Search Results (5,071)

The growing mismatch between ecosystem service (ES) supply and demand underscores the importance of thoroughly understanding their spatiotemporal patterns and key drivers to promote ecological civilization and sustainable development at the regional level in China. This study investigates six key ES indicators across mainland China—habitat quality (HQ), carbon sequestration (CS), water yield (WY), sediment delivery ratio (SDR), food production (FP), and nutrient delivery ratio (NDR)—by integrating a suite of analytical approaches. These include a spatiotemporal analysis of trade-offs and synergies in supply, demand, and their ratios; self-organizing maps (SOM) for bundle identification; and interpretable machine learning models. While prior research studies have typically examined ES at a single spatial scale, focusing on supply-side bundles or associated drivers, they have often overlooked demand dynamics and cross-scale interactions. In contrast, this study integrates SOM and SHAP-based machine learning into a dual-scale framework (grid and city levels), enabling more precise identification of scale-dependent drivers and a deeper understanding of the complex interrelationships between ES supply, demand, and their spatial mismatches. The results reveal pronounced spatiotemporal heterogeneity in ES supply and demand at both grid and city scales. Overall, the supply services display a spatial pattern of higher values in the east and south, and lower values in the west and north. High-value areas for multiple demand services are concentrated in the densely populated eastern regions. The grid scale better captures spatial clustering, enhancing the detection of trade-offs and synergies. For instance, the correlation between HQ and NDR supply increased from 0.62 (grid scale) to 0.92 (city scale), while the correlation between HQ and SDR demand decreased from −0.03 to −0.58, indicating that upscaling may highlight broader synergistic or conflicting trends missed at finer resolutions. In the spatiotemporal interaction network of supply–demand ratios, CS, WY, FP, and NDR persistently show low values (below –0.5) in western and northern regions, indicating ongoing mismatches and uneven development. Driver analysis demonstrates scale-dependent effects: at the grid scale, HQ and FP are predominantly influenced by socioeconomic factors, SDR and WY by ecological variables, and CS and NDR by climatic conditions. At the city level, socioeconomic drivers dominate most services. Based on these findings, nine distinct supply–demand bundles were identified at both scales. The largest bundle at the grid scale (B3) occupies 29.1% of the study area, while the largest city-scale bundle (B8) covers 26.5%. This study deepens the understanding of trade-offs, synergies, and driving mechanisms of ecosystem services across multiple spatial scales; reveals scale-sensitive patterns of spatial mismatch; and provides scientific support for tiered ecological compensation, integrated regional planning, and sustainable development strategies. Full article

Deep learning (DL) continues to play a pivotal role in a wide range of intelligent systems, including autonomous machines, smart surveillance, industrial automation, and portable healthcare technologies. These applications often demand low-latency inference and efficient resource utilization, especially when deployed on embedded or edge devices with limited computational capacity. As DL models become increasingly complex, selecting the right inference framework is essential to meeting performance and deployment goals. In this work, we conduct a comprehensive comparison of five widely adopted inference frameworks: PyTorch, ONNX Runtime, TensorRT, Apache TVM, and JAX. All experiments are performed on the NVIDIA Jetson AGX Orin platform, a high-performance computing solution tailored for edge artificial intelligence workloads. The evaluation considers several key performance metrics, including inference accuracy, inference time, throughput, memory usage, and power consumption. Each framework is tested using a wide range of convolutional and transformer models and analyzed in terms of deployment complexity, runtime efficiency, and hardware utilization. Our results show that certain frameworks offer superior inference speed and throughput, while others provide advantages in flexibility, portability, or ease of integration. We also observe meaningful differences in how each framework manages system memory and power under various load conditions. This study offers practical insights into the trade-offs associated with deploying DL inference on resource-constrained hardware. Full article

With continuous advancements in semiconductor technology, mastering efficient designs of high-quality and advanced chips has become an important part of science and technology education. Chip performances will determine the futures of various aspects of societies. However, novice students often encounter difficulties in learning digital chip designs using Verilog programming, a common hardware design language. An efficient self-study system for supporting them that can offer various exercise problems, such that any answer is marked automatically, is in strong demand. In this paper, we design and implement a web-based Verilog programming learning assistant system (VPLAS), based on our previous works on software programming. Using a heuristic and guided learning method, VPLAS leads students to learn the basic circuit syntax step by step, until they acquire high-quality digital integrated circuit design abilities through self-study. For evaluation, we assign the proposal to 50 undergraduate students at the National Taipei University of Technology, Taiwan, who are taking the introductory chip-design course, and confirm that their learning outcomes using VPLAS together are far better than those obtained when following a traditional method. In our final statistics, students achieved an average initial accuracy rate of over 70% on their first attempts at answering questions after learning through our website’s tutorials. With the help of the system’s instant automated grading and rapid feedback, their average accuracy rate eventually exceeded 99%. This clearly demonstrates that our system effectively enables students to independently master Verilog circuit knowledge through self-directed learning. Full article

