Optimal Model Parameters Research Articles

Application of Copula Models in Stock Market Analysis

Objectives. The objective of the study is to use copula models to analyze shares of the Russian stock market and describe changes in the relationship between the shares before and during the coronavirus infection (COVID-19).Methods. An algorithm for using copulas and functions of the R programming language in its implementation is presented. To model the dynamics of financial series the ARMA-GJR-GARCH process (autoregressive moving average Glosten-Jagannathan-Runkle model with generalized autoregressive conditional heteroskedasticity) is used. The selection of optimal families and parameters of copula models is carried out. The adequacy of the obtained models is checked and the results of the study of the relationship between the series are analyzed.Results. An algorithm has been developed for a relatively new approach to using copulas in conjunction with the ARMA-GJR-GARCH model. The approach was used to study the impact of coronavirus in the context of the Russian economy. It is revealed that during the COVID-19 period the dependence between different stocks increases. It is shown that the effect of volatility in financial series increases after the outbreak of the pandemic.Conclusion. The research algorithm using copula models in conjunction with the ARMA-GJR-GARCH process has shown its feasibility. This approach can be used with other GARCH-type models to study finance and other areas.

A proposed model to investigate the dynamic response of stay cables with viscous damper

Viscous dampers commonly mitigate structural vibrations, and various models exist to capture their nonlinear behavior. This article proposes a Hysteretic Maxwell model obtained by evolving the standard Maxwell model to effectively integrate the hysteresis effect. The model entails only a limited number of parameters. The optimized model parameters are identified by fitting model predictions with reported experimental measurements. A numerical case study is conducted, focusing on the longest stay cable of the Rades-La Goulette cable-stayed bridge. Simulation results emphasize the significant improvement of the proposed model over its predecessor, showcasing reductions in both free and forced first-mode vibrations.

Improved SVM-LSTM-based resource flow forecasting for the low-carbon urban distribution grid

Resource flow supports the delivery of products and services and plays a vital role in the low-carbon urban distribution grid. Therefore, reasonable forecasting of the resource flow is essential for financial decision-making. Through the trained model, the resource flow forecasting process can be simplified and one-click forecasting can be realized. However, this method relies on the selection and optimization of model parameters, where poor parameter choices can significantly impact the forecasting accuracy. This paper first introduces a model for identifying key influencing factors in resource flow data, incorporating an elastic network and gray correlation analysis. Subsequently, a resource flow forecasting method based on improved support vector machines–long- and short term memory (SVM-LSTM) is proposed. Finally, the superior performance of the proposed method is validated through simulations.

Hybrid Tiki Taka and Mean Differential Evolution based Weibull distribution: A comprehensive approach for solar PV modules parameter extraction with Newton-Raphson optimization

Effective parameter extraction is crucial in modeling and analyzing complex systems, particularly photovoltaic (PV) cells/modules. Therefore, it is essential to develop a robust optimization model that can effectively determine the optimal parameters of PV models. This study introduces a novel metaheuristic algorithm, Tiki Taka Algorithm (TTA), inspired by sports strategies, particularly the renowned tiki-taka style. The innovation lies in the hybridization of TTA with the Mean Differential Evolution based on Weibull distribution (MDEW). The resultant optimal parameters obtained from this hybridization serve as the initial guess for Newton-Raphson (NR), a critical step that ensures the estimated current closely aligns with the measured current, leading to a minimized Root Mean Square Error (RMSE). The hybrid approach leverages the excellent exploration capabilities of Weibull distribution and the exploitation strength of the Mean Differential Evolution (MeanDE) mutation, offering a comprehensive solution for navigating complex optimization landscapes. The proposed TTA-MDEW effectively identifies various parameters in PV models, including single diodes, double diodes, and PV modules. The findings show that TTA-MDEW holds its ground against the most sophisticated optimization methods in terms of reliability, accuracy, and speed of convergence. Additionally, data from real-world manufacturer datasheets reveal that our method delivers exceptionally precise results under varying irradiance and temperature conditions. Therefore, these outcomes establish the TTA-MDEW as an effective tool for extracting precise parameters from various PV models, enhancing the modeling of PV systems.

