Optimal Model Structure Research Articles

Measuring Saudi Arabian Students' Engagement in Synchronous Online Learning of Chinese as a Foreign Language

ABSTRACTBackgroundStudent engagement has been conceptualised and operationalised in various learning environments. However, there is currently a lack of established scales to measure student engagement in synchronous online learning. One possible reason is the existence of the conceptual and structural ambiguity regarding student engagement.ObjectiveWith its context situated in Saudi Arabian students' synchronous online learning of Chinese as a foreign language (L2 Chinese), this study attempts to find out the best representation and measure of synchronous online engagement based on four competing statistical modelling methods, including confirmatory factor analysis (CFA), exploratory structural equation modelling (ESEM), bi‐factor CFA (B‐CFA) and bi‐factor ESEM (B‐ESEM).MethodsA total of 167 Saudi Arabian students voluntarily participated in this online questionnaire‐based study. A 19‐item online questionnaire was adaptively developed to measure students' engagement in synchronous online learning of L2 Chinese from behavioural, cognitive, affective and social dimensions. CFA, ESEM, B‐CFA and B‐ESEM were employed to determine the optimal structure model for representing students' synchronous online engagement in L2 Chinese learning.Results and ConclusionThe results revealed that the B‐ESEM model was the best structure model for both measuring and accounting for the generality and specificity of students' engagement in synchronous online learning of L2 Chinese. More specifically, student online engagement was found to be a general unity with four distinctive subdimensions including behavioural, cognitive, affective and social engagement. This study not only reconciles the construct inconsistency of student engagement in the literature from the synchronous online learning perspective but also provides an optimal representation for measuring students' synchronous online engagement in L2 learning.

Design and Testing of a Gasoline Engine Muffler Based on the Principle of Split-Stream Rushing

In order to reduce the exhaust noise, which is the main source of gasoline engine noise, this paper uses on orthogonal test to optimize the parameters of the main structure of split-stream rushing muffler (the perforation rate of the perforated pipe, perforation aperture of the perforated pipe, perforation rate of the perforated plate). It also comprehensively evaluates its acoustic and aerodynamic performances to determine the optimal structural model. The acoustic performance and aerodynamic performance of the split-stream rushing muffler and the original muffler are compared and analyzed in the simulation test. The results show that the average Transmission Loss of the split-stream rushing muffler is greater than that of the original muffler, and its Pressure Loss is also lower than that of the original muffler. Through the insertion loss experiment, it was found that the average insertion loss of the main muffling frequency band is 19.14 dB, which is higher than that of the original muffler, and the peak frequency of the insertion loss of the split-stream rushing muffler corresponds well with the peak frequency of the engine exhaust noise. The Pressure Loss of the split-stream rushing muffler was tested on the experiment bench, and the relative error between the experiment data and the simulation data is within 8%. In summary, the split-stream rushing muffler can effectively reduce the exhaust noise problem of gasoline engines.

Data-driven time-varying discrete grey model for demand forecasting

Demand forecasting is critical for strategic decision-making in the business sector. However, estimating demand variations remains challenging due to their time-varying tendencies. To address this, we propose a novel universal approach called the time-varying discrete grey model, along with a data-driven model structure identification algorithm. Specifically, we introduce a universal model form that incorporates polynomial time-varying parameters to unify existing discrete grey models. We then discuss significant properties, such as unbiasedness and affine transformation. Furthermore, we develop a data-driven algorithm that adaptively identifies the optimal model structure via subset selection strategies. To validate the effectiveness of our approach, we conduct Monte Carlo simulations to assess its robustness against noise and evaluate its performance in multi-step-ahead forecasting. Finally, through extensive experiments on real-world datasets from USA State Retail Sales, we demonstrate the superiority of our model over benchmark approaches, including statistical models and artificial intelligence methods. Our proposed approach offers a competitive alternative for demand forecasting in the business sector.

The devil in the details: lessons from Li6PS5X for robust high-throughput workflows

Using Li6PS5Cl and related crystals as a case study, we explore key steps in high-throughput workflows and highlight potential challenges: selecting the optimal structural model, addressing disorder, and managing the role of temperature.

