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
Prediction and Assessment of Air Pollution in Shandong Province Based on CART Decision Tree and Radial Basis Function Neural Network

DOI: 10.12677/SA.2019.85082, PP. 725-733

Keywords: AQI，CART树，RBF网络，模型优劣对比
AQI, CART Tree, RBF Neural Network, Model Pros and Cons

Full-Text   Cite this paper   Add to My Lib

Abstract:

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。
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.

References

[1]	Kampa, M. and Castanas, E. (2008) Human Health Effects of Air Pollution. Environmental Pollution, 151, 362-367. https://doi.org/10.1016/j.envpol.2007.06.012
[2]	Zhan, D.S., Kwan, M.-P., Zhang, W.Z., et al. (2018) The Driving Factors of Air Quality Index in China. Journal of Cleaner Production, 197, 1342-1351. https://doi.org/10.1016/j.jclepro.2018.06.108
[3]	张松林. CART分类与回归树方法介绍[J]. 火山地质与矿产, 1997(1): 67-75.
[4]	Kim, B. and Kim, J. (2016) Stochastic Ordering of Gini Indexes for Multivariate Elliptical Risks. Insurance Mathematics and Economics, 68, 84-91.
[5]	刘云翔, 吴浩. 基于改进CART决策树建立水华预警模型[J]. 中国农村水利水电, 2018(1): 26-28.
[6]	蔡丽清. 基于CART算法的高校超市服务应用研究[J]. 电脑知识与技术, 2016, 12(13): 261-263.
[7]	黄晓君. 基于变化检测CART决策树模式自动识别沙漠化信息[J]. 灾害学, 2017, 32(1): 36-42.
[8]	孔颖. 基于CART算法的垃圾邮件过滤模型设计与实现[J]. 计算机应用, 2009, 29(2): 374-376.
[9]	钱揖丽. 基于分类回归树CART的汉语韵律短语边界识别[J]. 计算机工程与应用, 2006, 44(6): 169-171.
[10]	刘玉茹. CART分析及其在故障趋势预测中的应用[J]. 计算机应用, 2017(S2): 57-59.
[11]	冯洁. CART算法在银行CRM中的应用研究[J]. 高效理科研究, 2011(26): 111-112.
[12]	Shang, Z.G., Deng, T., He, J.Q. and Duan, X.H. (2019) A Novel Model for Hourly PM2.5 Concentration Prediction Based on CART and EELM. Sci-ence of the Total Environment, 651, 3043-3052. https://doi.org/10.1016/j.scitotenv.2018.10.193
[13]	Breiman, L., Friedman, J.H., Olshen, R.A. and Stone, C.J. (1984) Classification and Regression Trees, Wadsworth.
[14]	Bai, Y., Li, Y., Wang, X.X., Xie, J.J., et al. (2016) Air Pollutants Concentrations Forecasting Using Back Propagation Neural Network Based on Wavelet Decomposition with Meteorological Conditions. Atmospheric Pollution Research, 7, 557-566. https://doi.org/10.1016/j.apr.2016.01.004
[15]	Zhu, S.L., Lian, X.Y., Liu, H.X., Hu, J.M., Wang, Y.Y. and Che, J.X. (2017) Daily Air Quality Index Forecasting with Hybrid Models: A Case in China. Environmental Pollution, 231, 1232-1244. https://doi.org/10.1016/j.envpol.2017.08.069
[16]	He, Q.F., Shahabi, H. and Shirzadi, A. (2019) Landslide Spatial Modelling Using Novel Bivariate Statistical Based Na？ve Bayes, RBF Classifier, and RBF Network Machine Learning Algorithms. Science of the Total Environment, 663, 1-15. https://doi.org/10.1016/j.scitotenv.2019.01.329
[17]	Park, J. and Sandberg, I.W. (1993) Approximation and Radial-Basis-Function Networks. Neural Computation, 5, 305-316. https://doi.org/10.1162/neco.1993.5.2.305
[18]	Dong, J., Zhao, Y.X. and Liu, C. (2019) Orthogonal Least Squares Based Center Selection for Fault-Tolerant RBF Networks. Neurocomputing, 339, 217-231. https://doi.org/10.1016/j.neucom.2019.02.039

Full-Text