External Validation and Further Exploration of Fall Prediction Models Based on Questionnaires and Daily-Life Trunk Accelerometry

Ambulatory measurements of trunk accelerations can provide valuable insight into the amount and quality of daily life activities. Such information has been used to create models to identify individuals at high risk of falls. However, external validation of such prediction models is lacking, yet crucial for clinical implementation. We externally validated 3 previously described fall prediction models. Complete questionnaires and 1-week trunk acceleration data were obtained from 263 community-dwelling people (mean age 71.8 years, 68.1% female). To validate models, we first used the coefficients and optimal cutoffs from the original cohort, then recalibrated the original models, as well as optimized parameters based on our new cohort. Among all participants, 39.9% experienced falls during a 6-month follow-up. All models showed poor precision (0.20-0.49), poor sensitivity (0.32-0.58), and good specificity (0.45-0.89). Calibration of the original models had limited effect on model performance. Using coefficients and cutoffs optimized on the external cohort also had limited benefits. Lastly, the odds ratios in our cohort were different from those in the original cohort, which indicated that gait characteristics, except for the index of harmonicity ML (medial-lateral direction), were not statistically associated with falls. Fall risk prediction in our cohort was not as effective as in the original cohort. Recalibration as well as optimized model parameters resulted in a limited increase in accuracy. Fall prediction models are highly specific to the cohort studied. This highlights the need for large representative cohorts, preferably with an external validation cohort.

Enhanced Air Quality Prediction Using a Coupled DVMD Informer-CNN-LSTM Model Optimized with Dung Beetle Algorithm.

Accurate prediction of air quality is crucial for assessing the state of the atmospheric environment, especially considering the nonlinearity, volatility, and abrupt changes in air quality data. This paper introduces an air quality index (AQI) prediction model based on the Dung Beetle Algorithm (DBO) aimed at overcoming limitations in traditional prediction models, such as inadequate access to data features, challenges in parameter setting, and accuracy constraints. The proposed model optimizes the parameters of Variational Mode Decomposition (VMD) and integrates the Informer adaptive sequential prediction model with the Convolutional Neural Network-Long Short Term Memory (CNN-LSTM). Initially, the correlation coefficient method is utilized to identify key impact features from multivariate weather and meteorological data. Subsequently, penalty factors and the number of variational modes in the VMD are optimized using DBO. The optimized parameters are utilized to develop a variationally constrained model to decompose the air quality sequence. The data are categorized based on approximate entropy, and high-frequency data are fed into the Informer model, while low-frequency data are fed into the CNN-LSTM model. The predicted values of the subsystems are then combined and reconstructed to obtain the AQI prediction results. Evaluation using actual monitoring data from Beijing demonstrates that the proposed coupling prediction model of the air quality index in this paper is superior to other parameter optimization models. The Mean Absolute Error (MAE) decreases by 13.59%, the Root-Mean-Square Error (RMSE) decreases by 7.04%, and the R-square (R2) increases by 1.39%. This model surpasses 11 other models in terms of lower error rates and enhances prediction accuracy. Compared with the mainstream swarm intelligence optimization algorithm, DBO, as an optimization algorithm, demonstrates higher computational efficiency and is closer to the actual value. The proposed coupling model provides a new method for air quality index prediction.

Shape Pattern Recognition of Building Footprints Using t-SNE Dimensionality Reduction Visualization

The shape pattern recognition of building footprints stands as a pivotal concern within GIS spatial cognition. In this study, we introduce a novel approach for the shape recognition of building footprints, leveraging t-distributed stochastic neighbor embedding (t-SNE) dimensionality reduction visualization. First, the Canonical Time Warping (CTW) algorithm is employed to gauge the shape similarity distance of building footprints. Subsequently, the t-SNE model is utilized to map the building footprints, featuring varying numbers of coordinate vertices, onto points within the Cartesian coordinate system. The shape similarity distance serves as the input to the t-SNE model for parameter optimization. Lastly, building footprint shapes are identified through the inherent clustering patterns of points using a Gaussian Mixture Model (GMM). Experimental results demonstrate the method’s robustness to the translation, rotation, scaling, and mirroring of geometric objects, while effectively measuring shape similarity between building footprints. Furthermore, diverse types of building footprints are discernible through natural clustering in low-dimensional spaces, aligning closely with human visual perception.