A Lightweight Network with Domain Adaptation for Motor Imagery Recognition.

Brain-computer interfaces (BCI) are an effective tool for recognizing motor imagery and have been widely applied in the motor control and assistive operation domains. However, traditional intention-recognition methods face several challenges, such as prolonged training times and limited cross-subject adaptability, which restrict their practical application. This paper proposes an innovative method that combines a lightweight convolutional neural network (CNN) with domain adaptation. A lightweight feature extraction module is designed to extract key features from both the source and target domains, effectively reducing the model's parameters and improving the real-time performance and computational efficiency. To address differences in sample distributions, a domain adaptation strategy is introduced to optimize the feature alignment. Furthermore, domain adversarial training is employed to promote the learning of domain-invariant features, significantly enhancing the model's cross-subject generalization ability. The proposed method was evaluated on an fNIRS motor imagery dataset, achieving an average accuracy of 87.76% in a three-class classification task. Additionally, lightweight experiments were conducted from two perspectives: model structure optimization and data feature selection. The results demonstrated the potential advantages of this method for practical applications in motor imagery recognition systems.

The application of ICPA optimization algorithm in multi-objective optimization structural design of prefabricated buildings

With the prefabricated buildings developing, traditional architectural design methods can no longer meet the requirements of efficient, green, and sustainable development. In view of this, based on the analysis of the framework structure of the cyclical parthenogenesis algorithm, the study introduced chaotic optimization algorithm for improvement. And the improved new algorithm was applied to multi-objective problems in the optimization design of prefabricated building structures. Finally, a novel structural design optimization model was proposed. These experiments confirmed that the improved algorithm had the least 160 iterations and 17 optimal solutions, which was an increase of 15 compared to traditional aphid algorithms. Two function solutions of this new structural design optimization model were both between –0:5 and 0.5, with relatively smaller values. In addition, this model could effectively optimize and transform physical buildings, increasing their structural stability by 2.43%, increasing their structural quality coefficient by 4.49%, reducing vibration cycles by 0.06%, and reducing inter story displacement angles by 0.04%. In summary, the improved cyclical parthenogenesis algorithm has good performance in solving multi-objective problems in prefabricated structures, and can quickly and accurately find the global optimal solution. This study aims to provide guidance for the prefabricated building structure design.

Optimization of the Stand Structure in Secondary Forests of Pinus yunnanensis Based on Deep Reinforcement Learning

This study proposes a multi-objective stand structure optimization scheme based on deep reinforcement learning, demonstrating the strengths of deep reinforcement learning in solving multi-objective optimization problems and providing innovative insights for sustainable forest management. Using the Pinus yunnanensis secondary forest in Southwest China as the research subject, we established a stand structure optimization model with stand spatial structure indexes as the optimization objectives and non-spatial structure indexes as the constraints. We optimized the stand structure by combining deep reinforcement learning with three tree-felling decisions: random selection, tree homogeneity index, and spatial competition. Simulated cutting experiments were conducted on circular plots (P1–P5) using deep reinforcement learning and reinforcement learning. The initial objective function values of all plots (0.2950, 0.2954, 0.3445, 0.3010, 0.3168) were effectively improved. The maximum objective function values after optimization by the deep reinforcement learning schemes (0.3815, 0.3701, 0.4301, 0.4599, 0.3689) were significantly better than those achieved by the reinforcement learning schemes (0.3394, 0.3579, 0.3986, 0.4321, 0.3556). Among these, the optimization scheme combining random selection and deep reinforcement learning showed the greatest average improvement across the five plots (29.73%), with its enhancement of the objective function value significantly surpassing that of other optimization schemes. This study applies deep reinforcement learning to stand structure optimization, proposing a new approach to solving multi-objective optimization problems in stand structure and providing a reference for forest health management in Southwest China.

