Prediction Of Behavior Research Articles

Fast prediction of curing residual stress in polymer‐matrix composites by a deep learning method

AbstractCuring residual stress (CRS) is common in polymer‐matrix composites due to the anisotropic properties of materials. Finite element method (FEM), the most extensively used approach for curing behavior prediction, is usually complicated and time‐consuming. To achieve a fast prediction of process‐induced stresses, a convolutional neural network (CNN) is established based on the FEM. Firstly, a fully coupled methodology is built and validated through distortions of experimentally manufactured laminates. Then, it is applied to generate models with different stacking layers, and the residual stress is computed and serves as the dataset of the deep learning model. Finally, the construction and hyperparameters are determined, and the good generalization performance proves the high accuracy of the current model. Besides, the CNN method (<1 s) greatly reduces the computational time compared with the FEM (>14 min). The supervised machine learning method shows great potential in promoting efficiency in stacking sequence designing and optimization of composites.Highlights A fully coupled model was built to predict the curing behavior of composites. The numerical model was validated by the deformation of unsymmetrical composites. A FEM‐CNN method was proposed for the fast prediction of curing residual stress. Compared with FEM, this machine learning method is accurate and efficient.

Learning behaviour prediction and multi-task recommendation based on a knowledge graph in MOOCs

ABSTRACT One challenging issue in improving the teaching and learning methods in MOOCs is to construct potential knowledge graphs from massive learning resources. Therefore, this study proposes knowledge graphs driving online learning behaviour prediction and multi-learning task recommendation in MOOCs. Based on the knowledge graphs supported by multi-entities and features, the authors designed a novel deep learning model to fully calculate and optimise iterative learning processes, explore key semantics and potential values of learning behaviours, integrate multi-task items and flexibly analyse learners’ multi-entities and related features. Assisted by knowledge concept semantics and the formation of knowledge graphs, multi-entities of learning behaviours are fused and associated, which might be the leading trend of knowledge graphs. Sufficient experiments have proved that the whole work might ensure learning behaviour prediction and multi-task selection that can enable the knowledge graph to improve learning behaviours in MOOCs.

Optimizing Learning Path Design in Mobile Learning Platforms for Online Courses

With the rapid advancement of information technology, online education, particularly vocational education, has become a vital avenue for enhancing skills and knowledge. Vocational education necessitates flexible and personalized learning path design to accommodate the diverse needs and behaviors of learners. Mobile learning platforms, as a pivotal form of modern online education, provide learners with the convenience of accessing educational resources anytime and anywhere. However, existing methods for optimizing learning paths exhibit notable limitations, primarily in accurately capturing learners’ dynamic behaviors and in providing personalized and intelligent path design. Therefore, how to optimize learning paths based on learners’ dynamic behavior data has become a research hotspot in academia and educational practice. At present, many studies focus on matching analysis based on students’ static characteristics with course content but overlook learners’ behavioral changes and dynamic needs during the learning process. Traditional recommendation algorithms and rule-based path design methods are difficult to cope with complex learning behaviors and diverse learner needs. This study addresses these limitations by proposing an optimization model for mobile learning path design based on multi-view prediction of dynamic student behaviors. The model extracts mobile interaction features from student groups, constructs a multiple mobile behavior collaborative encoder, and employs multiple task label prediction techniques to achieve personalized and intelligent optimization of learning paths. The results demonstrate that this approach significantly enhances the learning efficiency and experience of learners, offering novel insights and technological support for the path design of mobile learning platforms.

A fishing vessel operational behaviour identification method based on 1D CNN-LSTM

Abstract The identification of fishing vessel operations holds significant importance in addressing fishing industry issues, such as overfishing and illegal, unreported and unregulated fishing (IUUF). Many countries utilise data from vessel monitoring systems (VMSs) or automatic identification systems (AISs) to monitor fishing activities. These data include vessel trajectories, headings and speeds, among others. We aimed to analyse the fishing behaviours of three types of fishing gear used by vessels (trawl, purse seine and gill net) and identify the types of gear employed by the vessels. Therefore, a 1D CNN-LSTM fishing vessel operational behaviour prediction model was proposed by combining a one-dimensional convolutional (1D CNN) neural network and a long short-term memory (LSTM) neural network. The model utilises 1D CNN to extract local features from fishing vessel trajectories and employs LSTM to capture the time series information in the data, eventually classifying fishing gears. The results show that the proposed model achieves a classification accuracy of 92% in categorising fishing vessel operational trajectories. This study significantly contributes to preventing IUUF, curtailing overfishing, and enhancing fisheries management strategies.

