Environmental noise prediction method and system based on improved neural network

Abstract

The invention relates to the technical field of data mining, in particular to an environment noise prediction method and system based on an improved neural network, and the method comprises the steps: firstly extracting environment noise data, dividing a training data set and a test data set, randomly generating a population, and obtaining a current rejection factor based on a heuristic factor; according to the method, the improved neural network is used to predict the environmental noise, the sine and cosine algorithm based on the rejection mechanism is used to optimize and design the parameters of the neural network model for predicting the environmental noise, and the prediction accuracy of the environmental noise is improved. The individuals in the population are made to be far away from the poor individuals by using the adaptive rejection factor, the search efficiency of the algorithm can be enhanced, the precision of predicting the environmental noise neural network model is improved, and the environmental noise prediction model obtained through training can improve the prediction precision of the environmental noise.

Description

technical field [0001] The invention relates to the technical field of data mining, in particular to an environmental noise prediction method and system based on an improved neural network. Background technique [0002] With the improvement of living standards, people pay more and more attention to the comfort of living environment. Environmental noise is an important factor affecting the comfort of living environment. In order to better monitor environmental noise, many cities have installed environmental noise monitoring equipment in various places. Environmental noise monitoring equipment can be used to collect environmental noise data in various places conveniently and in real time. With the accumulation of environmental noise data, researchers try to use data mining technology to analyze the accumulated environmental noise data, so as to grasp the environmental noise pollution status of various areas in the city from multiple levels. [0003] Prediction of environmen...

AI Technical Summary

Problems solved by technology

[0004] The object of the present invention is to provide a method and system for predicting environmental noise based on an improved neural network, so as to overcome to a certain extent the disadvantages that the traditional neural network is prone to fall into local optimum and the prediction accuracy is insufficient when it is applied to the prediction of environmental noise, thereby Improving the Prediction Accuracy of Environmental Noise

Images