Search Results (19,814)

The application of machine learning (ML) methods enables the modeling of sheet metal friction phenomena based on experimental data, allowing for the prediction of the coefficient of friction (CoF) under various operating conditions. The aim of this article is to compare the predictive capability of a wide range of ML algorithms trained on the results of the strip drawing test. The variable parameters in the strip drawing test were sheet orientation, load, sample orientation relative to the sheet rolling direction, and the drawing quality of the low-carbon steel sheet metal. Based on the coefficient of determination (R²) and the root mean squared error (RMSE), it was determined that the best predictive performance was achieved by a trilayer neural network (R² = 0.986, RMSE = 0.0025). It was found that the CoF decreased with increasing countersample surface roughness and load. Meanwhile, the orientation of strip samples relative to the sheet rolling direction had a statistically insignificant effect on the CoF. Based on SHapley Additive exPlanations (SHAP) values, it was shown that the average roughness of the countersamples and the load had the most significant influence on the friction coefficient. This was also confirmed using the F-test and permutation importance analysis of the friction process parameters. Full article

Pedestrian trajectory prediction remains a challenging task, particularly in long-tail scenarios where goal distributions are sparse and inter-agent behaviors are uncertain. In this work, we propose to disentangle the trajectory prediction task into two complementary components: interaction modeling and intention modeling. For interaction modeling, we introduce an adaptive meta-strategy that proactively extracts latent and rare-yet-critical interaction patterns often overlooked by conventional trajectory-only approaches. For intention modeling, we propose Continuous Waypoint Slot-Driven Prototypical Contrastive Learning (PCL). It adapts prototype learning to the multi-modal reality where conventional PCL fails to model diverse and continuous goal distributions. Capitalizing on the complementary strengths of both components, we orchestrate a unified frequency-based fusion module that seamlessly integrates interaction and intention modeling, yielding enhanced overall prediction accuracy. In particular, our method is model-agnostic and can be seamlessly incorporated into a wide range of existing prediction frameworks. Extensive experiments on several datasets demonstrate that our approach not only achieves consistent performance gains in standard settings, but also significantly alleviates degradation on hard or long-tail trajectory samples. Full article

Underwater acoustic coatings are widely used to suppress low-frequency noise radiation and sonar reflection in underwater vehicles. In this study, an underwater acoustic coating model consisting of viscoelastic rubber layers and micro-perforated panel (MPP) structures is investigated, with particular emphasis on the low-frequency sound absorption mechanism and predictive modeling. Based on an improved transfer function method, a novel Micro-Perforated Panel Acoustic Coating Layer (MPPACL) model is developed to describe the coupled acoustic behavior of multilayer coatings under underwater conditions. The low-frequency sound absorption performance is primarily governed by the viscoelastic characteristics of the rubber layer, including material damping and complex modulus, while the incorporation of the MPP further enhances absorption through resonance effects. To efficiently explore the relationship between structural parameters and acoustic response, an ensemble learning-based deep neural network (ELDNN) is constructed using analytically generated data, enabling both forward prediction of sound absorption performance and inverse prediction of structural design parameters. The results show that the frequency prediction accuracy of the IDNN model is 3.7 times that of the DNN model. Furthermore, the proposed MPPACL model has achieved a significantly enhanced sound absorption effect within the frequency range of 50 to 2000 hertz. This effect has also been further verified through underwater experiments. The proposed framework provides an efficient and reliable approach for the design and optimization of underwater acoustic coatings. Full article

Laser wire directed energy deposition (LWDED) has garnered significant attention for the fabrication of large metallic components. However, the complex coupling effects among its process parameters pose challenges for porosity control. Optimizing parameter combinations to effectively minimize porosity is therefore critical to the broader adoption of this technology. In this study, systematic experiments and modeling were conducted to optimize the LWDED process parameters and predict porosity. First, single-factor and orthogonal experiments were performed to evaluate the individual effects of laser power, scanning speed, wire feeding speed, and air pressure on porosity. Subsequently, range analysis and analysis of variance were employed to determine the influence of each parameter and the significance of their interactions. Four machine learning models—SVR, RF, GPR, and XGBoost—were then trained and compared. Among them, the SVR model exhibited the best predictive performance, achieving an R² of 0.8960, an RMSE of 0.19, and an MAE of 0.15, outperforming the other three models. Based on this, the SVR model was further utilized to establish the mapping between process parameters and porosity. Contour maps and three-dimensional surface plots were generated to visualize porosity variation patterns under interacting parameters. Validation experiments showed that the maximum relative error between model predictions and experimental measurements was 0.514%, with an average error of 0.251%. This study provides a reliable reference for selecting low-porosity parameter combinations in the LWDED fabrication of 5356 aluminum alloy components. Full article

