Optimal Radial Basis Function Research Articles

A Dual Filter Based on Radial Basis Function Neural Networks and Kalman Filters with Application to Numerical Wave Prediction Models.

The aim of this study is to introduce and evaluate a dual filter that combines Radial Basis Function neural networks and Kalman filters to enhance the accuracy of numerical wave prediction models. Unlike the existing methods, which focus solely on systematic errors, the proposed framework concurrently targets both systematic and non-systematic parts of forecast errors, significantly reducing the bias and variability in significant wave height predictions. The produced filter is self-adaptive, identifying optimal Radial Basis Function network configurations through an automated process involving various network parameters tuning. The produced computational system is assessed using a time-window procedure applied across divergent time periods and regions in the Aegean Sea and the Pacific Ocean. The results reveal a consistent performance, outperforming classic Kalman filters with an average reduction of 53% in bias and 28% in RMSE, underlining the dual filter's potential as a robust post-processing tool for environmental simulations.

Global Stochastic Comprehensive Sensitivity Analysis Based on Robustness Grouping and Improved Pelican Algorithm-Optimized Radial Basis Function Neural Network

Abstract Modeling analysis is one of the important means to analyze practical engineering, and as technology continues to evolve, various models are getting closer and closer to reality, while at the same time, there are more and more parameters in the models. It is important to analyse the impact of these parameters on the project to assist engineers in making plans or decisions. Sensitivity analysis (SA) can describe the effect of changes in these parameters on the model. However, complex models often have dozens or even hundreds of parameters, and most current SA methods struggle to deal reliably and effectively with these high-dimensional problems. In addition, it is difficult to obtain the sensitivity of continuous points in the parameter space with traditional SA methods. Therefore, this paper proposes a method that combines adaptive grouping and an Improved Pelican Optimization Algorithm for an optimal radial basis function (IPOA-RBF) agent model to solve these problems. Firstly, a clustering grouping method considering grouping robustness is established to obtain objective and stable parameter grouping results in high-dimensional sensitivity analysis. Secondly, a proxy model based on radial basis function neural network and an improved Pelican optimization algorithm are proposed to capture the logic of the proxy model to obtain the parameter sensitivity of continuous points in the parameter space. Finally, the superiority and applicability of this method is verified using an arch dam simulation model.

Systemic Financial Risk Forecasting: A Novel Approach with IGSA-RBFNN

Accurate measurement of systemic financial risk is crucial for maintaining the stability of financial markets. Taking China as the subject of investigation, the Chinese Financial Stress Index (CFSI) indicator system was constructed by integrating six dimensions and employing Gray Relation Analysis (GRA) to reduce the dimensionality of the indicators. The CFSI was derived using the Attribute Hierarchy Model (AHM) method with the Criteria Importance Through the Intercriteria Correlation (CRITIC) method, and an Improved Gravitational Search Algorithm (IGSA)-optimized Radial Basis Function Neural Network (RBFNN) was proposed for out-of-sample prediction of CFSI trends from 2024 to 2026. By analyzing the trends in financial pressure indicators, the intricate relationship between financial pressure and economic activity can be effectively discerned. The research findings indicate that (1) the CFSI is capable of accurately reflecting the current financial stress situation in China, and (2) the IGSA-RBFNN demonstrates strong robustness and generalization capabilities, predicting that the CFSI index will reach a peak value of 0.543 by the end of 2024, and there exists a regular pattern of stress rebound towards the end of each year. The novel methodology enables policymakers and regulatory authorities to proactively identify potential risks and vulnerabilities, facilitating the formulation of preventive measures.

