Search Results (201)

Short-term passenger flow prediction provides critical data-driven support for optimizing resource allocation, guiding passenger mobility, and enhancing risk response capabilities in urban rail transit systems. To further improve prediction accuracy, this study proposes a hybrid SMA-VMD-Informer-BiLSTM prediction model. Addressing the challenge of error propagation caused by non-stationary components (e.g., noise and abrupt fluctuations) in conventional passenger flow signals, the Variational Mode Decomposition (VMD) method is introduced to decompose raw flow data into multiple intrinsic mode functions (IMFs). A Slime Mould Algorithm (SMA)-based optimization mechanism is designed to adaptively tune VMD parameters, effectively mitigating mode redundancy and information loss. Furthermore, to circumvent error accumulation inherent in serial modeling frameworks, a parallel prediction architecture is developed: the Informer branch captures long-term dependencies through its ProbSparse self-attention mechanism, while the Bidirectional Long Short-Term Memory (BiLSTM) network extracts localized short-term temporal patterns. The outputs of both branches are fused via a fully connected layer, balancing global trend adherence and local fluctuation characterization. Experimental validation using historical entry flow data from Weihouzhuang Station on Xi’an Metro demonstrated the superior performance of the SMA-VMD-Informer-BiLSTM model. Compared to benchmark models (CNN-BiLSTM, CNN-BiGRU, Transformer-LSTM, ARIMA-LSTM), the proposed model achieved reductions of 7.14–53.33% in $f_{mse}$, 3.81–31.14% in $f_{rmse}$, and 8.87–38.08% in $f_{mae}$, alongside a 4.11–5.48% improvement in $R^2$. Cross-station validation across multiple Xi’an Metro hubs further confirmed robust spatial generalizability, with prediction errors bounded within $f_{mse}$: 0.0009–0.01, $f_{rmse}$: 0.0303–0.1, $f_{mae}$: 0.0196–0.0697, and $R^2$: 0.9011–0.9971. Furthermore, the model demonstrated favorable predictive performance when applied to forecasting passenger inflows at multiple stations in Nanjing and Zhengzhou, showcasing its excellent spatial transferability. By integrating multi-level, multi-scale data processing and adaptive feature extraction mechanisms, the proposed model significantly mitigates error accumulation observed in traditional approaches. These findings collectively indicate its potential as a scientific foundation for refined operational decision-making in urban rail transit management, thereby significantly promoting the sustainable development and long-term stable operation of urban rail transit systems. Full article

The global expansion of Korean language education has created an urgent need for scalable, objective, and consistent methods for assessing the writing skills of non-native (L2) learners. Traditional manual grading is resource-intensive and prone to subjectivity, while existing Automated Essay Scoring (AES) systems often struggle with the linguistic nuances of Korean and the specific error patterns of L2 writers. This paper introduces a novel hybrid AES system designed specifically for Korean L2 writing. The system integrates two complementary feature sets: (1) a comprehensive suite of conventional linguistic features capturing lexical diversity, syntactic complexity, and readability to assess writing form and (2) a novel semantic relevance feature that evaluates writing content. This semantic feature is derived by calculating the cosine similarity between a student’s essay and an ideal, high-proficiency reference answer generated by a Large Language Model (LLM). Various machine learning models are trained on the Korean Language Learner Corpus from the National Institute of the Korean Language to predict a holistic score on the 6-level Test of Proficiency in Korean (TOPIK) scale. The proposed hybrid system demonstrates superior performance compared to baseline models that rely on either linguistic or semantic features alone. The integration of the LLM-based semantic feature provides a significant improvement in scoring accuracy, more closely aligning the automated assessment with human expert judgments. By systematically combining measures of linguistic form and semantic content, this hybrid approach provides a more holistic and accurate assessment of Korean L2 writing proficiency. The system represents a practical and effective tool for supporting large-scale language education and assessment, aligning with the need for advanced AI-driven educational technology systems. Full article