Collaborative Optimization Model of Blast Furnace Raw Materials and Operating Parameters Based on Intelligent Calculation

Collaborative Optimization Model of Blast Furnace Raw Materials and Operating Parameters Based on Intelligent Calculation

Thermodynamic re-optimization of the CaO–SiO2 system integrated with experimental phase equilibria studies

CaO–SiO2 is the key system in ferrous and non-ferrous metallurgy, ceramic manufacture, cement production, and other applications. A number of discrepancies and gaps in knowledge has been identified and resolved since the last thermodynamic optimization of this system. This study reports new experimental phase equilibria data measured using recent advances in equilibration, sample quenching, and Electron Probe X-ray Microanalysis (EPMA) technique. An updated self-consistent set of thermodynamic model parameters is provided. Most importantly, these updates are integrated with a complete re-assessment of the 20-component Cu–Pb–Zn–Fe–Ca–Si–O–S–Al–Mg–Cr–Na–As–Sn–Sb–Bi–Ag–Au–Ni–Co system directly relevant to applications in the ferrous and non-ferrous metallurgical industries. To obtain a large single set of model parameters, significant advances were made in the computational approach, with a focus on simultaneous parallel optimization of binary and ternary model parameters using an experimental dataset combining binary, ternary, and multicomponent information. The Modified Quasichemical Formalism is used for the liquid slag phase. Thermodynamic properties of solid phases and liquid endmembers are completely revised following the recommendations for the third generation of CALPHAD databases. Other notable changes include the revision of the melting temperature of CaO, justified by extrapolations from the multicomponent systems, as well as a physically realistic heat capacity function for metastable SiO2 below the glass transition temperature. These updated properties expand the areas of application of the database to amorphous and partially crystallized slags at ambient temperatures, such as thermodynamics and kinetics of leaching of toxic elements in an aqueous environment. The fundamental limitations of the existing Modified Quasichemical Formalism are also discussed, along with strategies for addressing them.

Ultrafast‐and‐Ultralight ConvNet‐Based Intelligent Monitoring System for Diagnosing Early‐Stage Mpox Anytime and Anywhere

Due to the absence of more efficient diagnostic tools, the spread of mpox continues to be unchecked. Although related studies have demonstrated the high efficiency of deep learning models in diagnosing mpox, key aspects such as model inference speed and parameter size have always been overlooked. Herein, an ultrafast and ultralight network named Fast‐MpoxNet is proposed. Fast‐MpoxNet, with only 0.27 m parameters, can process input images at 68 frames per second (FPS) on the CPU. To detect subtle image differences and optimize model parameters better, Fast‐MpoxNet incorporates an attention‐based feature fusion module and a multiple auxiliary losses enhancement strategy. Experimental results indicate that Fast‐MpoxNet, utilizing transfer learning and data augmentation, produces 98.40% classification accuracy for four classes on the mpox dataset. Furthermore, its Recall for early‐stage mpox is 93.65%. Most importantly, an application system named Mpox‐AISM V2 is developed, suitable for both personal computers and smartphones. Mpox‐AISM V2 can rapidly and accurately diagnose mpox and can be easily deployed in various scenarios to offer the public real‐time mpox diagnosis services. This work has the potential to mitigate future mpox outbreaks and pave the way for developing real‐time diagnostic tools in the healthcare field.

ESC-NAS: Environment Sound Classification Using Hardware-Aware Neural Architecture Search for the Edge

The combination of deep-learning and IoT plays a significant role in modern smart solutions, providing the capability of handling task-specific real-time offline operations with improved accuracy and minimised resource consumption. This study provides a novel hardware-aware neural architecture search approach called ESC-NAS, to design and develop deep convolutional neural network architectures specifically tailored for handling raw audio inputs in environmental sound classification applications under limited computational resources. The ESC-NAS process consists of a novel cell-based neural architecture search space built with 2D convolution, batch normalization, and max pooling layers, and capable of extracting features from raw audio. A black-box Bayesian optimization search strategy explores the search space and the resulting model architectures are evaluated through hardware simulation. The models obtained from the ESC-NAS process achieved the optimal trade-off between model performance and resource consumption compared to the existing literature. The ESC-NAS models achieved accuracies of 85.78%, 81.25%, 96.25%, and 81.0% for the FSC22, UrbanSound8K, ESC-10, and ESC-50 datasets, respectively, with optimal model sizes and parameter counts for edge deployment.

