical structural damage at different levels. The results of an experiment conducted on an epoxy–glass-fiber-reinforced plate show that the extracted multi-feature parameters of Lamb waves in the time–frequency domain are sensitive to the accumulated typical damage. The damage assessment model can properly evaluate the damage degree with satisfactory accuracy. Full article

The Geostationary Interferometric Infrared Sounder (GIIRS) onboard the Fengyun-4B satellite plays a critical role in numerical weather prediction and extreme weather monitoring. To meet the requirements of quantitative remote sensing and high-precision operational applications for radiometric calibration accuracy, this study, based on pre-launch calibration experiments, conducts a novel modeling analysis of the coupling between stray radiation at the input side and the system’s nonlinearity, and proposes a correction method for nonlinear coupling errors. This method explicitly models and physically traces the calibration residuals caused by stray radiation introduced via non-nominal optical paths under the effect of system nonlinearity, which are related to the radiance of the observed target. Experimental results show that, within the brightness temperature range of 200–320 K, the calibration bias is reduced from approximately 0.7 to 0.3–0.4 K, with good consistency and stability observed across channels and pixels. Full article

As a typical cold region, Northeast China is characterized by its unique climate, hydrological conditions, and land systems, which collectively shape the diversity and complexity of regional ecosystem services (ESs). This review systematically examines research on ESs in Northeast China from 1997 to 2025, with particular emphasis on recent advances in service classification and spatiotemporal patterns, trade-offs and synergies among ESs, the identification of driving mechanisms, regulatory pathways, and policy effectiveness. The findings reveal obvious spatial heterogeneity and distinct stage-wise changing patterns in ESs across the region, with particularly pronounced trade-offs between food production and regulating services. The primary driving factors are concentrated in natural and human activities dimensions, whereas region-specific variables and policy-related drivers remain underexplored. Current research predominantly employs methods such as correlation analysis and geographically weighted regression; however, the capacity to uncover causal mechanisms and nonlinear interactions remains limited. Future research should strengthen the simulation of ecological processes in cold regions, improve the balance between ES supply and demand, improve policy scenario assessments, and develop dynamic feedback mechanisms. Compared with previous studies focusing on single services or regions, this review provides a multidimensional perspective by synthesizing multiple ES categories, integrating spatiotemporal comparative analysis, and incorporating modeling strategies specific to cold-region dynamics. These efforts will help shift ES research beyond static description toward more systematic regulation and management, providing both theoretical support and practical guidance for sustainable development and ecological governance in Northeast China. Full article

Rapid urbanisation has exacerbated habitat fragmentation and degradation, necessitating urgent improvements to urban habitat quality. However, most current studies lack an analysis of spatial differences in local ecological quality, particularly a systematic exploration of how different urban spatial characteristics drive such differences. Based on this, we use Shanghai as an example, employing the InVEST model to assess habitat quality, and utilise CatBoost machine learning models and the SHAP model to reveal the specific spatial distribution characteristics of the habitat quality spatial differences from a morphological perspective, as well as its response to changes in urban spatial form factors. The results indicate that (1) urban habitat quality exhibits significant spatial differences, with quality differences persisting even within regions of the same habitat grade, demonstrating complex spatial characteristics; (2) density-related indicators such as building density and population density have a significant negative impact on the habitat quality spatial difference value, while configuration-related indicators such as the water ratio and Normalised Difference Vegetation Index have a significant positive effect, with Population Density contributing the most among all variables (20.74%); and (3) the variables exhibit significant nonlinearity and threshold effects. For example, when building density exceeds 0.05, the positive impact becomes a negative impact. The interactions between variables further reveal the multi-dimensional coupling mechanisms underlying habitat quality performance. This study contributes to a deeper understanding of the spatial differences of urban habitat quality, providing scientific support for urban ecological zoning management, the optimised allocation of green space resources, and differentiated spatial governance while offering methodological and decision-making references for the construction of high-quality ecological cities. Full article