Nanofluids are an important technology for enhancing heat transfer in industrial applications by incorporating high thermal conductivity nanoparticles into base fluids. However, they often require higher pumping power and energy consumption. This study employs a two-dimensional (2D) approximation of vortex generators (VGs) in a turbulent trapezoidal channel with nanoparticle concentrations of ${\mathrm{Al}}_2{\mathrm{O}}_3$, ${\mathrm{SiO}}_2$, and ${\mathrm{TiO}}_2$. Simulations are performed using ANSYS Fluent 2021 with the Finite Volume Method (FVM) and the k–$\epsilon$ turbulence model to capture turbulence characteristics, eddy viscosity, and turbulent kinetic energy production. The introduction of vortex generators improves fluid mixing and reduces the thermal boundary layer, resulting in enhanced heat transfer, with a performance evaluation criterion (PEC) of 1.08 for water (baseline case without nanofluids). The single nanofluids further optimize heat transfer, increasing the Nusselt number and pressure drop while balancing thermal performance, reaching a PEC of 1.6 for ${\mathrm{SiO}}_2$ at 3% concentration, representing a 48% improvement over the baseline. A hybrid mixture of 1% ${\mathrm{Al}}_2{\mathrm{O}}_3$ and 2% ${\mathrm{SiO}}_2$ achieves the same PEC of 1.6 as single ${\mathrm{SiO}}_2$ nanoparticles, but with higher heat transfer and lower pressure drop, demonstrating improved thermal performance. Full article

Groundwater level (GWL) prediction in arid regions faces two fundamental challenges in conventional numerical modeling: (i) irreducible parameter uncertainty, which systematically reduces predictive accuracy; (ii) oversimplification of nonlinear process interactions, which leads to error propagation. Although machine learning (ML) methods demonstrate strong nonlinear mapping capabilities, their standalone applications often encounter prediction bias and face the accuracy–generalization trade-off. This study proposes a hybrid TCN–Transformer–LSTM (TTL) model designed to address three key challenges in groundwater prediction: high-frequency fluctuations, medium-range dependencies, and long-term memory effects. The TTL framework integrates TCN layers for short-term features, Transformer blocks to model cross-temporal dependencies, and LSTM to preserve long-term memory, with residual connections facilitating hierarchical feature fusion. The results indicate that (1) at the monthly scale, TTL reduced RMSE by 20.7% (p < 0.01) and increased R² by 0.15 compared with the Groundwater Modeling System (GMS); (2) during abrupt hydrological events, TTL achieved superior performance (R² = 0.96–0.98, MAE < 0.6 m); (3) PCA revealed site-specific responses, corroborating the adaptability and interpretability of TTL; (4) Grad-CAM analysis demonstrated that the model captures physically interpretable attention mechanisms—particularly evapotranspiration and rainfall—thereby providing clear cause–effect explanations and enhancing transparency beyond black-box models. This transferable framework supports groundwater forecasting, risk warning, and practical deployment in arid regions, thereby contributing to sustainable water resource management. Full article

Accurate short-term electricity load forecasting is essential for efficient energy management, grid reliability, and cost optimization. This study presents a comprehensive comparison of five supervised learning models—Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), a hybrid (CNN-LSTM) architecture, and Light Gradient Boosting Machine (LightGBM)—using multivariate data from the Greek electricity market between 2015 and 2024. The dataset incorporates hourly load, temperature, humidity, and holiday indicators. Extensive preprocessing was applied, including K-Nearest Neighbor (KNN) imputation, time-based feature extraction, and normalization. Models were trained using a 70:20:10 train–validation–test split and evaluated with standard performance metrics: MAE, MSE, RMSE, NRMSE, MAPE, and $R^2$. The experimental findings show that LightGBM beat deep learning (DL) models on all evaluation metrics and had the best MAE (69.12 MW), RMSE (101.67 MW), and MAPE (1.20%) and the highest $R^2$ (0.9942) for the test set. It also outperformed models in the literature and operational forecasts conducted in the real world by ENTSO-E. Though LSTM performed well, particularly in long-term dependency capturing, it performed a bit worse in high-variance periods. CNN, GRU, and hybrid models demonstrated moderate results, but they tended to underfit or overfit in some circumstances. These findings highlight the efficacy of LightGBM in structured time-series forecasting tasks, offering a scalable and interpretable alternative to DL models. This study supports its potential for real-world deployment in smart/distribution grid applications and provides valuable insights into the trade-offs between accuracy, complexity, and generalization in load forecasting models. Full article