The Application and Research of Particle Swarm Optimization Radial Basis Function Network Driven by Edge Computing in Bogie Fault Diagnosis

The bogie system is a key system that affects the safety and quality of high-speed train operation. Constructing a fault diagnosis model for the bogie system can effectively improve the safety and comfort of high-speed train operation. The traditional modeling method uses the BP neural network to fit the temperature and other parameters of the bogie system. However, because the BP neural network is prone to fall into local minima, slow convergence and poor diagnostic accuracy, this paper proposes a radial basis function network bogie fault diagnosis model based on particle swarm optimization based on edge computing. The model combines edge computing and particle swarm optimization algorithm to improve the accuracy and real-time of bogie fault diagnosis. By implementing model training and inference on edge devices, data transmission latency has been reduced and diagnostic efficiency has been improved. A particle radial basis neural network (PSRB) was designed using a highly convergent particle swarm optimization algorithm, and the parameters of the radial basis neural network (RBF Neural Networks) were optimized using the Particle Swarm Optimization algorithm. Based on the complexity of the input parameters of the bogie system, determine the input and output parameters of the model, and use particle swarm optimization algorithm to search for the optimal values of the basis function center, width, and output layer weight threshold of the RBF neural network. The composite algorithm was applied to the fault diagnosis of the bogie system, and a particle radial basis neural network bogie fault diagnosis model was designed. The simulation and experimental results of the model show that the diagnostic model can effectively improve the identification accuracy of fault diagnosis, with a minimum error accuracy of 0.0255, saving computation time. The computation time is reduced to 2.9 seconds, eliminating the influence of non target parameters on the inversion results. This model can also be used in other systems of high-speed trains and has practical application value.

A PSO-RBF prediction method on flow corrosion of heat exchanger using the industrial operations data

With the development of the petrochemical industry, corrosion problems of special equipment occur frequently. How to achieve accurate prevention and control of equipment flow corrosion problems become a key factor in ensuring the safety of equipment processes. This paper combines industrial field operation data, through the isolated forest algorithm for the screening of abnormal values, focusing on the analysis of the type of corrosion in the heat exchanger. A Particle Swarm Optimization optimized Radial Basis Function (PSO-RBF) prediction model was constructed to achieve fast prediction of ammonium crystallization temperature, and the Particle Swarm Optimization (PSO) algorithm was optimized using an adaptive weight optimization scheme. It shows that the optimized model error is within 3%, while the prediction accuracy is improved by 9.54%, and the coefficient of determination has also been improved. This paper also compares and analyzes several mature algorithms commonly used today, and the results show that the model has significant advantages in terms of prediction performance. In addition, the model can be applied to the condition inspection of petrochemical equipment, providing a practical guarantee for equipment operation, and reducing the risk of enterprise operation and maintenance.

Construction and analysis of a business English classroom teaching quality evaluation system based on multimodal neural network model assessment

In this paper, we propose a method for effectively evaluating the quality of business English teaching in colleges and universities. The approach is based on a multimodal neural network model integrated with grey correlation analysis. By employing the optimal data clustering criterion, we identify teaching quality evaluation indices. Subsequently, we establish a teaching quality evaluation index system using a genetic algorithm (GA) optimized Radial Basis Function (RBF) neural network. Grey correlation analysis is then applied to assess the quality of business English teaching by considering the relationship between the correlation degree and the evaluation level. The results indicate a correlation degree exceeding 0.90, signifying excellent teaching quality. The reliability of the selected evaluation indicators, assessed through retesting, surpasses 0.700, validating the evaluation results.

Investigating the effect of textural properties on CO2 adsorption in porous carbons via deep neural networks using various training algorithms

The adsorption of carbon dioxide (CO2) on porous carbon materials offers a promising avenue for cost-effective CO2 emissions mitigation. This study investigates the impact of textural properties, particularly micropores, on CO2 adsorption capacity. Multilayer perceptron (MLP) neural networks were employed and trained with various algorithms to simulate CO2 adsorption. Study findings reveal that the Levenberg–Marquardt (LM) algorithm excels with a remarkable mean squared error (MSE) of 2.6293E−5, indicating its superior accuracy. Efficiency analysis demonstrates that the scaled conjugate gradient (SCG) algorithm boasts the shortest runtime, while the Broyden–Fletcher–Goldfarb–Shanno (BFGS) algorithm requires the longest. The LM algorithm also converges with the fewest epochs, highlighting its efficiency. Furthermore, optimization identifies an optimal radial basis function (RBF) network configuration with nine neurons in the hidden layer and an MSE of 9.840E−5. Evaluation with new data points shows that the MLP network using the LM and bayesian regularization (BR) algorithms achieves the highest accuracy. This research underscores the potential of MLP deep neural networks with the LM and BR training algorithms for process simulation and provides insights into the pressure-dependent behavior of CO2 adsorption. These findings contribute to our understanding of CO2 adsorption processes and offer valuable insights for predicting gas adsorption behavior, especially in scenarios where micropores dominate at lower pressures and mesopores at higher pressures.

