Radial Basis Function Neural Network Based on an Improved Exponential Decreasing Inertia Weight-Particle Swarm Optimization Algorithm for AQI Prediction

Abstract

This paper proposed a novel radial basis function (RBF) neural network model optimized by exponential decreasing inertia weight particle swarm optimization (EDIW-PSO). Based on the inertia weight decreasing strategy, we propose a new Exponential Decreasing Inertia Weight (EDIW) to improve the PSO algorithm. We use the modified EDIW-PSO algorithm to determine the centers, widths, and connection weights of RBF neural network. To assess the performance of the proposed EDIW-PSO-RBF model, we choose the daily air quality index (AQI) of Xi'an for prediction and obtain improved results.where is the variable of radial basis function (⋅).

Prediction of influenza-like illness based on the improved artificial tree algorithm and artificial neural network

“…For example, in Qiu and Song 24 , a genetic algorithm was used to optimize the initial parameters of a BP neural network for Japanese stock forecasting. In Lu et al 19 and in Lu et al . 28 , particle swarm optimization algorithm was used to optimize the initial parameters of RBF for predicting AQI and GRBF neural networks for predicting the Chinese stock index, respectively.…”

“…Many methods for predictions and classifications exist. Among them, there are machine learning 9 for ILI, the artificial neural network 19 for air quality index (AQI), PDE 20 for prediction-error expansion-based reversible data hiding, finite element modeling 21 for prediction of muscle activation for an eye movement, and a time-space discretization approach 22 for bus travel time prediction.…”

“…Here, we focus on the neural network for prediction. The BP neural network (BPNN) 23 , 24 , the self-organization map neural network 25 , the radial basis function (RBF) neural network 19 , the wavelet neural network 26 , 27 , and the generalized radial basis function (GRBF) neural network 28 are used to perform predictions and classifications. The randomness of the artificial networks’ initial parameters generalizes the predictions & classifications.…”

The Improved Antlion Optimizer and Artificial Neural Network for Chinese Influenza Prediction

“…For example, SCA and GA are used to optimize the weight and basis of artificial neural network for predicting the direction of stock market index, respectively [31,32]. An improved dynamic particle swarm optimization with AdaBoost algorithm is used to optimize the parameters of generalized radial basis function neural network for stock market prediction [33], and an Improved Exponential Decreasing Inertia Weight-Particle Swarm Optimization Algorithm is utilized to optimize the parameters of radial basis function neural network for the air quality index (AQI) prediction [34], respectively. Artificial tree (AT) algorithm was improved and applied to optimize the parameters of artificial neural network for predicting influenza-like illness [35].…”

Urban Air Quality Analysis and Forecast Based on Intelligent Algorithm with Parameter Optimization and Decision Rules

“…Collecting AQI data is key for monitoring pollution problems. To solve the AQI problem, various approaches have been used for data mining, including artificial neural network (ANN), genetic algorithm (GA), decision tree (DT), random forest (RF), and support vector machine (SVM) [10][11][12][13][14][15][16][17][18][19][20]. Each method has a single basic point of view and provides a general performance analysis of air quality indicators, but it is difficult to distinguish the best method.…”