The intrinsic structural stability of ABO₃ perovskite materials is a pivotal factor determining their efficiency and durability in photovoltaic applications. However, accurately predicting stability, commonly measured by the energy above hull metric, remains challenging due to the complex interplay of compositional, crystallographic, and electronic features. To address this challenge, we propose a streamlined hybrid machine learning framework that combines the sequence modeling capability of Long Short-Term Memory (LSTM) networks with the robustness of Random Forest regressors. A genetic algorithm-based feature selection strategy is incorporated to identify the most relevant descriptors and reduce noise, thereby enhancing both predictive accuracy and interpretability. Comprehensive evaluations on a curated ABO₃ dataset demonstrate strong performance, achieving an $R^2$ of 0.98 on training data and 0.83 on independent test data, with a Mean Absolute Error (MAE) of 8.78 for training and 21.23 for testing, and Root Mean Squared Error (RMSE) values that further confirm predictive reliability. These results validate the effectiveness of the proposed approach in capturing the multifactorial nature of perovskite stability while ensuring robust generalization. This study highlights a practical and reliable pathway for accelerating the discovery and optimization of stable perovskite materials, contributing to the development of more durable next-generation solar technologies. Full article

Natural gas, a key low-emission energy source with significant strategic value in modern energy systems, necessitates accurate forecasting of its market price to ensure effective policy planning and economic stability. This paper proposes an ensemble framework to enhance natural gas price forecasting accuracy across multiple temporal scales (weekly and monthly) by constructing hybrid models and exploring diverse ensemble strategies, while balancing model complexity and computational efficiency. For weekly data, an Autoregressive Integrated Moving Average (ARIMA) model optimized via 5-fold cross-validation captures linear patterns, while the Long Short-Term Memory (LSTM) network captures nonlinear dependencies in the residual component after seasonal and trend decomposition based on LOESS (STL). For monthly data, the superior-performing model (ARIMA or SARIMA) is integrated with LSTM to address seasonality and trend characteristics. To further improve forecasting performance, three diverse ensemble techniques including stacking, bagging, and weighted averaging are individually implemented to synthesize the predictions of the two baseline models. The bagging ensemble method slightly outperforms other models on both weekly and monthly data, achieving MAPE, MAE, RMSE, and $R^2$ values of 9.60%, 0.3865, 0.5780, and 0.8287 for the weekly data, and 11.43%, 0.5302, 0.6944, and 0.7813 for the monthly data, respectively. The accurate forecasting of natural gas prices is critical for energy market stability and the realization of sustainable development goals. Full article

Direct air capture (DAC) has recently gained interest as a carbon dioxide removal (CDR) method to reduce atmospheric CO₂. DAC is mainly studied through standalone separation technologies, especially adsorption and absorption. Hybrid DAC, combining separation technologies, is rarely investigated and is the main topic of this work. This study investigates hybrid DAC using adsorption for pre-concentration up to a few percent or tens of percent depending on the case studied and membrane separation to concentrate the CO₂ stream to high purity (>90%). Adsorption regeneration by temperature swing adsorption (TSA) and vacuum thermal swing adsorption (VTSA) are compared, and VTSA regeneration achieved higher pre-concentration outlet CO₂ purity (15–30%) than TSA regeneration (1–10%). Membrane separation is studied depending on inlet CO₂ purity and outlet-required purity (90 or 95%), which influence the energy requirement and cost of capture. For all cases studied, the cost of capture remained high (>1700 €/tCO₂) with a high energy requirement (>2 MWh_e/tCO₂ and >27 GJ/tCO₂). The adsorption pre-concentration step accounted for the majority (>80%) of the energy requirement and cost of capture, and future work should be focused on preferentially improving adsorption step performance. Full article