A Multi-Objective Optimization Design Method for High-Aspect-Ratio Wing Structures Based on Mind Evolution Algorithm Backpropagation Surrogate Model

The design of high-aspect-ratio wings enhances the flight efficiency of UAVs but also introduces significant aeroelasticity challenges. The efficient optimization of wing structures in complex environments has become critical. To address the current challenges in balancing wing strength with lightweight structural designs, this study proposed an intelligent solution method for optimizing wing dimensions and structural layout. Driven by mechanical simulation data, the method established a mapping relationship between the structural layout and dimensions of the wing and its bending stiffness. This approach was further enhanced by the mind evolution algorithm (MEA) to optimize the solution performance of the surrogate model. The wing structure optimization model was established using the multi-objective grey wolf optimizer (MOGWO) based on the surrogate model for search and optimization. This study focused on the composite material wing of a long-endurance unmanned aerial vehicle (UAV). The established MEA-BP surrogate model demonstrated high computational efficiency, with the prediction error standard deviation (STD) of wing deflection not exceeding 0.495 mm. The optimization model required 175 s to calculate the Pareto front solutions. The optimized structure resulted in a 28.32% increase in wing equivalent stiffness, and weight only increased by 6.67% compared to the original structure. These results showcased the effectiveness of the proposed method and validated the feasibility of integrating intelligent optimization algorithms and machine learning in the field of aircraft design.

Green Transformation of Industrial Structure of Jiaxing City Driven by Synergizing the Reduction of Pollution and Carbon Emissions

The "Implementation Plan for Reduction of Pollution and Carbon Emissions" emphasizes the need to explore mechanisms for pollution and carbon emission reductions, strengthen efforts for synergistic reduction, and accelerate the green and low-carbon development in different types of cities. Thus, this study established a multi-objective optimization model for the industrial structure of the city based on green total factor productivity （GTFP）, which was applied to Jiaxing, an emerging coastal city. The results indicated an overall 8% increase in GTFP across various industries in Jiaxing from 2016 to 2019. The top three economic sectors - chemical products； electricity and thermal production and supply； and communication equipment, computers, and other electronic devices-ranked 12th, 15th, and 5th in GTFP, respectively. Conversely, industries with the top three GTFP rankings-other manufacturing products, specialized equipment, food, and tobacco-ranked 19th, 12th, and 14th in GDP, respectively. Given the mismatch between economic output and environmental benefits among different industries, deepening industrial structure adjustment and promoting synergistic pollution reduction and carbon reduction are imperative. The chemical industry （decreasing by 2%） and the electricity and thermal production and supply industry （decreasing by 1%） crucially need industrial transformation. This can be achieved by setting higher environmental thresholds, reducing the growth rate of fixed asset investment, and curbing the final consumption of these industries to enhance the efficiency of existing facilities. Meanwhile, the service industry （increasing by 5%） should be rapidly developed, while other industries can continue to grow at their current pace. The city-level industrial structure optimization model established in this study can effectively support future decision-making for the dual control of total carbon emissions and intensity, foster new-quality productivity, and promote carbon peaking and green low-carbon high-quality development in different cities.

3D Topology optimization considering multiple loading

Topological optimization looks for determining the ideal material distribution within a design domain (2D/3D) in order to optimize structural performance following imposed design constraints. This material distribution can vary continuously, resulting in complex shapes that are lighter than the original structure and take better advantage of material strengths. Incorporating multiple loads into topology optimization increases the complexity of the problem, as it requires simultaneous consideration of different types of loads and their interactions with the structure in problems that have several degrees of freedom. This can include the analysis of load combinations due to self-weight, other load combinations or even dynamic or thermal loads. This work aims to develop and implement a 3D structural topological optimization model that takes these multiple loads into account using MATLAB program language. Practical examples of optimization cases considering multiple loads are presented, as well as comparisons with existing results in the literature, in order to demonstrate the accuracy of the proposed algorithm.