Accurate short-range precipitation prediction plays a crucial role in daily life and disaster mitigation. However, the existing methods often suffer from inefficient large-scale feature extraction, severe redundant information interference, and insufficient attention to the problem of imbalanced data distributions, leading to unsatisfactory performance. To address these issues, in this paper, we first propose a novel spatiotemporal module called Group Large Kernel Convolution (GLKC) and develop a short-range precipitation forecasting model based on it, GLKC-Net, using multiple meteorological variables. Specifically, we use decomposed large-kernel convolution to enhance the ability to understand large-scale atmospheric processes. Meanwhile, we introduce the group convolution and channel shuffle operator to control the fusion of channel-wise information, enabling efficient information exchange and reducing redundancy in the channel dimension with multiple variables. Furthermore, we treat the causes of poor model performance for extreme precipitation events with an imbalanced data distribution perspective and design a Multi-threshold Adaptive Loss function (MTA Loss). This function strengthens the model’s focus on high-threshold precipitation events that are inherently difficult to forecast, aiming to improve model performance for extreme events. Finally, forecasting experiments for validation were conducted over southwestern China using ERA5-Land and CMPAS datasets. The results demonstrate that our proposed method outperforms several existing approaches in terms of forecasting accuracy. Full article

This study presents an integrated experimental and modeling framework to investigate human–robot collision dynamics involving a collaborative manipulator (KUKA LBR iiwa 14 R820). A dedicated impact test prototype was developed to reproduce controlled contact scenarios between the robot and human body analogues under various dynamic conditions. The experimental setup enables the acquisition of synchronized force, velocities, and displacement signals during contact events. These data are used to calibrate and validate a set of contact models, ranging from classical formulations such as Hertz and Hunt–Crossley to more recent supervised machine learning models. The proposed methodology allows a quantitative assessment of model accuracy and physical consistency in replicating real collision phenomena. Furthermore, the effective mass of the robot along its kinematic chain is estimated to compute impact energy and predict the interaction severity according to ISO 10218-1/2:2025 safety limits. The results highlight the trade-off between model complexity and predictive capability, offering alternative guidelines for collision severity evaluation in collaborative robotics applications. Full article

Soil moisture prediction is essential for precision irrigation in water-limited agricultural systems. This study presents a deep learning-driven irrigation framework for winter wheat, integrating a novel Informer–UNet model with a Comprehensive Irrigation Index for adaptive water management. The Informer–UNet combines ProbSparse self-attention mechanisms with UNet’s multi-scale feature fusion, enabling simultaneous prediction of soil moisture at 27 monitoring points across three depths, 10, 30, and 50 cm, while quantifying prediction uncertainty through Monte Carlo Dropout. A Comprehensive Irrigation Index incorporating moisture deviation, spatial variance, and confidence interval width was developed, with weights optimized via genetic algorithm. Field experiments were conducted in Chengdu, China, over two winter wheat growing seasons. The Informer–UNet achieved superior prediction accuracy, R² greater than 0.98, RMSE less than 0.65, compared to LSTM, Transformer, and standard Informer models, with the fastest convergence and lowest validation loss. The proposed DeepIndexIrr strategy maintained soil moisture within the target range, 55% to 75%, for over 81% of the irrigation period, reducing water consumption by 38.2% compared to fixed-threshold control and 19.2% compared to expert manual scheduling. These results demonstrate that integrating spatially distributed deep learning predictions with uncertainty-informed decision rules offers a promising approach for sustainable precision irrigation. Full article

Drawing-based social deduction games require artificial intelligence (AI) agents to infer semantic information from incomplete and evolving visual inputs under asymmetric information conditions. In this study, we address the problem of recognizing drawing targets from partial sketch sequences toward constructing an AI player for Drawing Werewolf, a collaborative drawing game derived from the Werewolf (Mafia) genre. Using stroke-based representations from the “Quick, Draw!” dataset, we formulate incremental sketch classification as a sequence modeling task and compare a unidirectional Long Short-Term Memory (UniLSTM) model with a Transformer-based model under realistic online inference constraints. Experiments were conducted on 44 animal classes, evaluating classification accuracy at different drawing stages ranging from one stroke to completed sketches. The results demonstrate that both models improve as additional strokes are observed; however, the Transformer consistently outperforms UniLSTM across all stroke counts. The performance gap is particularly pronounced in early-stage prediction, where sketches are highly incomplete and ambiguous. Class-wise analyses further reveal that the advantage of self-attention depends on visual characteristics and drawing progression. These findings indicate that self-attention mechanisms are well suited for modeling partial sketch sequences and provide valuable insights for designing AI players capable of real-time inference in drawing-based social deduction games. Full article

