Optimal Radial Basis Function Neural Network Research Articles

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.

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.

Removal of hydrochlorothiazide from molecular liquids using carbon nanotubes: Radial basis function neural network modeling and culture algorithm optimization

The removal of hydrochlorothiazide (HCT) from molecular liquids on multi-walled carbon nanotubes (MWCNTs) and single-walled carbon nanotubes (SWCNTs) was studied in a batch system. In this present work, multiple linear regression (MLR) and radial basis function neural network (RBFNN) were utilized to forecast the adsorption removal percentage of HCT by both adsorbents. The influences of process variables on the removal efficiency were optimized by culture algorithm (CA) optimization. The results displayed the RBFNN was better than the MLR to simulate removal of HCT by two adsorbents. The optimal RBFNN model using the test dataset predicted HCT removal (%) with the coefficient of determination (R2) values of 0.8460 and 0.9438; mean squared error (MSE) values of 0.0117 and 0.0010, respectively for SWCNTs and MWCNTs. At the optimum value of parameters, the adsorption isotherms could be fitted well by the Langmuir model with adsorption capacity values of 66.225 mg g−1 for MWCNTs and 45.662 mg g−1 for SWCNTs. It was also found that the pseudo second-order and intraparticle diffusion models were more suitable for explaining the adsorption mechanism by CNTs.

Vehicular traffic noise prediction and propagation modelling using neural networks and geospatial information system.

This study proposes a neural network (NN) model to predict and simulate the propagation of vehicular traffic noise in a dense residential area at the New Klang Valley Expressway (NKVE) in Shah Alam, Malaysia. The proposed model comprises of two main simulation steps: that is, the prediction of vehicular traffic noise using NN and the simulation of the propagation of traffic noise emission using a mathematical model. First, the NN model was developed with the following selected noise predictors: the number of motorbikes, the sum of vehicles, car ratio, heavy vehicle ratio (e.g. truck, lorry and bus), highway density and a light detection and ranging (LiDAR)-derived digital surface model (DSM). Subsequently, NN and its hyperparameters were optimised by a systematic optimisation procedure based on a grid search approach. The noise propagation model was then developed in a geographic information system (GIS) using five variables, namely road geometry, barriers, distance, interaction of air particles and weather parameters. The noise measurement was conducted continuously at 15-min intervals and the data were analysed by taking the minimum, maximum and average values recorded during the day. The measurement was performed four times a day (i.e. morning, afternoon, evening, and midnight) over two days of the week (i.e. Sunday and Monday). An optimal radial basis function NN was used with 17 hidden layers. The learning rate and momentum values were 0.05 and 0.9, respectively. Finally, the accuracy of the proposed method achieved 78.4% with less than 4.02dB (A) error in noise prediction. Overall, the proposed models were found to be promising tools for traffic noise assessment in dense urban areas.

An Optimal Radial Basis Function Neural Network Enhanced Adaptive Robust Kalman Filter for GNSS/INS Integrated Systems in Complex Urban Areas.

Inertial Navigation System (INS) is often combined with Global Navigation Satellite System (GNSS) to increase the positioning accuracy and continuity. In complex urban environments, GNSS/INS integrated systems suffer not only from dynamical model errors but also GNSS observation gross errors. However, it is hard to distinguish dynamical model errors from observation gross errors because the observation residuals are affected by both of them in a loosely-coupled integrated navigation system. In this research, an optimal Radial Basis Function (RBF) neural network-enhanced adaptive robust Kalman filter (KF) method is proposed to isolate and mitigate the influence of the two types of errors. In the proposed method, firstly a test statistic based on Mahalanobis distance is treated as judging index to achieve fault detection. Then, an optimal RBF neural network strategy is trained on-line by the optimality principle. The network’s output will bring benefits in recognizing the above two kinds of filtering fault and the system is able to choose a robust or adaptive Kalman filtering method autonomously. A field vehicle test in urban areas with a low-cost GNSS/INS integrated system indicates that two types of errors simulated in complex urban areas have been detected, distinguished and eliminated with the proposed scheme, success rate reached up to 92%. In particular, we also find that the novel neural network strategy can improve the overall position accuracy during GNSS signal short-term outages.