Structural optimization model of oil-natural air-natural transformer radiator based on data-model hybrid-driven

The power transformer is the central equipment of the power system. Establishing a model between radiator structural parameters and hot spot temperature (HST) is crucial for optimizing transformer cooling structures, enhancing transformer cooling capabilities, and ensuring the safe and stable operation of power systems. Existing models typically utilize data-driven methods. However, due to their lack of reasonable physical significance, existing models often suffer from issues such as insufficient generalization capability, high computational complexity, and poor interpretability, restricting their predictive accuracy and applicability. Therefore, this paper proposes a data-model hybrid-driven model (DMHDM) that integrates the radiator heat transfer physical model of the oil-natural air-natural (ONAN) transformer with HST data obtained from a finite element simulation model. Firstly, a theoretical analysis of the heat transfer process of the radiator fins is conducted, leading to the establishment of a low-fidelity physics model. Then, employing the full factorial design method and CFD model, sample data is obtained to develop a high-fidelity HST prediction model based on the data-driven method. Finally, a CFD model of a single-phase ONAN transformer was constructed. The DMHDM was compared with the traditional response surface methodology (RSM), and the sources of errors were analyzed. The results indicate that DMHDM provides better interpretability, improves accuracy by 20.5% within the sample set, enhances generalization capability by 98.6%, and reduces computational complexity by 92.5%. This study provides an efficient and feasible framework for establishing the relationship between structural parameters of ONAN transformer radiators and HST.

Interpreting Federated Learning (FL) Models on Edge Devices by Enhancing Model Explainability with Computational Geometry and Advanced Database Architectures

Federated learning (FL) on edge devices has emerged as a promising approach for decentralized model training, enabling data privacy and efficiency in distributed networks. However, the complexity of these models presents significant challenges in terms of transparency and interpretability, which are critical for trust and accountability in real-world applications. This paper explores the integration of explainable AI techniques to enhance model interpretability within federated learning systems. By incorporating computational geometry, we aim to optimize model structure and decision-making processes, providing clearer insights into how models generate predictions. Additionally, we examine the role of advanced database architectures in managing the complexity of federated learning models on edge devices, ensuring efficient data handling and storage. Together, these approaches contribute to a more transparent, efficient, and scalable framework for federated learning on edge networks, addressing key challenges in both model explainability and performance optimization. This review highlights recent advancements and suggests future directions for research at the intersection of federated learning (FL), edge computing, explainability, and computational techniques.

Research on the prediction of material removal and over-grinding optimization for abrasive flow machining of 3D printed right-angle bends

Abstract Addressing the issue of over-grinding on the outer side of right-angle bends in abrasive flow machining due to the gradient change of abrasive inertia force, a model for predicting material removal and an optimized structure for right-angle bends, both based on abrasive flow machining, are proposed. In this paper, the 3D-printed aluminium alloy right-angle bends are used as experimental objects, and the Carreau-Yasuda equations are fitted for simulation and analysis after rheological testing of the medium used in the test. A predictive model for material removal was developed by integrating simulated channel pressure with machining cycles, and its effectiveness was validated through experiments. Using this predictive model for structural optimization of bends, an unevenly thickened optimized right-angle bend was designed. The machining tests verified the accuracy of the simulation analysis, and the over-grinding region of the right-angle bend appeared at the maximum of the pressure region in the numerical simulation. At a processing pressure of 10 MPa and cycles of 20, 60, and 100, the prediction model resulted in material removal errors of 6.94%, 8.93%, and 13.31% respectively for the outer side of the bend, indicating a good fit of the prediction model. The optimized bend designed according to the predictive model exhibited an 80.37% reduction in overall deviation at the elbow compared to conventional right-angle bends, and a 67.31% reduction in contour deviation at the area most affected by inertia forces, effectively mitigating the issue of over-grinding at the elbow. This research facilitates quantitative control of material removal in abrasive flow machining of right-angle bends and provides theoretical support for non-uniform thickness design in bends.

A mechanics-based data-free Problem Independent Machine Learning (PIML) model for large-scale structural analysis and design optimization

Machine learning (ML) enhanced fast structural analysis and design recently attracted considerable attention. In most related works, however, the generalization ability of the ML model and the massive cost of dataset generation are the two most criticized aspects. This work combines the advantages of the universality of the substructure method and the superior predictive ability of the operator learning architecture. Specifically, using a novel mechanics-based loss function, lightweight neural network mapping from the material distribution inside a substructure and the corresponding continuous multiscale shape function is well-trained without preparing a dataset. In this manner, a problem machine learning model (PIML) that is generally applicable for efficient linear elastic analysis and design optimization of large-scale structures with arbitrary size and various boundary conditions is proposed. Several examples validate the effectiveness of the present work on efficiency improvement and different kinds of optimization problems. This PIML model-based design and optimization framework can be extended to large-scale multiphysics problems.