DRNAS: Differentiable RBF neural architecture search method considering computation load in adaptive control

In this work, we investigated an online differential neural network search control algorithm using a backstepping method with a radial basis function (RBF) neural network (NN) framework. In this approach, we mainly focused on searching a neural network architecture with optimal control performance and optimal computation load by learning NN parameters among a finite number of RBF NNs with different architectures. The previous works on RBFNN and backstepping methods mainly considered the control performance of systems, and the computation load limitations of control computers were rarely considered. In this paper, we herein propose a differentiable RBF neural architecture search (DRNAS) method. First, we built a hypernetwork and constructed an appropriate optimization objective function with information of a tracking error and a computation load. This hypernetwork consists of different networks with weight parameters. Then, through backpropagation and based on the gradient descent method, we updated the parameters of the hypernetwork and determined the optimal RBF NN architecture in the search space. Finally, we performed simulations to verify the effectiveness of the proposed method, where we designed an RBF NN adaptive backstepping controller for aircraft pitch rate dynamics and used the DRNAS method to train the hypernetwork based on different mission scenarios. The simulation results verified that the proposed method can effectively balance the controller’s tracking capability with its computation load.

Reliability control and calculation for agri-equipments based on an intelligent algorithm

In the research, an agricultural machinery reliability analysis method based on fusion algorithm is proposed, a optimal radial basis function neural network and M-C statistical test method are mixed to obtain an agricultural machinery reliability. This mixed model is used to reliability design and calculation of a cotton picker, the simulation model of reliability control and calculation for a cotton picker based on the mixed algorithm is set up, and reliability of the level spindle of a cotton picker is computed through the mixed method, and the effect of important factors on the cotton picker is predicted. The level spindle is critical force-bearing parts of a cotton picker and breakdown occurs frequently, their reliability control and optimization are key problems that need to be solved urgently, this study builds an innovative approach for the reliability optimization and design of agricultural equipments.

Analysis of hydraulic performance in a structured packing column for air/water system: RSM and ANN modeling

The study investigated the hydraulic characteristics of a structured packing column for an air/water system using two modeling approaches: artificial neural network (ANN) and response surface methodology (RSM). Seven parameters were identified as influential factors for pressure drop and liquid hold-up. Two correlations for the responses were proposed using the two-factor interaction (2FI) model based on the RSM-central composite design approach. In the ANN modeling, two algorithms were applied: multi-layer perceptron (MLP) and radial basis function (RBF). The optimal MLP structure using the Bayesian Regularization (trainbr) algorithm had two hidden layers, 16 and 8 neurons, and the optimal RBF structure had 42 neurons. The best MSE performance of the MLP network was 0.0938 and 0.0083 for pressure drop and hold-up, respectively, at 16 epochs. The best MSE performance of the RBF network was 0.0685 and 0.0140 for pressure drop and hold-up, respectively, at 42 epochs. Both the ANN and RSM models provided reliable predictions of the experimental data. In addition, ANN's prediction performance (R2 = 0.993) was somewhat better than RSM's (R2 = 0.926). The results showed that gas factor and liquid load had the greatest effect on pressure drop and liquid hold-up, respectively.