The grapevine (Vitis vinifera L.) is one of the most economically valuable horticultural crops worldwide and is cultivated across a wide range of agroclimatic regions. The objective of this study was to develop a predictive model to estimate the yield of the cultivar Treixadura as a function of meteorological, phenological, aerobiological, and phytopathological variables. The study was conducted in a vineyard located within the Ribeiro Designation of Origin (Spain) over 21 consecutive growing seasons. During the period from 2004 to 2023, grapevine yield exhibited pronounced interannual variability, with the lowest yield recorded in 2018 and the highest in 2023. Correlation analysis showed that grapevine yield was significantly and positively associated with temperature, airborne pollen and the Plasmopara viticola pathogen, and negatively with rainfall and the Botrytis pathogen. Yield was predicted using a model that included rainfall in the first ten days of April, airborne pollen concentration, and Plasmopara viticola from the third ten-days of April as explanatory variables. This model accounted for approximately 70% of the observed variability in yield. The achieved predictive performance enables the anticipation of harvest outcomes several months in advance, thereby supporting more effective viticultural planning. Furthermore, the results highlight the importance of disease control in vineyards, as pathogen incidence not only reduces yield directly but may also compromise the accuracy of yield prediction models. Full article

Within a spatial-economics framework, this paper extends a general-equilibrium model to examine how high-speed rail (HSR) openings reduce migration costs and thereby alleviate regional factor misallocation. The model predicts that improved connectivity lowers labor mobility frictions, facilitates cross-regional reallocation of productive factors, and reduces misallocation. Using a panel of China’s prefecture-level cities from 2006 to 2016 and a difference-in-differences design, we estimate the causal effects of HSR on the misallocation of labor and capital. The results show that HSR openings significantly improve both labor and capital allocation, and the findings remain robust to a range of endogeneity checks and alternative specifications. Heterogeneity analyses indicate that the improvement is concentrated in eastern cities, while the effects are statistically insignificant in central and western regions. We also find that the reduction in misallocation occurs in both provincial capital and non-capital cities. These results imply that HSR can enhance resource-use efficiency and support sustainable regional development by reducing spatial frictions and promoting more balanced factor allocation. From a policy perspective, accelerating HSR network expansion can lower cross-regional mobility costs and enable freer flows of labor and capital, thereby improving allocative efficiency and fostering inclusive and sustainable growth. Full article

This investigation assessed the neurovascular coupling response through integrated assessments of neuronal function [electroencephalography (EEG)], microvascular oxygenation concentrations [functional near-infrared spectroscopy (fNIRS)], and arterial responses [transcranial Doppler ultrasound (TCD)]. The NVC response was assessed in 113 participants (86 females, aged 19–40 years) during visual (“Where’s Waldo?”) and motor (finger tapping) tasks. Block-averaged, time–frequency power was computed from the EEG data, while hemodynamic response functions were obtained from the fNIRS and TCD metrics. Granger causality assessed the predictiveness between EEG-fNIRS-TCD waveforms for each participant and was converted into a percentage of individuals displaying a significant value. Linear models were computed to determine the influence of sex, concussion history, young adulthood age, cardiorespiratory fitness, and mental health/learning disabilities on NVC parameters. During the initial 10 s of task onset, unidirectional predictiveness was weak to very strong for EEG-TCD (range: 47–83%) and fNIRS-TCD (44–92%) relationships; however, very weak to weak predictiveness was seen for the E0EG-fNIRS (0–29%) relationship for both tasks. Aside from known sex-, age-, and fitness-based influences on baseline/peak hemodynamic values (p < 0.050), the addition of concussion history and mental health/learning disabilities had minimal influence on NVC responses (p > 0.050). The findings demonstrated a unidirectional feedforward mechanism from the neuronal and microvasculature to the upstream arteries during task onset. Full article

Background/Objectives: Joubert syndrome is a rare neurodevelopmental disorder characterized by congenital cerebellar and brainstem malformations affecting networks involved in predictive motor control, sensorimotor integration, and autonomic regulation, resulting in a heterogeneous motor phenotype. Functional impairment is typically described using global gross motor scores, which may not adequately reflect axial control, postural organization, musculoskeletal alignment, or respiratory–postural interactions. The objective of this descriptive pilot case series was to provide a multidimensional functional characterization of children with Joubert syndrome by integrating standardized motor assessments with postural, musculoskeletal, and thoracoabdominal measures. Methods: Six children with genetically and radiologically confirmed Joubert syndrome underwent a single standardized assessment session conducted by the same examiner. This cross-sectional, non-controlled study was based on feasibility sampling, and no a priori power calculation was performed. Gross motor function and postural control were evaluated using the Gross Motor Function Measure-88 and the Balance Assessment Rating Scale. Additional measures included joint range of motion, sacral inclination angle, thoracic configuration, thoracic excursion during quiet breathing, and respiratory rate. Analyses were limited to descriptive statistics. Results: Gross motor performance varied widely across participants, whereas postural control scores did not parallel gross motor performance levels within the cohort. Inter-individual variability was observed in joint mobility, pelvic alignment, and thoracoabdominal configuration, including among children with relatively preserved gross motor scores. Thoracic excursion during quiet breathing demonstrated a relatively narrow and low within-cohort range. Conclusions: In this small exploratory case series, functional characteristics observed in this cohort extended beyond global motor scores. Axial control, postural organization, and thoracoabdominal configuration may represent relevant descriptive domains of functional presentation within a multidimensional framework. Larger, longitudinal, and controlled studies are required to determine their clinical and neurodevelopmental significance. Full article