Background: As population aging accelerates, the demand for professionals in older adult care continues to rise. Traditional teaching methods often fail to improve students’ willingness to serve older adults or foster teamwork. This study evaluated the effects of integrating a flipped classroom with project-based learning (PBL) and a hands-on clinical practicum into a health internship course. Methods: A mixed-methods design was adopted. Participants included 88 interdisciplinary university students enrolled in an 18-week, two-credit geriatric health internship course offered at a university in central Taiwan from August 2023 to July 2024. The course combined flipped classroom and PBL approaches, as well as clinical practicum activities. Data on willingness to serve older adults, teamwork skills, and learning outcomes were collected using structured questionnaires and analyzed with paired t-tests. Results: Significant improvements were found in willingness (from 68.93 to 73.15), teamwork (67.33 to 71.45), and learning outcomes (89.84 to 102.14) (p = 0.001). Qualitative findings further revealed increased empathy, improved teamwork, and enhanced ability to apply knowledge in real-world contexts. Conclusions: A teaching approach that integrates a flipped classroom, PBL, and a clinical practicum can effectively enhance students’ competencies in older adult care. Future research should explore long-term and cross-cultural impacts. Full article

This study proposes an optimized approach to address the high computational demands and significant GPU memory consumption commonly associated with Transformer-based models. Building upon the HAT framework, a shallow feature extraction module is enhanced to improve local feature representation, thereby achieving a better balance between computational efficiency and model performance. Furthermore, inspired by self-supervised learning (SSL) techniques and incorporating shift operations, the proposed method effectively reduces both the number of parameters and the overall computational load. The resulting ISR-SHA model is trained and evaluated on the DF2K dataset, achieving approximately a 30% reduction in FLOPs and parameter count compared to the original HAT model, with only marginal declines in PSNR (0.02) and SSIM (0.0006). Experimental results confirm that ISR-SHA outperforms most existing super-resolution models in terms of performance while significantly enhancing computational efficiency without compromising output quality. Full article

Background: Brazilian Jiu-Jitsu (BJJ) is a physically demanding sport associated with a notable risk of musculoskeletal injuries. Understanding injury patterns, rehabilitation approaches, and psychological readiness to return to sport (RTS) is essential for prevention and management strategies. This study aimed to investigate injury characteristics among Italian BJJ athletes, assess their rehabilitation processes and psychological recovery, and identify key risk factors such as belt level, body mass index (BMI), and training load. Methods: A cross-sectional survey was conducted among members of the Italian BJJ community, including amateur and competitive athletes. A total of 360 participants completed a 36-item online questionnaire. Data collected included injury history, rehabilitation strategies, RTS timelines, and responses to the Injury-Psychological Readiness to Return to Sport (I-PRRS) scale. A Random Forest machine learning algorithm was used to identify and rank potential injury risk factors. Results: Of the 360 respondents, 331 (92%) reported at least one injury, predominantly occurring during training sessions. The knee was the most frequently injured joint, and the action “attempting to pass guard” was the most reported mechanism. Most athletes (65%) returned to training within one month. BMI and age emerged as the most significant predictors of injury risk. Psychological readiness scores indicated moderate confidence, with the lowest levels associated with playing without pain. Conclusions: Injuries in BJJ are common, particularly affecting the knee. Psychological readiness, especially confidence in training without pain, plays a critical role in RTS outcomes. Machine learning models may aid in identifying individual risk factors and guiding injury prevention strategies. Full article

The development in coastal engineering and maritime transport demands accurate wave height prediction. In this study, hybrid deep learning models, including CNN-LSTM, CNN-BiLSTM, CNN-GRU, and CNN-BiGRU, are employed to develop regional multivariate wave prediction models that incorporate multiple features, such as wave height, wind stress, water depth, pressure, and sea surface temperature (SST), for the entire Bay of Bengal area. Sensitivity analysis is performed to evaluate the accuracy using statistical metrics, such as the correlation coefficient, RMSE, and MAE. The findings demonstrate that regional multivariate models offer satisfactory results for the entire Bay of Bengal region. The multivariate model performs better compared to the univariate model as the forecast horizon increases. Performance assessment of each environmental factor, employing the integrated gradient method, reveals that sea surface temperature has the most significant influence, while wind stress is the least dominant factor in the wave prediction model. Among the tested models, the CNN-BiGRU has superior performance with a correlation of 0.9872, an RMSE of 0.1547, and an MAE of 0.1005 for the 3 h prediction and is proposed as the optimal model. This study contributes to assessing the contribution of each environmental feature and improving the accuracy of regional wave prediction. Full article