Short-Term Load Forecasting Using Adaptive Annealing Learning Algorithm Based Reinforcement Neural Network

A reinforcement learning algorithm is proposed to improve the accuracy of short-term load forecasting (STLF) in this article. The proposed model integrates radial basis function neural network (RBFNN), support vector regression (SVR), and adaptive annealing learning algorithm (AALA). In the proposed methodology, firstly, the initial structure of RBFNN is determined by using an SVR. Then, an AALA with time-varying learning rates is used to optimize the initial parameters of SVR-RBFNN (AALA-SVR-RBFNN). In order to overcome the stagnation for searching optimal RBFNN, a particle swarm optimization (PSO) is applied to simultaneously find promising learning rates in AALA. Finally, the short-term load demands are predicted by using the optimal RBFNN. The performance of the proposed methodology is verified on the actual load dataset from the Taiwan Power Company (TPC). Simulation results reveal that the proposed AALA-SVR-RBFNN can achieve a better load forecasting precision compared to various RBFNNs.

Study on a Novel Hybrid Intelligent Fault Diagnosis Method Based on Improved DE and RBFNN

The radial basis function neural network (RBFNN) is a great potential artificial intelligence technology and can effectively realize the fault diagnosis for small sample and nonlinear problem. But the parameters of RBFNN model seriously affects the generalization ability and diagnosis accuracy on the great extent. So an improved differential evolution algorithm based on dynamic adaptive adjustment strategy is proposed to optimize the parameters of RBFNN model for obtaining the optimal RBFNN (DASDERBFNN) method. Then the proposed DASDERBFNN method is used to construct a new fault diagnosis (DSDRBFNFD) method. In the DSDRBFNFD method, the dynamic adaptive adjustment strategy is used to adaptively adjust the crossover probability (CR ) value according to the fitness value of current individual in the population for obtaining the improved DE(DASDE) algorithm. Then the selection of parameters in the RBFNN is regarded as a combination optimization of parameters in order to establish the objective function of combination optimization. The DASDE algorithm is used to search for the optimal value of objective function to obtain the better parameter optimization of the RBFNN (DASDERBFNN), which is applied in the fault diagnosis for constructing a new fault diagnosis (DSDRBFNFD) method. Finally, the proposed DSDRBFNFD method is used to diagnose the fault of the cylinder of the engine in order to validate the diagnosis effectiveness of the DSDRBFNFD method. The experiment results show that the proposed DSDRBFNFD method can obtain the higher accuracy of fault diagnosis and is effective fault diagnosis for the engine.

Near infrared spectroscopy coupled with radial basis function neural network for at-line monitoring of Lactococcus lactis subsp. fermentation

In our previous work, partial least squares (PLSs) were employed to develop the near infrared spectroscopy (NIRs) models for at-line (fast off-line) monitoring key parameters of Lactococcus lactis subsp. fermentation. In this study, radial basis function neural network (RBFNN) as a non-linear modeling method was investigated to develop NIRs models instead of PLS. A method named moving window radial basis function neural network (MWRBFNN) was applied to select the characteristic wavelength variables by using the degree approximation (Da) as criterion. Next, the RBFNN models with selected wavelength variables were optimized by selecting a suitable constant spread. Finally, the effective spectra pretreatment methods were selected by comparing the robustness of the optimum RBFNN models developed with pretreated spectra. The results demonstrated that the robustness of the optimal RBFNN models were better than the PLS models for at-line monitoring of glucose and pH of L. lactis subsp. fermentation.

Modeling of ECDM micro-drilling process using GA- and PSO-trained radial basis function neural network

Electrochemical discharge machining (ECDM) is a non-traditional manufacturing process potentially used to machine electrically non-conductive materials, such as ceramics and glass. The present paper explains the modeling of multi-input---multi-output ECDM micro-drilling of silicon nitride ceramics using radial basis function neural network (RBFNN). To establish the model, the process parameters such as applied voltage, electrolyte concentration and inter-electrode gap are treated as inputs and the important machining criteria namely material removal rate, radial overcut and heat affected zone are considered as outputs. A batch mode of training has been implemented to tune the developed RBFNN by utilizing a genetic algorithm (GA) and particle swarm optimization (PSO) methods, separately. Once, the optimal RBFNN is obtained, the performances of GA-trained RfBFNN (GA-RBFNN) and PSO-trained RBFNN (PSO-RBFNN) are compared with the help of experimental test cases. It has been observed that PSO-RBFNN is found to perform marginally better than GA-RBFNN.