Feature selection for image classification using ESSO

Feature selection is one of the major components of the data processing flow that correctly selects real-time entities for categorization. It is utilized in numerous research fields, including the machine learning approach. Feature selection and classification are beneficial to the processing of biomedical data in high-importance, high-dimensional datasets. Due to numerous obstacles in research, the current implementations are inadequate for predicting classification accuracy. To handle the classification challenge, we require dedicated neural network and classification model approaches. Initial features are selected using a method called "fuzzy c-means clustering with rough set theory" and are subsequently classified using "support vector machines." The learning machines' accuracy is seriously harmed by irrelevant and redundant features. The curse of dimensionality makes it difficult to locate data clusters in high-dimensional space. Data in the irrelevant dimensions may cause a lot of noise when the dimensionality grows. In addition, the current approach has a significant flaw: it is extremely time-consuming. The proposed solution used efficient feature subset selection in high-dimensional data to fix these problems. To begin with, our recommended method used Enhanced Social Spider Optimization (ESSO) computation, in which the standard Social Spider Optimization is improved with the aid of optimal radial based calculation to select the best highlights. When categorizing data, the Optimal Radial Basis Function Neural Network (ORBFNN) is used. Methods for calculating Artificial Bee Colony (ABC) are used to streamline RBFNN's sufficiency in characterizing smaller scale show information.

A novel road traffic flow prediction model using hybrid Particle Swarm Optimization (PSO) and Radial Basis Function Neural Network (RBFNN)

<p>Traffic congestion is a major problem in urban areas, leading to increased travel time, air pollution, and fuel consumption. Road impedance function, which describes the relationship between traffic status and travel time, plays an important role in predicting travel time and managing traffic flow. Traditional methods for estimating road impedance function rely on manual calibration and may have limitations in reflecting the complexity of traffic patterns. To address these challenges, researchers have proposed various machine learning models for predicting travel time and road impedance function. In this paper, a hybrid particle swarm optimization—radial basis function neural network model is proposed for improving the accuracy of the road impedance function. The model takes into consideration various vehicle types and is validated using travel time data collected from a road section in Huai’an City, China. The effectiveness of the proposed model is compared with the traditional road impedance function calibrated by nonlinear regression. The experimental results indicate that the Mean Relative Error (MRE) of PSORBFNN is increased by 3.89% and 6.28% respectively when compared with DPNR training samples and validation samples. When compared with DPPSO training and validation samples, the MRE of PSORBFNN is increased by 2.87% and 3.3% respectively. These findings suggest that the proposed model could guide and assist traffic engineers and practitioners in predicting travel time on road sections with improved accuracy.</p>

Prediction of shear strength for granular material under the effect of liquid-powder binder using a PSO–RBF neural network model

In this paper, the performance of particle swarm optimization–radial basis function (PSO–RBF) neural network was examined to predict the shear strength of granular material. Direct shear tests were conducted on glass beads (400–600 mm in size) with 2% of liquid content at different powder contents (1, 2, 3, 4, and 5%) as the binder. Hydrated lime (HL), quick lime (QL), calcite, and sodium lignosulfonate (SL) powders were used to compare their shear strength characteristics. The actual loading stress was controlled at five levels (6.9, 10.3, 13.8, 17.3, and 20.7 kPa), and five further levels (24.2, 27.7, 31.2, 34.6, and 38.1 kPa) were used for prediction. Results showed that at 2% of water, the shear strength regularly increased at all amounts of HL, QL, and calcite powder. With the increased SL powder, the shear strength decreased. The actual and predicted maximum shear stress values for different levels of normal stress were fitted using the widely accepted Mohr–Coulomb criterion to determine the internal friction angle and cohesion, and R 2 was improved from 0.98 to 0.99. The PSO–RBF neural network model was a flexible and accurate method for the prediction of the shear strength of granular material.

Profit Suggestion Technique in Agronomics Using a New Heuristic-Based Barnacle Mating Honey Badger Algorithm I-BMHBA

Second phase, the prediction in Minimum Support Price (MSP) is made through detected species. The required data in the price is gathered through online resources that are utilized for the data normalization stage in further. These normalized data are used in the deep feature extraction stage by utilizing the autoencoder and the Conventional Neural Network (CNN) to extract the required deep feature; it is then fused in that stage. Further, these fused features are fed into the optimal feature selection stage to choose the important optimal features by utilizing the newly developed algorithm Intensity-based Barnacle Mating Honey Badger Algorithm (I-BMHBA). Then, the selected features are fed into the Optimized Radial Basis Function + Gated Recurrent Unit (RBF + GRU) to predict MSP prices based on the crop type. The predicted prices are then divided into four shares as well as made the profit suggestion is through training the regional and location crops data. In the end, the Optimized RBF + GRU provide better profitable harvest outcomes. From these investigations, it is proven that the proposed profit suggestion via species prediction and MSP prediction method is better when assimilated with another existing model by utilizing the various performance metrics.