From the perspectives of theoretical design and practical application, the existing fault diagnosis methods with the complex identification process owing to manual feature extraction and the insufficient feature extraction for time series data and weak fault signal is not suitable for AC/DC microgrids. Thus, this paper proposes a fault diagnosis method that integrates a convolutional neural network (CNN) with a long short-term memory (LSTM) network and attention mechanisms. The method employs a multi-scale convolution-based weight layer (Weight Layer 1) to extract features of faults from different dimensions, performing feature fusion to enrich the fault characteristics of the AC/DC microgrid. Additionally, a hybrid attention block-based weight layer (Weight Layer 2) is designed to enable the model to adaptively focus on the most significant features, thereby improving the extraction and utilization of critical information, which enhances both classification accuracy and model generalization. By cascading LSTM layers, the model effectively captures temporal dependencies within the features, allowing the model to extract critical information from the temporal evolution of electrical signals, thus enhancing both classification accuracy and robustness. Simulation results indicate that the proposed method achieves a classification accuracy of up to 99.5%, with fault identification accuracy for noisy signals under 10 dB noise interference reaching 92.5%, demonstrating strong noise immunity. Full article

With the development of active magnetic bearings (AMBs) toward higher speeds, understanding high-speed rotor dynamics has become a crucial focus in AMB research. Traditional finite element modeling (FEM) methods, however, are unable to rapidly and comprehensively uncover the complex interplay between controller parameters and dynamic behavior. To address this limitation, a surrogate modeling approach based on a hybrid gated recurrent unit–Kolmogorov–Arnold network (GRU-KAN) is introduced to mathematically capture the effects of coupled control gains on rotor dynamics. To enhance model generalization, a genetic algorithm-driven uniform design sampling strategy is also implemented. Comparative studies against support vector regression and Kriging surrogates indicate a higher coefficient of determination ($R^2=0.9887$) and lower residuals for the proposed approach. Experimental validation across multiple controller parameter combinations shows that the resulting machine learning surrogate predicts the critical speed with a mean absolute error of only 38.51 rpm and a mean absolute percentage error of $1.56\times {10}^{-1}\%$, while requiring merely $1.14\times {10}^{-4}$ s per evaluation—compared to 201 s for traditional FEM. These findings demonstrate the surrogate’s efficiency, accuracy, and comprehensive predictive capabilities, offering an effective method for rapid critical speed estimation in AMB–rotor systems. Full article

In dynamic and open cloud service processes, particularly in distributed networked manufacturing environments, the complex and volatile manufacturing landscape introduces numerous uncertainties and disturbances. This paper addresses the common issue of cloud resource connection interruptions by proposing a path substitution strategy based on alternative service routes. By integrating agent-based simulation and complex network methodologies, a simulation model for evaluating the robustness of cloud manufacturing service systems is developed, enabling dynamic simulation and quantitative decision-making for the proposed robustness enhancement strategies. First, a hybrid modeling approach for cloud manufacturing service systems is proposed to meet the needs of robustness analysis. The specific construction of the hybrid simulation model is achieved using the AnyLogic 8.7.4 simulation software and Java-based secondary development techniques. Second, a complex network model focusing on cloud manufacturing resource entities is further constructed based on the simulation model. By combining the two models, two-dimensional robustness evaluation indicators—comprising performance robustness and structural robustness—are established. Then, four types of edge attack strategies are designed based on the initial topology and recomputed topology. To ensure system operability after edge failures, a path substitution strategy is proposed by introducing redundant routes. Finally, a case study of a cloud manufacturing project is conducted. The results show the following: (1) The proposed robustness evaluation model fully captures complex disturbance scenarios in cloud manufacturing, and the designed simulation experiments support the evaluation and comparative analysis of robustness improvement strategies from both performance and structural robustness dimensions. (2) The path substitution strategy significantly enhances the robustness of cloud manufacturing services, though its effects on performance and structural robustness vary across different disturbance scenarios. Full article