Data-driven Performance Indicators for SAGD Process of Oil Sands Using Support Vector Regression Machine with Parameter Optimization Algorithm

Abstract The rapid and accurate forecasting of performance in the Steam-Assisted Gravity Drainage (SAGD) process for oil sands is crucial for the reasonable design of the development plan. This study aims to address this need by presenting novel data-driven performance indicators based on support vector regression (SVR), a machine learning method that complements the traditional physics-driven approach. During the SAGD process, steam is injected into the reservoir to heat the bitumen, reducing its viscosity, and allowing it to flow towards a lower well where it can be collected. The performance of the SAGD process depends on various factors such as steam injection rate, reservoir heterogeneity, and operating conditions. Accurately forecasting the performance of the SAGD process can help optimize these parameters and improve the overall efficiency of oil sands recovery. The data-driven performance indicators proposed in this study utilize the SVR method to establish a relationship between input parameters and the desired performance outputs. In the constructing process, some parameter optimization algorithms, like grid search method, particle swarm optimization algorithm and genetic algorithm, are used to identify the optimal SVR model structure. The validation results show that the design meets the desired objectives. All in all, through proposed data-driven performance indicators, the performance of SAGD process in candidate oil sands projects could be rapidly and easily obtained.

Cost optimization in structural design for reinforced concrete frames using Jaya algorithm

This study analyzes and optimizes the structural design of three-dimensional (3D) reinforced concrete framestructures to minimize the amount of two main materials, including concrete and steel reinforcement, used inreinforced concrete frames. Jaya algorithm was developed based on evolutionary algorithms to build the structural optimization model. The objective function (minimum material cost) with variables being column andbeam cross-sections was set up. In which, the constraints related to the maximum internal force and displacement being in the structural members satisfy limited strength and serviceability requirements. A subroutine written in Python was used to connect the optimization process to the structural analysis software, ETABS. The 3D reinforced concrete frame of a three-story building was selected for cost and design optimization analysis. In which, the optimization problem was solved in cases of three different maximum numbers of iterations, including 20, 35, and 50. In each iteration level, a setting of five independent runs was performed. The subroutine proved to be fast, robust, and convenient manner for solving optimization problems in designing 3D reinforced concrete frames. In which, the best optimal cost might be obtained after twenty iterations and the better convergence behavior occurred at higher numbers of iterations. The study results showed that, for this reinforced concrete frame, applying optimal design led to a materials cost reduction (success rate) by 33.67% compared to that of the conventional design. This success rate would fluctuate according to different nations’ design codes.

Spatiotemporal modelling of airborne birch and grass pollen concentration across Switzerland: A comparison of statistical, machine learning and ensemble methods

BackgroundStatistical and machine learning models are commonly used to estimate spatial and temporal variability in exposure to environmental stressors, supporting epidemiological studies. We aimed to compare the performances, strengths and limitations of six different algorithms in the retrospective spatiotemporal modeling of daily birch and grass pollen concentrations at a spatial resolution of 1 km across Switzerland. MethodsDaily birch and grass pollen concentrations were available from 14 measurement sites in Switzerland for 2000–2019. To develop the spatiotemporal models, we considered spatiotemporal, spatial and temporal predictors including meteorological factors, land-use, elevation, species distribution and Normalized Difference Vegetation Index (NDVI). We used six statistical and machine learning algorithms: LASSO, Ridge, Elastic net, Random forest, XGBoost and ANNs. We optimized model structures through feature selection and grid search techniques to obtain the best predictive performance. We used train-test split and cross-validation to avoid overfitting and overoptimistic performance indicators. We then combined these six models through multiple linear regression to develop an ensemble hybrid model. ResultsThe 5th-95th percentiles of birch and grass pollen concentrations were 0–151 and 0–105 grains/m3, respectively. The hybrid ensemble model achieved the best RMSE on the test dataset for both birch and grass pollen with 94.4 and 19.7 grains/m3, respectively.Nonlinear models (Random forest, XGBoost and ANNs) achieved lower test RMSE's than linear models (LASSO, Ridge, Elastic net) for both pollen types, with RMSE's ranging from 105.9 to 140.5 grains/m3 for birch and from 20.0 to 25.4 grains/m3 for grass pollen. The Random forest algorithm yielded the best spatial and temporal performance among the six evaluated modelling methods. The ensemble hybrid model outperformed the six linear and nonlinear algorithms. Country-wide pollen concentration, land use, weather, and NDVI were important predictors. ConclusionNonlinear algorithms outperformed linear models and accurately explained complex, nonlinear relationships between environmental factors and measured concentrations.