Evaluasi Model Jaringan Saraf Tiruan Berbasis LSTM dalam Memprediksi Fluktuasi Harga Bitcoin

Amid the highly volatile fluctuations in the cryptocurrency market, the ability to accurately predict Bitcoin prices becomes crucial for investors and financial analysts. This study aims to develop a predictive model using Long Short-Term Memory (LSTM) Neural Networks, a specific form of recurrent neural network, to predict Bitcoin prices. Historical data on daily closing prices of Bitcoin from 2015 to 2023 was used to train and test the model. Following data preprocessing, which included normalization and the creation of a time series dataset, the LSTM model was constructed with two LSTM layers and two dense layers to enhance the predictive analysis. The model was trained with the data split into 80% for training and 20% for testing. Results show that the LSTM model was able to produce fairly accurate predictions with a low loss value on the test data. Further evaluation through comparison with baseline models showed significant improvements in predictive accuracy. This research demonstrates the potential application of advanced machine learning techniques in financial analysis, particularly in predicting the prices of highly volatile assets like Bitcoin. With continuous improvements to the model architecture and parameter optimization, Bitcoin price predictions could become more reliable, helping stakeholders make more informed investment decisions.

Modeling and Design Parameter Optimization to Improve the Sensitivity of a Bimorph Polysilicon-Based MEMS Sensor for Helium Detection.

Helium is integral in several industries, including nuclear waste management and semiconductors. Thus, developing a sensing method for detecting helium is essential to ensure the proper operation of such facilities. Several approaches can be used for helium detection, including based on the high thermal conductivity of helium, which is several times higher than air. This work utilizes the high thermal conductivity of helium to design and analyze a bimorph MEMS sensor for helium sensing applications. COMSOL Multiphysics software (version 6.2) is used to carry out this investigation. The sensor is constructed from poly-silicon and SiO2 materials with a trenched cantilever beam configuration. The sensor is electrically heated, and its morphed displacement depends on the surrounding gas's composition, which decreases in the presence of helium. Several factors were investigated to probe their effect on the sensor's sensitivity to helium, including the thickness of the poly-silicon layer, the configuration of the trench, and the thickness and location of SiO2 layer. The simulations showed that the best performance, up to 2 ppm helium detection level, can be achieved with thinner beams and medium trench lengths.

Optimization of Cohesive Parameters in the Interfacial Transition Zone of Rubberized Concrete Based on the Response Surface Method.

Rubber concrete has been applied to a certain extent in fatigue-resistant structures due to its good durability. Based on a cohesive model of rubber composed of a five-phase material containing mortar, aggregate, rubber, aggregate-mortar interfacial transition zone (ITZ), and rubber-mortar ITZ, this paper studies the influence of the cohesive parameters in the rubber-mortar ITZ on the fatigue problem of rubber concrete on the mesoscopic scale. As the weak part of cement-based composite materials, the ITZ has a great influence on the mechanical properties and durability of concrete, but the performance of the ITZ is difficult to test in macro experiments, resulting in difficulties in determining its simulation parameters. Based on the cohesive model with a rubber content of 5%, this study uses Monofactor analysis and the Plackett-Burman test to quickly and effectively determine the primary and secondary influences of the cohesive model parameters in the rubber-mortar ITZ; further, the response surface method is used to optimize the cohesive parameters in the rubber-mortar ITZ, and the numerical simulation results after optimizing the cohesive parameters are compared and analyzed with the simulation results before optimization. The results show that, under the setting of the optimized parameters, the simulation results of each item of the optimal cohesive model parameters in the rubber-mortar ITZ are in line with the reality and closer to the experimental data, and they are also applicable to rubber concrete models with different rubber dosing.

