RBF-neural-network-based atmospheric pollutant concentration prediction method

Abstract

The invention relates to an RBF-neural-network-based atmospheric pollutant concentration prediction method. The RBF-neural-network-based atmospheric pollutant concentration prediction method includesthe steps: dividing experimental data according to the actual situation of the predicted area, and pre-processing the atmospheric pollutant concentration data; using the MMOD improved K-means++ algorithm to solve the center of clustering, and calculating each kernel function width based on the variance; sampling the experimental data, wherein data subsets taking part in creation of RBF neural networks are IOB, and the remaining data that are not drawn are OOB data; evaluating learners to screen out the RBF neural network with the smallest generalization error, training an integrated RBFNN model; and by means of the weighted integrated RBFNN algorithm, based on weighted Euclidean distance, training single parameter through the center of clustering, the width and the weight to optimize RBFNN, and applying the single parameter to the integrated RBFNN to predict data. The RBF-neural-network-based atmospheric pollutant concentration prediction method is applied to atmospheric pollutant concentration prediction, and can greatly improve accuracy of atmospheric pollutant concentration prediction.

Description

technical field [0001] The invention relates to a neural network prediction technology, in particular to a method for predicting the concentration of air pollutants based on an RBF neural network. Background technique [0002] Today in the 21st century, with the rapid development of global industry and the acceleration of urbanization, various countries in the world, especially developing countries, are facing different levels of air pollution. Environmental pollution has become one of the problems that countries have to face. As the largest developing country, although China has made great progress in economic development and has become the second largest economy in the world, in the process of rapid development, my country's environmental and ecological conditions are facing huge challenges. From the 20th century to the 21st century, my country has experienced the transformation from an agricultural country to an industrial country. At the same time, my country's energy co...

AI Technical Summary

Problems solved by technology

The neural network has good fault tolerance and information synthesis capabilities, and can coordinate the input of contradictory related information, but it also has its own shortcomings: the neural network training speed is slow, it is difficult to converge, and it is easy to fall into a local minimum point

Although this training method is simple, it also has defects. First, the traditional k-means algorithm is easily affected by outliers and initial center points. Therefore, the center points obtained by using k-means clustering are unstable and difficult to be optimal. untie

Secondly, the method does not fully consider the distribution of data when selecting the width, which affects the performance of the RBF neural network.

Images