Analysis and prediction of the temporal and spatial evolution of carbon emissions in China's eight economic regions.

Facing increasingly severe environmental problems, as the largest developing country, achieving regional carbon emission reduction is the performance of China's fulfillment of the responsibility of a big government and the key to the smooth realization of the global carbon emission reduction goal. Since China's carbon emission data is updated slowly, in order to better formulate the corresponding emission reduction strategy, it is necessary to propose a more accurate carbon emission prediction model on the basis of fully analyzing the characteristics of carbon emissions at the provincial and regional levels. Given this, this paper first calculated the carbon emissions of eight economic regions in China from 2005 to 2019 according to relevant statistical data. Secondly, with the help of kernel density function, Theil index and decoupling index, the dynamic evolution characteristics of regional carbon emissions are discussed. Finally, an improved particle swarm optimization radial basis function (IPSO-RBF) neural network model is established to compare the simulation and prediction models of China's carbon emissions. The results show significant differences in carbon emissions in different regions, and the differences between high-value and low-value areas show an apparent expansion trend. The inter-regional carbon emission difference is the main factor in the overall carbon emission difference. The economic region in the middle Yellow River (ERMRYR) has the most considerable contribution to the national carbon emission difference, and the main contributors affecting the overall carbon emission difference in different regions are different. The number of regions with strong decoupling between carbon emissions and economic development is increasing in time series. The results of the carbon emission prediction model can be seen that IPSO-RBF neural network model optimizes the radial basis function (RBF) neural network, making the prediction result in a minor error and higher accuracy. Therefore, when exploring the path of carbon emission reduction in different regions in the future, the IPSO-RBF neural network model is more suitable for predicting carbon emissions and other relevant indicators, laying a foundation for putting forward more scientific and practical emission reduction plans.

Autonomous Maneuver Decision of Air Combat Based on Simulated Operation Command and FRV-DDPG Algorithm

With the improvement of UAV performance and intelligence in recent years, it is particularly important for unmanned aerial vehicles (UAVs) to improve the ability of autonomous air combat. Aiming to solve the problem of how to improve the autonomous air combat maneuver decision ability of UAVs so that it can be close to manual manipulation, this paper proposes an autonomous air combat maneuvering decision method based on the combination of simulated operation command and the final reward value deep deterministic policy gradient (FRV-DDPG) algorithm. Firstly, the six-degree-of-freedom (6-DOF) model is established based on the air combat process, UAV motion, and missile motion. Secondly, a prediction method based on the Particle swarm optimization radial basis function (PSO-RBF) is designed to simulate the operation command of the enemy aircraft, which makes the training process more realistic, and then an improved DDPG strategy is proposed, which returns the final reward value to the previous reward value in a certain proportion of time for offline training, which can improve the convergence speed of the algorithm. Finally, the effectiveness of the algorithm is verified by building a simulation environment. The simulation results show that the algorithm can improve the autonomous air combat maneuver decision-making ability of UAVs.

Temperature compensation methods of spin-exchange relaxation-free co-magnetometer

According to the temperature characteristics of spin-free exchange relaxation (SERF) co-magnetometer, three temperature compensation methods are proposed in this paper, including particle swarm optimization radial basis function (PSO-RBF) neural network, Gaussian regression and least squares support vector basis. The effectiveness of the three compensation methods is verified by experiments and compared with the back-propagation (BP) neural network optimized by a genetic algorithm compensation method. In order to improve the effect of temperature compensation, this paper also conducts correlation and cluster analysis on the different positions temperature and output signals of the SERF co-magnetometer, and selects the data of temperature points that are closely related to signal bias changes for model training. Through experimental comparison with traditional linear compensation and BP neural network compensation methods, it is found that PSO-RBF neural network has advantages in training speed, compensation accuracy and robustness. Experiments show that PSO-RBF neural network temperature compensation algorithm improves the stability of the SERF co-magnetometer by more than 53 at room temperature or under artificially imposed temperature changes.