Biokinetics modelling of lycopene-producing E. coli fermentation using PAT methodology

Process analytical technology (PAT), which espouses the use of in-line analytics to monitor critical process parameters (CPPs), critical quality attributes (CQAs) and mathematical analyses, was employed to elucidate underlying carbon-source metabolism of a lycopene-producing E. coli strain during non-induced and induced batch fermentations. In-line dielectric and Raman spectroscopies were deployed to monitor real-time culture biomass viability (X), primary substrate glucose (S), and intracellular lycopene production (P), together with off-line HPLC quantification of broth acetate (A). In-line PAT monitoring enabled identification of two distinct metabolic regimes during induced batch run with lycopene accumulation. Biokinetics mathematical models using differential-algebraic equations and Monod-type conversions were formulated to explain experimentally measured dynamic trends of the state variables X, S, A and P during the batch runs. Their optimized model parameters and seven dimensionless ratios reflected changes in concentrations or rates relative to glucose, acetate, or lycopene. The calculated rates of culture growth, glucose utilization, acetate accumulation, and lycopene production revealed salient underlying carbon metabolic shifts and transient trends that explained phenomenological observations: such as growth patterns, carbon source usage, overflow mechanism, cellular affinity or inhibitory effects, and lycopene cytotoxicity. These parameters and dimensionless ratios could be used to compare novel strains, develop in silico simulations for scale-up or troubleshoot batch-to-batch variations.

A novel artificial hummingbird algorithm improved by natural survivor method

The artificial hummingbird algorithm (AHA) has been applied in various fields of science and provided promising solutions. Although the algorithm has demonstrated merits in the optimization area, it suffers from local optimum stagnation and poor exploration of the search space. To overcome these drawbacks, this study redesigns the update mechanism of the original AHA algorithm with the natural survivor method (NSM) and proposes a novel metaheuristic called NSM-AHA. The strength of the developed algorithm is that it performs population management not only according to the fitness function value but also according to the NSM score value. The adopted strategy contributes to NSM-AHA exhibiting powerful local optimum avoidance and unique exploration ability. The optimization ability of the proposed NSM-AHA algorithm was compared with 21 state-of-the-art algorithms over CEC 2017 and CEC 2020 benchmark functions with dimensions of 30, 50, and 100, respectively. Based on the Friedman test results, it was observed that NSM-AHA ranked 1st out of 22 competitive algorithms, while the original AHA ranked 8th. This result highlights that the NSM update mechanism provides a remarkable evolution in the convergence performance of the original AHA algorithm. Furthermore, two constrained engineering problems including the optimization of single-diode solar cell model (SDSCM) parameters and the design of a power system stabilizer (PSS) are solved with the proposed algorithm. The NSM-AHA algorithm provided better results compared to other algorithms with a value of 9.86E − 04 root mean square error for SDSCM and 1.43E − 03 integral time square error for PSS. The experimental results showed that the proposed NSM-AHA is a competitive optimizer for solving global and engineering problems.

Analysis of Unmanned Aerial Vehicle-Assisted Cellular Vehicle-to-Everything Communication Using Markovian Game in a Federated Learning Environment

The paper studies a game theory model to ensure fairness and improve the communication efficiency in an unmanned aerial vehicle (UAV)-assisted cellular vehicle-to-everything (C-V2X) communication network using Markovian game theory in a federated learning (FL) environment. The UAV and each vehicle in a cluster utilized a strategy-based mechanism to maximize their model completion and transmission probability. We modeled a two-stage zero sum Markovian game with incomplete information to jointly study the utility maximization of the participating vehicles and the UAV in the FL environment. We modeled the aggregating process at the UAV as a mixed strategy game between the UAV and each vehicle. By employing Nash equilibrium, the UAV determined the probability of sufficient updates received from each vehicle. We analyzed and proposed decision-making strategies for several representative interactions involving gross data offloading and federated learning. When multiple vehicles enter a parameter transmission conflict, various strategy combinations are evaluated to decide which vehicles transmit their data to the UAV. The optimal payoff in a transmission window is derived using the Karush–Khun–Tucker (KKT) optimality conditions. We also studied the variation in optimal model parameter transmission probability, average packet delay, UAV transmit power, and the UAV–Vehicle optimal communication probabilities under different conditions.