Shear strength behavior of reinforced concrete T-beams without web reinforcement

To investigate the influencing factors of shear strength for reinforced concrete beams without web reinforcement, 36 reinforced concrete beams were tested: 27 with a T-shaped section and 9 with a rectangular section. The experiments were designed to analyze the impact of various parameters on the shear strength behavior, including the shear span ratio, tension reinforcement ratio, and beam shape. The experimental findings indicate that each variable has a significant improvement, particularly, the contributions of the flange on the shear behavior of RC beams. Based on collected the shear database, two proposed equations were established and verified against the suggested equations in several international codes. The proposed equations herein exhibit an incredible, accurate, and consistent predictions of shear behavior of the beams. Additionally, the collected dataset was analyzed using various machine learning algorithms to explore the applicability; the results demonstrate that the modern data-driven techniques can provide an efficient and reliable prediction for the shear behavior.

Arrears behavior prediction of power users based on BP neural network and multi-scale feature learning: a refined risk assessment framework

This study aims to develop an efficient model to predict the arrears behavior of electricity users by integrating multi-scale feature learning with a backpropagation (BP) neural network. The goal is to provide accurate early warning systems and enhanced risk management tools for power companies. The BP neural network algorithm adjusts weights to minimize prediction errors, while multi-scale feature learning captures the diversity and regularity of user behavior by extracting data from various time dimensions, such as daily, weekly, and monthly intervals. First, electricity usage and weather data from the UMass Smart Dataset are preprocessed, including steps such as data cleaning, standardization, and normalization. Next, features are extracted across three time scales—daily, weekly, and monthly. These features are then input into the BP neural network model using the multi-scale feature learning method. A hierarchical neural network structure is designed to address the characteristics of different scales in distinct layers. Key model parameters are optimized, and a sensitivity analysis is conducted. The experimental results demonstrate that the BP neural network model incorporating multi-scale features outperforms traditional BP neural network models and other control models in several evaluation metrics. Specifically, the Gini coefficient is 0.55, the Kolmogorov-Smirnov statistic is 0.60, the Matthews correlation coefficient is 0.45, and specificity is 0.82. These results indicate that the proposed method offers significant improvements in capturing user behavior patterns and enhancing prediction accuracy. The study concludes that the effective fusion of multi-scale features not only enhances the model’s prediction performance but also strengthens its generalization ability. This method provides an advanced risk management tool for power companies, helping to increase the operational efficiency of smart grids and encouraging further research toward greater intelligence in the field.

An Exploratory Alternative Approach to Potential Incident Simulation, Control, and Evaluation System for Prediction of Oil Spill Behavior Through Supervised Machine Learning

<p><span style="font-family:"Times New Roman",serif;font-size:12.0pt;" lang="EN-US">The incidents occurring within the marine environment are supported by various Decision Support Systems (DSS), both in simulation and intervention. Accurate and real-time data inputs into these systems greatly contribute to the effective and prompt decision-making process. However, the absence of these systems in all situations or the inability to provide real-time data inputs can negatively impact the effectiveness of decision processes. This study aims to create a method that can enable reliable and accurate predictions regarding oil pollution and the cost-effective execution of certain decision processes. For this purpose, an exploratory study with various cases of ship-sourced oil pollution has been simulated using the Potential Incident Simulation Control and Evaluation System (PISCES). Random input values for each case have been utilized in PISCES simulation experiments. Afterward, supervised machine learning models were trained using the simulation experiments data set to predict oil dispersion amount and time of oil impact to shore. Model hyperparameters were optimized using cross-validated grid-searches. Through hyperparameter optimization using grid search, XGB, Random Forest, and Gradient Boosting emerged as the leading models for estimating oil dispersion. However, while Gradient Boosting yielded satisfactory outcomes, its performance could be further enhanced with additional data. Obtained results show that the proposed methodology has the potential for predicting the time of impact to shore, hence for rapid results for standard initial actions, they can be used as an alternative DSS to PISCES.</span></p>

A method to predict binary eutectic mixtures for mechanochemical syntheses and cocrystallizations

Mechanochemical syntheses may benefit from the formation of a liquid eutectic intermediate. The software PoEM predicts the eutectic point in a binary mixture from the thermodynamic data and the interaction modes of the two components of the mixture.

