%0 Journal Article
%T 基于CART决策树和RBF神经网络的山东省空气污染状况预测评估<br> Prediction and Assessment of Air Pollution in Shandong Province Based on CART Decision Tree and Radial Basis Function Neural Network
%A 赵亚男
%J Statistics and Applications
%P 725-733
%@ 2325-226X
%D 2019
%I Hans Publishing
%R 10.12677/SA.2019.85082
%X <div style=\"text-align:justify;\">
	<span style=\"font-size:14px;\">为了更好地监测空气质量，作出相应的空气保护措施，本文运用CART树对山东省2018年的空气质量级别进行建模，并用2019年上半年的数据进行分类预测，并将此方法与RBF网络进行对比，实证分析表明CART树拟合效果更好，模型准确率更高。而此模型也可以运用到山东省空气污染情况的预测治理上。<br />
In order to better monitor air quality and make corresponding air protection measures, this paper uses CART tree to model the air quality level of Shandong Province in 2018, and the data from the first half of 2019 for classifying and predicting. Compared with RBF network, empirical analysis shows that the CART tree has a better fitting effect with higher model accuracy, and this model can also be applied to the forecasting and control of air pollution in Shandong Province.</span> 
</div>
%K AQI，CART树，RBF网络，模型优劣对比<br> AQI
%K CART Tree
%K RBF Neural Network
%K Model Pros and Cons
%U http://www.hanspub.org/journal/PaperInformation.aspx?PaperID=32446