With the continuous acceleration of industrialization, air pollution has become increasingly severe and has, to some extent, contributed to the progression of global climate change. Against this backdrop, accurate temperature forecasting plays a vital role in various fields, including agricultural production, energy scheduling, environmental governance, and public health protection. To improve the accuracy and stability of temperature prediction, this study proposes a hybrid modeling approach that integrates convolutional neural networks (CNNs), Long Short-Term Memory (LSTM) networks, and random forests (RFs). This model fully leverages the strengths of CNNs in extracting local spatial features, the advantages of LSTM in modeling long-term dependencies in time series, and the capabilities of RF in nonlinear modeling and feature selection through ensemble learning. Based on daily temperature, meteorological, and air pollutant observation data from Wuhan during the period 2015–2023, this study conducted multi-scale modeling and seasonal performance evaluations. Pearson correlation analysis and random forest-based feature importance ranking were used to identify two key pollutants (PM_2.5 and O₃) and two critical meteorological variables (air pressure and visibility) that are strongly associated with temperature variation. A CNN-LSTM model was then constructed using the meteorological variables as input to generate preliminary predictions. These predictions were subsequently combined with the concentrations of the selected pollutants to form a new feature set, which was input into the RF model for secondary regression, thereby enhancing the overall model performance. The main findings are as follows: (1) The six major pollutants exhibit clear seasonal distribution patterns, with generally higher concentrations in winter and lower in summer, while O₃ shows the opposite trend. Moreover, the influence of pollutants on temperature demonstrates significant seasonal heterogeneity. (2) The CNN-LSTM-RF hybrid model shows excellent performance in temperature prediction tasks. The predicted values align closely with observed data in the test set, with a low prediction error (RMSE = 0.88, MAE = 0.66) and a high coefficient of determination (R² = 0.99), confirming the model’s accuracy and robustness. (3) In multi-scale forecasting, the model performs well on both daily (short-term) and monthly (mid- to long-term) scales. While daily-scale predictions exhibit higher precision, monthly-scale forecasts effectively capture long-term trends. A paired-sample t-test on annual mean temperature predictions across the two time scales revealed a statistically significant difference at the 95% confidence level (t = −3.5299, p = 0.0242), indicating that time granularity has a notable impact on prediction outcomes and should be carefully selected and optimized based on practical application needs. (4) One-way ANOVA and the non-parametric Kruskal–Wallis test were employed to assess the statistical significance of seasonal differences in daily absolute prediction errors. Results showed significant variation across seasons (ANOVA: F = 2.94, p = 0.032; Kruskal–Wallis: H = 8.82, p = 0.031; both p < 0.05), suggesting that seasonal changes considerably affect the model’s predictive performance. Specifically, the model exhibited the highest RMSE and MAE in spring, indicating poorer fit, whereas performance was best in autumn, with the highest R² value, suggesting a stronger fitting capability. Full article