Modeling Fibrous Tissue in Vascular Fluid-Structure Interaction: A Morphology-Based Pipeline and Biomechanical Significance.

Modeling fibrous tissue for vascular fluid-structure interaction analysis poses significant challenges due to the lack of effective tools for preparing simulation data from medical images. This limitation hinders the physiologically realistic modeling of vasculature and its use in clinical settings. Leveraging an established lumen modeling strategy, we propose a comprehensive pipeline for generating thick-walled artery models. A specialized mesh generation procedure is developed to ensure mesh continuity across the lumen and wall interface. Exploiting the centerline information, a series of procedures are introduced for generating local basis vectors within the arterial wall. The procedures are tailored to handle thick-walled tissues where basis vectors may exhibit transmural variations. Additionally, we propose methods for accurately identifying the centerline in multi-branched vessels and bifurcating regions. These modeling approaches are algorithmically implementable, rendering them readily integrable into mainstream cardiovascular modeling software. The developed fiber generation method is evaluated against the strategy using linear elastostatics analysis, demonstrating that the proposed approach yields satisfactory fiber definitions in the considered benchmark. Finally, we examine the impact of anisotropic arterial wall models on the vascular fluid-structure interaction analysis through numerical examples, employing the neo-Hookean model for comparative purposes. The first case involves an idealized curved geometry, while the second studies an image-based abdominal aorta model. Our numerical results reveal that the deformation and stress distribution are critically related to the constitutive model of the wall, whereas hemodynamic factors are less sensitive to the wall model. This work paves the way for more accurate image-based vascular modeling and enhances the prediction of arterial behavior under physiologically realistic conditions.

What Factors Influence the Financial Risk Tolerance - A Further Examination on the Nexus Between Financial Risk Tolerance and Financial Environmental Factors

The consideration of risk tolerance plays a crucial role in the process of making optimal portfolio selections. In particular, the level of financial risk that an investor is willing to take, known as their financial risk tolerance (FRT), is sometimes regarded as the single most essential characteristic for the prediction of investor behaviour. In spite of this, it is a challenging endeavour since it is dependent on a wide variety of financial environment elements. For this reason, evaluating financial risk tolerance and identifying the elements that influence individual investors’ views of the financial risks they face have been interest of research and investigations for significant years. This study investigates the relationship between the financial risk tolerance of individual equity investors and financial environmental factors. For this purpose, four indicators namely “financial anxiety, money ethics, financial stress, and financial satisfaction” were used to check the impact of financial environmental determinants on FRT. The present study was executed in the state of Kerala, and the information was collected from individual retail investors through the use of a predesigned questionnaire. The Structural Equation Modelling (SEM) technique was utilised to evaluate the model. The results indicate that financial anxiety, money ethics, financial stress, and financial satisfaction exert significant positive effects on FRT. The findings of the current study may offer important assistance to state and national policymakers in the process of creating investment policies.

Deformation behavior and yield strength prediction of [112] oriented NbMoTaW refractory high entropy alloy nanowires

Refractory high entropy alloys (RHEAs) have garnered widespread attention due to their potential applications at extremely high temperatures. However, accurately predicting the mechanical properties of these materials is challenging due...

Dynamic compression mechanical behavior and strength prediction modeling of sulfate attacked concrete under triaxial static pre-loading

Dynamic compression mechanical behavior and strength prediction modeling of sulfate attacked concrete under triaxial static pre-loading

A Evaluation-Based Large Model for Multi-Step Behavior Prediction in Intelligent Consumer Electronics

A Evaluation-Based Large Model for Multi-Step Behavior Prediction in Intelligent Consumer Electronics

Prediction of Mechanical Properties and Fracture Behavior of TC17 Linear Friction Welded Joint Based on Finite Element Simulation.