This paper introduces a speed-sensorless dual-field-oriented control (DFOC) strategy for induction motors (IMs). DFOC combines the advantages or rotor- and stator-field orientation to significantly reduce the parameter sensitivity of the control regarding the generation of the converter control variable. A simplified structure is also proposed, using only two regulators for the flux and speed control, eliminating the two current regulators. Related to sensorless control, the classical adaptation mechanism within an MRAS (model reference adaptive system) observer is replaced with artificial intelligence (AI)-based approaches. Specifically, artificial neural networks (ANNs) and recurrent neural networks (RNNs) are employed for rotor speed estimation. They offer significant advantages in managing complex and nonlinear systems, providing enhanced flexibility and adaptability compared to traditional MRAS methods. The effectiveness of the proposed sensorless control scheme is validated through both simulation and real-time implementation. The paper focuses on the ANN and RNN architectures, as deep learning models, in terms of the reliability and accuracy of rotor speed estimation under various operating conditions. Full article

In this paper, we present the notion of fuzzy $\mathcal{R}-F-$contractive mappings and provide some fuzzy fixed point results in the setting of fuzzy metric spaces, which are endowed with binary relations. Furthermore, we apply our newly established fuzzy fixed point results to solve certain boundary value problems for nonlinear fractional differential equations involving the Caputo fractional derivatives. Also, we provide some examples to show the utility of our new results. Full article

The explosive growth in marine economy has the capacity to not only revolutionize the marine economic development model but also produce a transition from a marine powerhouse to a marine superpower. China’s 11 coastal provinces and municipalities, capitalizing on their geographic advantages and distinct resource endowments, have emerged as principal locations propelling maritime economic growth. In this report, we employ a green finance (GF) framework and analyze panel data from 11 coastal provinces and municipalities in China as obtained over the period from 2010 to 2021. Such an analysis has the capacity to elucidate the driving mechanisms and extent of GF’s influence on the high-quality growth of the marine sector (EQUS). Our results reveal that GF substantially promotes the EQUS, a finding that is consist with that from several robust tests involved with evaluating this relationship. When analyzing the mediating impact of GF, it appears that GF may indirectly enhance the quality and efficiency of the maritime economy by stimulating technical innovations. Results from threshold effects research indicate that the promotional impact of GF is limited by the extent of maritime technical innovation, with levels above a certain threshold markedly increasing the influence of GF. When evaluating the role of heterogeneity, the impact of green money on promotion demonstrates regional and temporal diversity, exhibiting nonlinear traits across various locations and phases of development. In areas with robust economic foundations and developed maritime sectors, the marginal impacts of green financing are significantly enhanced. Based upon these findings, it is recommended that any courses which advance the EQUS should be promoted. Specifically, the augmentation of marine-related innovation skills, cultivation of green technology innovation (TEC), and the optimization of innovative resource distribution represents critical measures to achieve this goal. Full article

The precise forecasting of renewable energy production and usage is essential for the stability, efficiency, and sustainability of contemporary power systems. This requirement is especially urgent in South Africa, a nation currently grappling with considerable energy issues, such as recurrent load shedding, outdated coal-fired power plants, and an increasing electricity demand. As the country moves towards a more renewable-focused energy portfolio, the capacity to anticipate future energy requirements is crucial for effective planning, operational stability, and grid resilience. This study introduces a hybrid approach that combines deep learning and machine learning techniques, specifically integrating long short-term memory (LSTM) neural networks with extreme gradient boosting (XGBoost) to provide more accurate and detailed forecasts of energy demand. LSTM networks are particularly effective in capturing long-term temporal dependencies in sequential data, such as patterns of energy usage. At the same time, XGBoost delivers high-performance gradient-boosted decision trees that can manage non-linear relationships and noise present in extensive datasets. The proposed hybrid LSTM-XGBoost model was trained and assessed using high-resolution data on energy consumption and weather conditions gathered from a coastal municipality in KwaZulu-Natal, South Africa, a country that exemplifies the convergence of renewable energy potential and challenges related to energy reliability. The preprocessing steps, including normalization, feature selection, and sequence modeling, were implemented to enhance the input data for both models. The performance of the model was thoroughly evaluated using standard statistical metrics, specifically the mean absolute error (MAE), the root mean squared error (RMSE), and the coefficient of determination (R²). The hybrid model achieved an MAE of merely 192.59 kWh and an R² of approximately 0.71, significantly surpassing the performance of the individual LSTM and XGBoost models. These findings highlight the enhanced predictive capabilities of the hybrid model in capturing both temporal trends and feature interactions in energy consumption behavior. Full article