Estimation of the state of charge for a LFP battery using a hybrid method that combines a RBF neural network, an OLS algorithm and AGA

A method to accurately estimate the State-of-Charge (SOC) for LiFePO4 (LFB) batteries is urgently required, to address the issues associated with the increased use of LFP batteries for portable devices. This paper proposes a hybrid method that combines a radial basis function (RBF) neural network, an orthogonal least-squares (OLS) algorithm and an adaptive genetic algorithm (AGA) to estimate the SOC in discharging condition. The OLS algorithm determines the optimal number of nodes in the hidden layer of the RBF neural network. With an optimal RBF neural network structure, the AGA is then used to tune the parameters of the RBF neural network, including the centers and widths of RBF and the connection weights. The trained RBF neural network is then used to estimate the SOC of a LFP battery. In order to demonstrate the effectiveness of the proposed estimation method, the method is tested using LFP batteries under several different discharging conditions. The effectiveness of the proposed method is compared with the Coulomb integration method and a back propagation (BP) neural network. The results show that the proposed method outperforms the other methods.

Short-term load forecasting using SVR (support vector regression)-based radial basis function neural network with dual extended Kalman filter

Accurate load forecasting is an important issue for the reliable and efficient operation of the power system. This paper presents a hybrid algorithm which combines SVR (support vector regression), RBFNN (radial basis function neural network), and DEKF (dual extended Kalamn filter) to construct a prediction model (SVR–DEKF–RBFNN) for short-term load forecasting. In the proposed model, first, the SVR model is employed to determine both the structure and initial parameters of the RBFNN. After initialization, the DEKF is used as the learning algorithm to optimize the parameters of the RBFNN. Finally, the optimal RBFNN model is adopted to predict short-term load. The performance of the proposed approach is evaluated on real-load data from the Taipower Company, and compared with DEKF–RBFNN and GRD-RBFNN (gradient decent RBFNN) models. Simulation results of three cases show that the proposed method has better forecasting performance than the other methods.

Melt index prediction by RBF neural network with an ICO‐VSA hybrid optimization algorithm

AbstractMelt index (MI) is considered as one of the most significant parameter to determine the quality and the grade of the practical polypropylene polymerization products. A novel ICO‐VSA‐RNN (RBF neural network with ICO‐VSA algorithm) MI prediction model is proposed based on radial basis function (RBF) neural network and improved chaos optimization (ICO), and variable‐scale analysis (VSA), where the ICO is first added and then combined with the VSA to overcome the defects of ICO and VSA, then the parameters of the RBF neural network are optimized with them. At last, the RBF neural network model for MI prediction model is developed. Further researches on the optimal RBF neural network model of MI prediction are carried out with the data from a real industrial plant, and the prediction results show that the performance of this prediction model is much better than the RBF neural network model without optimization. © 2012 Wiley Periodicals, Inc. J Appl Polym Sci, 2012

Improving multiclass pattern recognition with a co-evolutionary RBFNN

A new hybrid scheme of the radial basis function neural network (RBFNN) model and the co-operative co-evolutionary algorithm (Co-CEA) is presented for multiclass classification tasks. This combination of the conventional RBFNN training algorithm and the proposed Co-CEA enforces the strength of both methods. First, the decaying radius selection clustering (DRSC) method is used to obtain the initial hidden nodes of the RBFNN model, which are further partitioned into modules of hidden nodes by the K-means method. Then, subpopulations are initialized on modules, and the Co-CEA evolves all subpopulations to find the optimal RBFNN structural parameters. Matrix-form mixed encoding and special crossover and mutation operators are designed. Finally, the proposed algorithm is tested on 14 real-world classification problems from the UCI machine learning repository, and experimental results illustrate that the algorithm is able to produce RBFNN models that have better prediction accuracies and simpler structures than conventional algorithms of classification.