Automated guided vehicles (AGVs) operating in uneven environments are typically designed with an elevated chassis to enhance obstacle-crossing. In inductive power transfer (IPT) systems for such AGVs, a long transmission distance along with limited installation space for coils leads to a medium distance-to-diameter ratio (DDR) (1 < DDR ≤ 2), which reduces coupling efficiency and degrades misalignment tolerance. To address this issue, this paper proposes a compact dual-receiver IPT system for medium DDR conditions. The system adopts a flat U-shaped solenoid (FUS) coil as both the transmitter and the primary receiver, and a square solenoid (SS) coil as the secondary receiver, forming the FUSS dual-receiver structure. The FUS coil is optimized through finite element analysis to improve coupling, while the SS coil captures vertical flux to compensate for misalignment losses, thereby enhancing misalignment tolerance. A hybrid rectifier integrating a full-bridge and voltage doubler topology is used to suppress output voltage fluctuation, reduce the number of receiver coil turns, and minimize system volume. A 300 W/100 kHz prototype with a coupler size of 183 × 126 × 838 mm³ achieves 83.51% efficiency under medium DDR and a 185 mm air gap. Voltage fluctuation remains within 5% under ±51.4% X-axis and ±51.7% Y-axis misalignment, confirming the stable power delivery and improved misalignment tolerance of the system. Full article

The purpose of this narrative review is to critically appraise recent advances in sports injury rehabilitation—primarily focusing on biopsychosocial (BPS) approaches alongside emerging technological innovations—and identify current gaps and future directions. A literature search was conducted in PubMed, Scopus, and Web of Science for the years 2018–2024. Eligible records were English-language, human studies comprising systematic reviews, clinical trials, and translational investigations on wearable sensors, artificial intelligence (AI), virtual reality (VR), regenerative therapies (platelet-rich plasma [PRP], bone marrow aspirate concentrate [BMAC], stem cells, and prolotherapy), and BPS rehabilitation models; single-patient case reports, editorials, and non-scholarly sources were excluded. The synthesis yielded four themes: (1) BPS implementation remains underutilised owing to a lack of validated tools, variable provider readiness, and system-level barriers; (2) wearables and AI can enhance real-time monitoring and risk stratification but are limited by data heterogeneity, non-standardised pipelines, and sparse external validation; (3) VR/gamification improves engagement and task-specific practice, but evidence is dominated by pilot or laboratory studies with scarce longitudinal follow-up data; and (4) regenerative interventions show mechanistic promise, but conclusions are constrained by methodological variability and regulatory hurdles. Conclusions: BPS perspectives and emerging technologies have genuine potential to improve outcomes, but translation to practice hinges on (1) pragmatic or hybrid effectiveness–implementation trials, (2) standardisation of data and intervention protocols (including core outcome sets and effect-size reporting), and (3) integration of psychological and social assessment into routine pathways supported by provider training and interoperable digital capture. Full article

Cyclic solvent injection (CSI) with CO₂ is a promising non-thermal enhanced oil recovery (EOR) method for heavy oil reservoirs that also supports CO₂ sequestration. However, its effectiveness is limited by short foamy oil flow durations and low CO₂ utilization. This study explores how waterflooding and nanoparticle-assisted flooding can enhance CO₂-CSI performance through experimental and numerical approaches. Three sandpack experiments were conducted: (1) a baseline CO₂-CSI process, (2) a waterflood-assisted CSI process, and (3) a hybrid sequence integrating CSI, waterflooding, and nanoparticle flooding. The results show that waterflooding prior to CSI increased oil recovery from 30.9% to 38.9% under high-pressure conditions and from 26.9% to 28.8% under low pressure, while also extending production duration. When normalized to the oil saturation at the start of CSI, the Effective Recovery Index (ERI) increased significantly, confirming improved per-unit recovery efficiency, while nanoparticle flooding further contributed an additional 5.9% recovery by stabilizing CO₂ foam. The CO₂-CSI process achieved a maximum CO₂ sequestration rate of up to 5.8% per cycle, which exhibited a positive correlation with oil production. Numerical simulation achieved satisfactory history matching and captured key trends such as changes in relative permeability and gas saturation. Overall, the integrated CSI strategy achieved a total oil recovery factor of approximately 70% and improved CO₂ sequestration efficiency. This work demonstrates that combining waterflooding and nanoparticle injection with CO₂-CSI can enhance both oil recovery and CO₂ sequestration, offering a framework for optimizing low-carbon EOR processes. Full article