In alignment with global educational trends, Australia has adopted a pluralistic approach to initial teacher education (ITE), encompassing traditional university-based programs, employment-integrated models and vocational training routes. This diversification of pathways has emerged as a strategic response to persistent workforce challenges, including chronic shortages, uneven distribution of qualified educators, and limited demographic diversity within the profession. Rather than supplanting conventional ITE models, these alternative pathways serve as complementary options, broadening access and enhancing system responsiveness to evolving societal and educational needs. The rise in non-traditional routes represents a deliberate response to the well-documented global teacher shortage, frequently examined in comparative educational research. Central to their design is a restructuring of traditional program elements, particularly duration and delivery methods, to facilitate more flexible and context-sensitive forms of teacher preparation. Such approaches often create opportunities for individuals who may be excluded from conventional pathways due to socioeconomic constraints, geographic isolation, or non-linear career trajectories. Significantly, the diversity introduced by alternative entry candidates has the potential to enrich school learning environments. These educators often bring a wide range of prior experiences, disciplinary knowledge, and cultural perspectives, contributing to more inclusive and representative teaching practices. The implications for student learning are substantial, particularly in disadvantaged communities where culturally and professionally diverse teachers may enhance engagement and academic outcomes. From a policy perspective, the development of flexible, multifaceted teacher education pathways constitutes a critical component of a sustainable workforce strategy. As demand for qualified teachers intensifies, especially in STEM disciplines and in rural, regional and remote areas, the role of alternative pathways is likely to become increasingly pivotal in achieving broader goals of equity, quality and innovation in teacher preparation. Full article

Metaheuristics are powerful optimization techniques that are well-suited for addressing complex combinatorial problems across diverse scientific and industrial domains. However, their application to computationally expensive problems remains challenging due to the high cost and significant number of fitness evaluations required during the search process. Surrogate modeling has recently emerged as an effective solution to reduce these computational demands by approximating the true, time-intensive fitness function. While surrogate-assisted metaheuristics have gained attention in recent years, their application to complex scheduling problems such as the Permutation Flowshop Scheduling Problem (PFSP) under learning, deterioration, and maintenance effects remains largely unexplored. To the best of our knowledge, this study is the first to investigate the integration of surrogate modeling within the artificial bee colony (ABC) framework specifically tailored to this problem context. We develop and evaluate two distinct strategies for integrating surrogate modeling into the optimization process, leveraging the ABC algorithm. The first strategy uses a Kriging model to dynamically guide the selection of the most effective search operator at each stage of the employed bee phase. The second strategy introduces three variants, each incorporating a Q-learning-based operator in the selection mechanism and a different evolution control mechanism, where the Kriging model is employed to approximate the fitness of generated offspring. Through extensive computational experiments and performance analysis, using Taillard’s well-known standard benchmarks, we assess solution quality, convergence, and the number of exact fitness evaluations, demonstrating that these approaches achieve competitive results. Full article

Modern manufacturing demands real-time, scalable coordination that legacy manufacturing management systems cannot provide. Digital transformation encompasses the entire manufacturing infrastructure, which can be represented by digital twins for facilitating efficient monitoring, prediction, and optimization of factory operations. A Federated Digital Twin (FDT) emerges by combining heterogeneous digital twins, enabling real-time collaboration, data sharing, and collective decision-making. However, deploying FDTs introduces new concurrency control challenges, such as priority inversion and synchronization failures, which can potentially cause process delays, missed deadlines, and reduced customer satisfaction. Traditional concurrency control approaches in the computing domain, due to their reliance on static priority assignments and centralized control, are inadequate for managing dynamic, real-time conflicts effectively in real production lines. To address these challenges, this study proposes a novel concurrency control framework combining Deep Reinforcement Learning with the Priority Ceiling Protocol. Using SimPy-based discrete-event simulations, which accurately model the asynchronous nature of FDT interactions, the proposed approach adaptively optimizes resource allocation and effectively mitigates priority inversion. The results demonstrate that against the rule-based PCP controller, our hybrid DRLCC enhances completion time maximum of 24.27% to a minimum of 1.51%, urgent-job delay maximum of 6.65% and a minimum of 2.18%, while preserving lower-priority inversions. Full article

Understanding and forecasting energy consumption patterns is crucial for improving energy efficiency and human well-being, especially in diverse infrastructures like Spain. This research addresses a significant gap in energy demand forecasting across three building types by comparing six machine learning algorithms: Artificial Neural Networks, Random Forest, XGBoost, Radial Basis Function Network, Autoencoder, and Decision Trees. The primary aim is to identify the most effective model for predicting energy consumption based on historical data, contributing to the relationship between energy systems and urban well-being. The study emphasizes challenges in energy use and advocates for sustainable management practices. By forecasting energy demand over the next three years using linear regression, it provides actionable insights for energy providers, enhancing resilience in urban environments impacted by climate change. The findings deepen our understanding of energy dynamics across various building types and promote a sustainable energy future. Stakeholders will receive targeted recommendations for aligning energy production with consumption trends while meeting environmental responsibilities. Model performance is rigorously evaluated using metrics like Squared Mean Root Percentage Error (RMSPE) and Coefficient of Determination (R²), ensuring robust analysis. Training times for models in the LUCIA building ranged from 2 to 19 s, with the Decision Tree model showing the shortest times, highlighting the need to balance computational efficiency with model performance. Full article