TC17 titanium alloy is widely used in the aviation industry for dual-performance blades, and linear friction welding (LFW) is a key technology for its manufacturing and repair. However, accurate evaluation of the mechanical properties of TC17-LFW joints and research on their joint fracture behavior are still not clear. Therefore, this paper used the finite element numerical simulation method (FEM) to investigate the mechanical behavior of the TC17-LFW joint with a complex micro-structure during the tensile processing, and predicted its mechanical properties and fracture behavior. The results indicate that the simulated elastic modulus of the joint is 108.5 GPa, the yield strength is 1023.2 MPa, the tensile strength is 1067.5 MPa, and the elongation is 1.98%. The deviations from measured results between simulated results are less than 2%. The stress and strain field studies during the processing show that the material located at the upper and lower edges of the joint in the WZ experiences stress and strain concentration, followed by the extending of the stress and strain concentration zone toward the center of the WZ. And finally, the strain concentration zone covered the entire WZ. The fracture behavior studies show that the material necking occurs in the TMAZ of TC17(α + β) and WZ, while cracks first appear in the WZ. Subsequently, joint cracks propagate along the TC17(α + β) side of the WZ until fracture occurs. There are obvious tearing edges formed by the partial tearing of the WZ structure in the simulated fracture surface, and there are fracture surfaces with different height differences at the center of the joint crack, indicating that the joint has mixed fracture characteristics.

Emotion Recognition in Natural Language Processing: Understanding How AI Interprets the Emotional Tone of Text

Emotion recognition is one of the newest transformational tools in the area of (Natural Language Processing) NLP for AI to make out the emotional feel of text with great accuracy. While analyzing unstructured data, such as customer feedback, social media posts, and reviews, algorithms within NLP detect emotions like anger, happiness, sadness, and frustration. This helps the firms to understand their customers more emotionally and helps them develop suitable products, services, and strategies for engagement. AI-powered emotion detection enhances customer support systems through personalized service interactions and faster grievance redressal. It also supports marketing functions through trend identification and prediction of customer behavior. The satisfaction of users will improve, brand loyalty will be created, and competitiveness will increase as the companies use more and more emotion-aware systems. These come with their own challenges to be faced very seriously: cultural differences, interpretation of context, and data privacy. This article focuses on methodologies of emotion recognition in NLP, various applications, and ethical use, pointing out impacts on customer experience management and future directions in AI-driven sentiment analysis.

Substantiation and selection of parameters for supporting mine workings at deep levels

Purpose.The research aims to conduct a comprehensive study on substantiation and selection of optimal parameters for supporting mine workings at deep levels by analyzing the stress-strain state (SSS) of the rock mass, modeling geomechanical processes and developing effective strengthening technologies in difficult geological conditions. Methods. The research includes modeling of the stress-strain state of the rock mass using ANSYS, Phase2 and Prorock software packages. To assess and predict the stress-strain state of the mass in the area of stope blocks, a series of numerical experiments have been conducted to analyze the near-contour rock mass stability. The physical-mechanical characteristics of ores and host rocks are used as input data for modeling. Findings. The mass SSS analysis has confirmed that increasing the number of cable bolts up to four provides mine wor-king stability, but is accompanied by intensive fracture formation beyond the contour, as well as convergence up to 14 cm, which requires the use of reinforcing mesh and reinforcing frame in two layers. The mining system elements have been found to provide the necessary safety factor for end ore drawing (ks ≥ 3.0) and slicing mining with hardening backfill (ks ≥ 5.0). Originality. The parameters for supporting mine workings have been substantiated, which ensures safe mining of deep levels. It has been revealed that when backfilling, the height of the caving zone is 125 m and the fracture zone is 60 m. For mining systems with caving, these figures reach 280 and 470 m, respectively. Practical implications. The technology has been developed for supporting capital mine workings with the use of reinforced combined support and roof bolts. The results obtained contribute to the improvement of reliability and efficiency of mining operations by providing accurate prediction of rock behavior under conditions of changing stresses and reduction of their strength characteristics.

