青岛大学学报（自然科学版）2017，Vol.30Issue(2)：83-87,91,6.DOI:10.3969/j.issn.1006-1037.2017.05.18
基于Pearson相关指标的BP神经网络PM2.5预测模型
PM2.5 Prediction Model of BP Neural Network Based on Pearson Correlation Index
摘要
Abstract
In order to reduce the prediction cost of PM2.5 equipment,and to analyse the correlation between atmospheric factors and pollutants,the pollutant index of O3、CO、PM10、SO2、NO2 was selected to predict PM2.5,then added temperature,humidity,wind power and other atmospheric indexes,for establishing the comprehensive meteorological index system.Using Pearson algorithm to merge the index, with the method of BP neural network related indicators again on PM2.5 forecast.Compared with the experimental results, the BP neural network model based on Pearson related index in PM2.5 can improve the prediction accuracy and reduce the time complexity of prediction, which can reduce the prediction cost of PM2.5.关键词
PM2.5/神经网络/预测/pearsonKey words
PM2.5/neural networks/prediction/pearson分类
信息技术与安全科学引用本文复制引用
张怡文,敖希琴,时培俊,郭傲东,费久龙,陈家丽..基于Pearson相关指标的BP神经网络PM2.5预测模型[J].青岛大学学报（自然科学版）,2017,30(2):83-87,91,6.基金项目
安徽省高校自然科学重点项目(批准号:KJ2015A309)资助. （批准号:KJ2015A309）