Multicycle Parameter Estimations in Coupled Earth System Models Based on Multiscale Sensitivity Responses in the Context of Low-Order Models

Abstract Climate model simulations tend to drift away from the real world because of model errors induced by an incomplete understanding and implementation of dynamics and physics. Parameter estimation uses data assimilation methods to optimize model parameters, which minimizes model errors by incorporating observations into the model through state-parameter covariance. However, traditional parameter estimation schemes that simultaneously estimate multiple parameters using observations could fail to reduce model errors because of the low signal-to-noise ratio in the covariance. Here, based on the saturation time scales of model sensitivity that depend on different parameters and model components, we design a new multicycle parameter estimation scheme, where each cycle is determined by the saturation time scale of sensitivity of the model state associated with observations in each climate system component. The new scheme is evaluated using two low-order models. The results show that due to high signal-to-noise ratios sustained during the parameter estimation process, the new scheme consistently reduces model errors as the number of estimated parameters increases. The new scheme may improve comprehensive coupled climate models by optimizing multiple parameters with multisource observations, thereby addressing the multiscale nature of component motions in the Earth system. Significance Statement Parameter estimation is used to reduce model errors by optimizing the model parameter values with observational information, which is important for improving long-term predictions. In previous parameter estimation methods, multisource observations have not yet been sufficiently used because the quality and dimension size of the optimized parameters are limited. Here, based on the multiscale nature of component motion in the Earth system, we develop a new parameter estimation method that makes full use of multisource observations. The new method processes the parameters being estimated sequentially according to sensitivity magnitudes and saturation time scales so that the parameters can be continuously optimized. This new method has large application potential for weather and climate reanalyses and predictions.

Cutting Energy Consumption Modeling by Considering Tool Wear and Workpiece Material Properties for Multi-Objective Optimization of Machine Tools

The increasing demand for energy is leading to global depletion of fossil fuels and growing environmental pressures, which are issues that need to be addressed. Machine tools are basic energy-consuming equipment in manufacturing systems. However, existing theoretical models ignore tool wear as well as workpiece material properties. This makes it difficult to further improve the accuracy of the model. Therefore, this study begins with the point of view of energy dissipation in the metal material removal process. A milling power model for computer numerical control (CNC) machines, considering tool wear and workpiece material properties during machining, is established. At the same time, milling is taken as the research object. A multi-objective cutting parameter optimization model is established to ensure the surface quality of the workpiece. In addition, the cutting energy consumption is taken into account in the developed models. Based on the multi-objective manta ray foraging optimization algorithm (MOMRFO), the Pareto-optimal solution set under multiple cutting conditions is solved. Finally, the experimental results of optimized parameters are compared with empirical parameters. The average prediction accuracy of the proposed energy consumption prediction model is above 91%. The experiments show that machining quality improves by optimizing the cutting parameters, with SEC, MRR, and Ra increasing by more than 44%, 53%, and 38%, respectively. The goals of reducing energy consumption and increasing productivity are achieved.

Evaluation of the physical characteristics of reinforced concrete subject to corrosion using a poro-elastic acoustic model inversion technique applied to ultrasonic measurements

The use of reinforced concrete is foundational to modern infrastructure. Acknowledging this, it is imperative that health monitoring techniques be in place to study corrosion within these structures. By using a non-destructive method for detecting the early formation of cracks within reinforced concrete, the method presented in this paper seeks to improve upon traditional techniques of monitoring corrosion, within reinforced concrete structures. In this paper, the authors present a method to evaluate the physical characteristics of reinforced concrete subject to corrosion using a poro-elastic acoustic model inversion technique applied to a set of ultrasonic measurements, which constitutes a novel approach to the problem of observing the impact of corroding rebars and resulting concrete damage. A non-contact ultrasonic transducer is operated at a carrier frequency of 500 [kHz], with a layer of saltwater separating the sensor from the concrete surface. Following this non-contact measurement collection of the surface and rebar echo responses, a poro-elastic model is used to model the sound propagation, through an adapted version of the Biot-Stoll model. At first, a set of default parameters, obtained from the physical characteristics of the reinforced concrete, are used to match experimental and simulated acoustic signature of the sample. Performing statistical averaging along the corroding rebar within three samples over a period of nearly nine months, a small but monotonous increase in the distance between the concrete surface and the top of the rebar, indicating gradual corrosion of the rebar. Next, a non-linear optimization algorithm is used to optimize the match between measured and simulated echoes. Through the implementation of this model parameter optimization, the root mean square error between measured and simulated responses was reduced by 63.7% for the full signal, and 62.6% for the rebar echo.