Multi-Phase Permanent Magnet Generator with Halbach Array for Direct Driven Wind Turbine: A Hybrid Technique

ABSTRACT In this paper, a hybrid approach is proposed for Multiphase Halbach Array Permanent Magnet Generator (MHAPMG) in the direct driven wind turbine. The proposed approach is the consolidation of Archimedes optimization algorithm (AOA) and Radial Basis Function Neural Network (RBFNN) named AOA-RBFNN approach. The proposed approach achieves higher efficiency at low speed and it is utilized to improve the lesser Cogging torque with torque ripple and fault tolerance. The proposed generator is compared with Multiphase Surface Mount conventional Permanent Magnet Generator (MSMPMG) for its improved outputs. The proposed generator is used to chose the turbine design and to estimate the output of 1000 W with a speed of 440 RPM and the wind speed of 9 m/s. The proposed approach optimizes the electromagnetic performance of Cogging and back electromotive force. The performance of the proposed Halbach array is analyzed with the regular sequence with multiphase topology based on the induced electromotive force, Cogging Torque, Air gap Flux density, and Harmonic Components. The proposed generator is investigated by finite element analysis (FEA). By then, the performance of the proposed system is activated on MATLAB/Simulink platform. The efficiency of WT using proposed technique, HS, TS, and PSO becomes 98%, 80%, 77%, and 82%, respectively.

Chatter detection in milling process based on the combination of wavelet packet transform and PSO-SVM

Chatter is one of the biggest unfavorable factors during the high speed machining process of a machine tool. It severely affects the surface finish and geometric accuracy of the workpiece. To address this obstacle and improve the quality and efficiency of products, it is significantly essential to detect chatter during machining. Therefore, a multi-feature recognition system for chatter detection on the basis of the fusion technology of wavelet packet transform (WPT) and particle swarm optimization support vector machine (PSO-SVM) was proposed in this paper. Firstly, the original vibration signals collected from the acceleration sensor were processed through wavelet packet transform (WPT). The noise and the irrelevant information were remarkably decreased. In addition, the wavelet packets containing chatter-emerging information were chosen and reconstructed. The fourteen time–frequency domain characteristics of the reconstructed vibration signal were calculated and chosen as the multi-feature vectors of chatter detection. Finally, to obtain the optimal radial basis function parameter g and penalty parameter C of the SVM prediction model, the optimization algorithms of k-fold cross-validation (k-CV), genetic algorithm (GA), and particle swarm optimization (PSO) were employed in optimizing the model parameters of SVM. It was indicated that the PSO-SVM improved obviously the accuracy of chatter recognition than the others. In addition, we applied the optimized SVM prediction model by PSO for detecting chatter state in end milling machining. Chatter recognition results indicated that the model accurately predicted the slight chatter state in advance.

LA-LMRBF: Online and Long-Term Web Service QoS Forecasting

We propose a <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">L</u> ong-term Quality of Service (QoS) forecasting approach using <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">A</u> dvertisement and <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">L</u> evenberg- <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">M</u> arquardt improved <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">R</u> adial <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">B</u> asis <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">F</u> unction (LA-LMRBF)—a novel online QoS forecasting approach. LA-LMRBF aims to accurately predict QoS attributes of Web services in the form of multivariate time series via three stages. First, the phase space reconstruction theory is employed to restore multi-dimensional and nonlinear relations among the multivariate QoS attributes. Second, short-term QoS advertisement data is incorporated to enable long-term QoS forecasting. Finally, an optimized Radial Basis Function (RBF) neural network is constructed to forecast long-term multivariate QoS values, where the Affinity Propagation clustering algorithm is used to determine the number of hidden nodes and the Levenberg-Marquardt (LM) algorithm is utilized to dynamically update some parameters of the RBF neural network. A series of experiments are performed on a mixture of public and self-collected data sets. The results show that LA-LMRBF is superior to the other approaches and more suitable for long-term QoS forecasting.