On the drawability prediction of AA5754 aluminum alloy sheet

In order to study the drawability of AA5754 aluminum alloy blank, the numerical predictions of fracture failure behavior caused by cup drawing of metal sheet were carried out by using the GTN model and the thermodynamic-based continuous damage mechanics (CDM) model. The CDM model coupling the nonlinear isotropic and kinematic hardening laws with the isotropic ductile damage model was developed to carry out the numerical computation in the form of the user material subroutines. Although the forming limit curves predicted by GTN model and CDM model are distinctly different, but both of them are feasible to characterize the formability of metal sheets. The numerically predicted drawability of metal sheet is in good agreement with the experimental results in terms of strokes, sheet thinning and fracture failure location. The effects of sheet original thickness and friction coefficient between punch and sheet on the drawability of metal sheet were further investigated in detail.

ANALYSIS OF THE EFFECT OF U-TURN ON TRAFFIC FLOW PERFORMANCE

This paper aims to explore the impact of U-turn motions on traffic flow and service levels. The research employs the Guidebook (PKJI, 2023) to assess observations related to traffic volume, vehicle speed, and both disturbed and undisturbed flow, which are gathered during the field survey. The data used for analysis was obtained by collecting primary data and secondary data according to the needs of the research. In addition, the data was obtained from a number of reports and documents that had been prepared, as well as the results of other literature studies. The results show that the number of vehicles on a road section is significantly increased, resulting in a significant increase in traffic volume and a decrease in vehicle speed. Moreover, the frequency of the use of the maneuvers affects the level of congestion on the road section, highlighting the need for early and strategic planning in the development of transportation infrastructure, particularly land transportation, which is crucial for facilitating everyday mobility and economic activities. This paper also highlights the importance of incorporating advanced traffic modeling techniques and simulations to enhance prediction of traffic behavior under different scenarios, informing infrastructure improvements and traffic management strategies. Finally, comparing findings with similar studies in other regions could yield valuable benchmarks for assessing traffic efficiency and service quality.

Physics-regularized neural networks for predictive modeling of silicon carbide swelling with limited experimental data

This study introduces a physics-regularized neural network (PRNN) as a computational approach to predict silicon carbide’s (SiC) swelling under irradiation, particularly at high temperatures. The PRNN model combines physics-based regularization with neural network methodologies to generalize the behavior of SiC, even in conditions beyond the traditional empirical model’s valid range. This approach ensures continuity and accuracy in SiC behavior predictions in extreme environments. A key aspect of this research is using nested cross-validation to ensure robustness and generalizability. The PRNN model effectively bridges empirical and sparse experimental data by integrating prior knowledge and refined tuning procedures. It demonstrates its SiC’s predictive power in high-irradiation conditions essential for nuclear and aerospace applications.

Heating dictates the scalability of CO2 electrolyzer types.

Electrochemical CO2 reduction offers a promising method of converting renewable electrical energy into valuable hydrocarbon compounds vital to hard-to-abate sectors. Significant progress has been made on the lab scale, but scale-up demonstrations remain limited. Because of the low energy efficiency of CO2 reduction, we suspect that significant thermal gradients may develop in industrially relevant dimensions. We describe here a model prediction for non-isothermal behavior beyond the typical 1D models to illustrate the severity of heating at larger scales. We develop a 2D model for two membrane electrode assembly (MEA) CO2 electrolyzers; a liquid anolyte fed MEA (exchange MEA) and a fully gas fed configuration (full MEA). Our results indicate that full MEA configurations exhibit very poor electrochemical performance at moderately larger scales due to non-isothermal effects. Heating results in severe membrane dehydration, which induces large Ohmic losses in the membrane, resulting in a sharp decline in the current density along the flow direction. In contrast, the anolyte employed in the exchange MEA configuration is effective in preventing large thermal gradients. Membrane dehydration is not a problem for the exchange MEA configuration, leading to a nearly constant current density over the entire length of the modeled domain, and indicating that exchange MEA configurations are well suited for scale-up. Our results additionally indicate that a balance between faster kinetics, higher ionic conductivity, smaller pH gradients and lower CO2 solubility causes an optimum operating temperature between 60 and 70 °C.