Membrane fouling remains a major challenge in full-scale membrane bioreactor (MBR) systems, reducing operational efficiency and increasing maintenance needs. This study introduces a predictive and analytic framework for membrane fouling by integrating artificial intelligence (AI)-driven feature engineering and explainable AI (XAI) using real-world data from an MBR treating food processing wastewater. The framework refines the target parameter to specific flux (flux/transmembrane pressure (TMP)), incorporates chemical oxygen demand (COD) removal efficiency to reflect biological performance, and applies a moving average function to capture temporal fouling dynamics. Among tested models, CatBoost achieved the highest predictive accuracy (R² = 0.8374), outperforming traditional statistical and other machine learning models. XAI analysis identified the food-to-microorganism (F/M) ratio and mixed liquor suspended solids (MLSSs) as the most influential variables affecting fouling. This robust and interpretable approach enables proactive fouling prediction and supports informed decision making in practical MBR operations, even with limited data. The methodology establishes a foundation for future integration with real-time monitoring and adaptive control, contributing to more sustainable and efficient membrane-based wastewater treatment operations. However, this study is based on data from a single full-scale MBR treating food processing wastewater and lacks severe fouling or cleaning events, so further validation with diverse datasets is needed to confirm broader applicability. Full article

This review investigates the application of Artificial Intelligence (AI), deep learning (DL), and the Internet of Things (IoT) in water resource management, focusing on distribution optimization, demand prediction, and water quality enhancement. The study synthesizes findings from 2015 to 2024, encompassing experimental and applied research published in English or French in recognized scientific outlets. By analyzing the prevalent algorithms, IoT technologies, and their impacts, this systematic review highlights research gaps and proposes directions for future work. The results show significant advancements in predictive analytics and real-time monitoring through AI and the IoT. However, challenges remain in scalability, interdisciplinary integration, and contextual adaptation. Full article

The growing demand for agile and reliable Unmanned Aerial Vehicles (UAVs) has spurred the advancement of advanced control strategies capable of ensuring stability and precision under nonlinear and uncertain flight conditions. This work addresses the challenge of accurately tracking UAV position by proposing a neural-network-based approach designed to replicate the behavior of classical control systems. A complete nonlinear model of the quadcopter was derived and linearized around a hovering point to design a traditional proportional derivative (PD) controller, which served as a baseline for training a nonlinear autoregressive exogenous (NARX) artificial neural network. The NARX model, selected for its feedback structure and ability to capture temporal dynamics, was trained to emulate the control signals of the PD controller under varied reference trajectories, including step, sinusoidal, and triangular inputs. The trained networks demonstrated performance comparable to the PD controller, particularly in the vertical axis, where the NARX model achieved a minimal Mean Squared Error (MSE) of $7.78\times {10}^{-5}$ and an $R^2$ value of 0.9852. These results confirm that the NARX neural network, trained via supervised learning to emulate a PD controller, can replicate and even improve classical control strategies in nonlinear scenarios, thereby enhancing robustness against dynamic changes and modeling uncertainties. This research contributes a scalable approach for integrating neural models into UAV control systems, offering a promising path toward adaptive and autonomous flight control architectures that maintain stability and accuracy in complex environments. Full article

With the increasing integration of renewable energy and smart technologies in residential energy systems, proactive household energy management (HEM) have become critical for reducing costs, enhancing grid stability, and achieving sustainability goals. This study proposes a ultra-short-term forecasting-driven proactive energy consumption optimization strategy that integrates advanced forecasting models with multi-objective scheduling algorithms. By leveraging deep learning techniques like Graph Attention Network (GAT) architectures, the system predicts ultra-short-term household load profiles with high accuracy, addressing the volatility of residential energy use. Then, based on the predicted data, a comprehensive consideration of electricity costs, user comfort, carbon emission pricing, and grid load balance indicators is undertaken. This study proposes an enhanced mixed-integer optimization algorithm to collaboratively optimize multiple objective functions, thereby refining appliance scheduling, energy storage utilization, and grid interaction. Case studies demonstrate that integrating photovoltaic (PV) power generation forecasting and load forecasting models into a home energy management system, and adjusting the original power usage schedule based on predicted PV output and water heater demand, can effectively reduce electricity costs and carbon emissions without compromising user engagement in optimization. This approach helps promote energy-saving and low-carbon electricity consumption habits among users. Full article