This study employs the improved modified extended tanh method (IMETM) to derive exact analytical solutions of a higher-order nonlinear Schrödinger (HNLS) model, incorporating $\beta$-fractional derivatives in both time and space. Unlike classical methods such as the inverse scattering transform or Hirota’s bilinear technique, which are typically limited to integrable systems and integer-order operators, the IMETM offers enhanced flexibility for handling fractional models and higher-order nonlinearities. It enables the systematic construction of diverse solution types—including Weierstrass elliptic, exponential, Jacobi elliptic, and bright solitons—within a unified algebraic framework. The inclusion of fractional derivatives introduces richer dynamical behavior, capturing nonlocal dispersion and temporal memory effects. Visual simulations illustrate how fractional parameters $\alpha$ (space) and $\beta$ (time) affect wave structures, revealing their impact on solution shape and stability. The proposed framework provides new insights into fractional NLS dynamics with potential applications in optical fiber communications, nonlinear optics, and related physical systems. Full article

Background: Early identification of visual disorders in children is essential to prevent long-term visual impairment and support academic development. Despite the recognized importance of visual screenings, no universal consensus exists on which visual parameters or threshold values should be used, particularly for measuring visual acuity (VA) in pediatric populations. Objectives: This study aimed to develop age-related percentile norms for VA using LEA symbol charts. Methods: A sample of Italian schoolchildren aged 5 to 15 years (n = 1510) participated in the study. Data were collected retrospectively from school-based vision screenings conducted across 12 schools in the Lombardy and Piedmont regions from 2010 to 2019. Monocular and binocular VA were measured at 3 m using a standardized LEA symbol chart, and values were scored letter-by-letter on a LogMAR scale. Smoothed percentile curves were derived using Box–Cox, Cole, and Green distribution modeling and regression analysis. Results: The results showed a non-linear improvement in VA with age. Compared to prior studies, LEA symbols yielded slightly lower VA scores, reinforcing the need for chart-specific norms. The 50th percentile VA improved from approximately +0.07 LogMAR at age 6 to about −0.09 LogMAR at age 15. Conclusions: These findings highlight the importance of age-specific, chart-specific, and statistically robust reference data for VA screening in children. The derived percentile tables offer a more sensitive tool than fixed cut-offs for identifying visual anomalies and tailoring clinical interventions. This work contributes to standardizing pediatric VA screening practices and improving early detection of visual deficits. Full article

The coordinated development of tourism and industrialization is essential for achieving sustainable and inclusive growth in the tourism sector, as well as for ensuring long-term regional economic sustainability. This study is motivated by the observation that land is a key factor influencing the coordination between tourism and industrialization, yet the specific role of land use remains underexplored. Therefore, the objective of this paper is to investigate the nonlinear relationship and underlying mechanisms through which tourism development impacts industrialization, with a particular focus on land transfers. To achieve this, the study employs an empirical approach using multi-source data—including data on China’s A-level scenic areas and land transfers—combined with an econometric method. The results indicate a U-shaped relationship between both the quantity and quality of tourism resources and the growth of industrial enterprises, as well as an inverted U-shaped relationship between the concentration of tourism resources and industrial development. The research finds that tourism development influences industrialization through two primary land-related mechanisms: the factor competition effect and the resource conservation effect. This study also investigates the potential for synergistic development between the tourism and industrial sectors, providing valuable insights for the sustainable economic advancement of land-based tourism and industrialization. Full article

Background: This study aimed to examine changes in heart rate variability (HRV) across three match-related time points (pre-match, during the match, and post-match) and to explore whether these physiological responses differed between winners and losers in competitive padel. Methods: Twelve matches were analyzed, involving 11 high-level Finnish padel players ranked within the national top 24. HRV was recorded before, during, and immediately after each match, with each measurement lasting a minimum of five min. Time-domain (e.g., SDNN, RMSSD, pNN50), frequency-domain (e.g., LF, HF), and non-linear (e.g., SD1, SD2) HRV metrics were extracted for analysis. All matches took place in Tampere, Finland, under controlled conditions. Results: Results revealed significant intra-match fluctuations in HRV across all domains. Moreover, losing players exhibited consistently higher relative heart rate during the match, suggesting greater physiological strain. Conclusions: This study contributes novel evidence on the dynamic nature of autonomic responses in padel and supports the integration of HRV monitoring in performance and recovery management protocols for high-level athletes. Full article