Optimizing Stand Spatial Structure at Different Development Stages in Mixed Hard Broadleaf Forests

Thinning plays a key role in regulating the stand spatial structure (SpS) to improve the development of stand quality, and the stand has different characteristics of stand structure (SS) at different growth and development stages (DSs), so it is most important to reasonably determine the stage of growth and development of the stand to optimize the stand structure. We applied the TWINSPAN two-way indicator species analysis method to classify the different development stages of mixed hard broadleaf forests. We provided a comprehensive stand spatial structure optimization model for three selected plots at different development stages, respectively, to optimize the SpS. The results demonstrated the classified DS of 29 mixed hard broadleaf plots for three forest stages: the establishment stage, competitive stage, and quality selection stage. We then applied the SpS optimization model to our three plots; the Q(x) increased by 124.04%, 333.74%, and 116.83% when compared with those with no harvest, in which, upon the removal of 10% of the trees from the three plots, the maximum RIP values were all observed. Our results indicated that the SpS optimization model could regulate the SS for different growth stages and DSs.

Research on Optimization of Image Recognition Algorithm Based on Deep Learning

With the rapid development of information technology, image recognition has become increasingly crucial in numerous fields. Deep learning, as a highly potent machine learning approach, has brought about a revolutionary breakthrough in image recognition. This paper delves into the optimization of image recognition algorithms based on deep learning. Firstly, it analyzes the application status of deep learning in image recognition, covering common neural network architectures such as convolutional neural network (CNN). Then, the optimization strategy of the image recognition algorithm is elaborated from multiple aspects, including data augmentation to increase data diversity, model structure optimization for better feature extraction, and hyperparameter adjustment to enhance performance. Through extensive experiments, the effects of different optimization methods are compared meticulously. It is demonstrated that the optimized algorithm shows significant improvements in accuracy, robustness, and efficiency. Finally, the paper looks ahead to the future development trend of image recognition algorithms based on deep learning, envisioning further advancements and broader applications.

Uncovering the Over-Smoothing Challenge in Image Super-Resolution: Entropy-Based Quantification and Contrastive Optimization.

PSNR-oriented models are a critical class of super-resolution models with applications across various fields. However, these models tend to generate over-smoothed images, a problem that has been analyzed previously from the perspectives of models or loss functions, but without taking into account the impact of data properties. In this paper, we present a novel phenomenon that we term the center-oriented optimization (COO) problem, where a model's output converges towards the center point of similar high-resolution images, rather than towards the ground truth. We demonstrate that the strength of this problem is related to the uncertainty of data, which we quantify using entropy. We prove that as the entropy of high-resolution images increases, their center point will move further away from the clean image distribution, and the model will generate over-smoothed images. Implicitly optimizing the COO problem, perceptual-driven approaches such as perceptual loss, model structure optimization, or GAN-based methods can be viewed. We propose an explicit solution to the COO problem, called Detail Enhanced Contrastive Loss (DECLoss). DECLoss utilizes the clustering property of contrastive learning to directly reduce the variance of the potential high-resolution distribution and thereby decrease the entropy. We evaluate DECLoss on multiple super-resolution benchmarks and demonstrate that it improves the perceptual quality of PSNR-oriented models. Moreover, when applied to GAN-based methods, such as RaGAN, DECLoss helps to achieve state-of-the-art performance, such as 0.093 LPIPS with 24.51 PSNR on 4× downsampled Urban100, validating the effectiveness and generalization of our approach.