The accurate prediction of gas turbine output power is critical for flexible scheduling and shipboard microgrid resilience. However, purely data-driven models suffer from poor generalization and physical inconsistency in complex marine environments, especially under unseen operation conditions. This paper proposes a condition-adaptive physics-informed long short-term memory (CAPI-LSTM) framework to ensure physical consistency across the full operation envelope. In the proposed framework, an MLP-based condition-adaptive regulator is developed to dynamically adjust the compressor air flow rate within the embedded physics-informed loss function. The proposed CAPI-LSTM model is verified using the operation data from an LM2500+ gas turbine. The comparison results demonstrate the superiority of the proposed method over traditional architectures. The CAPI-LSTM model achieves the lowest root mean square error of 0.177 MW, and its error distribution is the most concentrated near zero among all compared models. The robustness of the CAPI-LSTM model is further verified under the unseen operation conditions. The CAPI-LSTM still maintains excellent generalization capability compared to both purely data-driven models and standard physics-informed models, with an average error of only 0.218 MW and a narrow interquartile range of [0.058, 0.363]. The paired t-test results confirm that the improvement of the CAPI-LSTM model is statistically significant. The CAPI-LSTM model achieves competitive computational efficiency despite the integration of the physics-informed loss function with a condition-adaptive regulator. Furthermore, the CAPI-LSTM model achieves superior performance in noise immunity and transferability to other types of gas turbines. In summary, the proposed CAPI-LSTM model provides an effective and practical solution for marine gas turbine output power prediction. Full article

This study focuses on the spatial variation in seed germination characteristics of Picea glauca and P. mariana, prominent and widespread species within the Canadian boreal forest. The main objective was to determine seed germination requirements of geographically distinct seed collections of P. glauca and P. mariana. A total of 73 collections of P. glauca and 62 collections of P. mariana were selected across Canada and tested for germination under various temperatures. Base temperature (T_b) and thermal time required to reach 50% germination (TH₅₀) were derived from thermal model parameters for all seed collections. Correlation analyses between seed germination traits, geographic, and climatic variables were conducted. Base temperatures for germination of P. glauca ranged from 5.2 to 11.9 °C while P. mariana had base temperatures ranging from 6.2 to 12.8 °C, indicating a broader temperature range for the former to initiate germination. Optimal germination temperatures ranged from 15 to 20 °C for P. glauca and from 17.5 to 30 °C for P. mariana. Thermal time requirements for 50% germination were higher for P. glauca than for P. mariana, indicating that the former takes longer to germinate under the same temperature conditions. Latitudinal-related variables such as temperature of sites had a stronger influence on germination relative to precipitation or potential evaporation and affected seed viability, final germination and germination capacity of all seed sources. Seed viability was lower in northern seed collections and germination capacity was diminished at lower temperatures for both species. The results from this study can be built into models predicting shifts in boreal forest species under climate change. Full article

Traditional methods for geostressfield inversion face issues such as weak physical interpretability and insufficient generalization ability. This study pioneers the application of Physics-Informed Neural Network (PINN) to this problem, developing a data- and physics-driven inversion algorithm. The framework incorporates a constitutive-equation-based regularized loss function as a hard constraint during training to ensure physical consistency. To address boundary load uncertainty, two quantification approaches—Bayesian linear regression and surrogate model optimization—are proposed to establish 95% confidence intervals for boundary coefficients. Verification based on simple three-dimensional models and actual geological models of mines shows that PINN inversion achieves a mean absolute relative error as low as 0.0772%, with an error of 15.67% under sparse sampling conditions—significantly lower than the 31.07% error of the traditional Back propagation neural network. This demonstrates excellent robustness and data efficiency. In the practical engineering application of complex geological bodies, the average error of principal stress inversion is 9.35% with a minimum error of 0.137%. All inversion results fall within the permissible accuracy range of engineering, and the stress distribution conforms to basic laws, with an average error of 0.453 in the constitutive relation. Compared with BP neural network and multiple linear regression methods, it shows obvious accuracy advantages. This method provides a new solution for intelligent ground stress prediction with high accuracy, high efficiency, and strong physical interpretability, and also lays the foundation for early identification of geological disasters. Full article