[1]周杉杉,李文静,乔俊飞.基于自组织递归模糊神经网络的PM2.5浓度预测[J].智能系统学报,2018,13(04):509-516.[doi:10.11992/tis.201710007]
 ZHOU Shanshan,LI Wenjing,QIAO Junfei.Prediction of PM2.5 concentration based on self-organizing recurrent fuzzy neural network[J].CAAI Transactions on Intelligent Systems,2018,13(04):509-516.[doi:10.11992/tis.201710007]
点击复制

基于自组织递归模糊神经网络的PM2.5浓度预测(/HTML)
分享到:

《智能系统学报》[ISSN:1673-4785/CN:23-1538/TP]

卷:
第13卷
期数:
2018年04期
页码:
509-516
栏目:
出版日期:
2018-07-05

文章信息/Info

Title:
Prediction of PM2.5 concentration based on self-organizing recurrent fuzzy neural network
作者:
周杉杉12 李文静12 乔俊飞12
1. 北京工业大学 信息学部, 北京 100124;
2. 计算智能与智能系统北京市重点实验室, 北京 100124
Author(s):
ZHOU Shanshan12 LI Wenjing12 QIAO Junfei12
1. Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China;
2. Beijing Key Laboratory of Computational Intelligent System, Beijing 100124, China
关键词:
PM2.5预测PCA递归模糊神经网络自组织自适应梯度下降
Keywords:
PM2.5predictionPCArecurrent fuzzy neural networkself-organizingadaptive gradient descent algorithm
分类号:
TP18
DOI:
10.11992/tis.201710007
摘要:
针对PM2.5浓度非线性动态变化的特点,提出了一种自组织递归模糊神经网络(self-organizing recurrent fuzzy neural network,SORFNN)方法预测PM2.5小时浓度。首先,通过分析影响PM2.5浓度的多种因素,利用主成分分析法(principal component analysis,PCA)筛选出与PM2.5浓度相关性较强的特征变量作为神经网络的输入变量。然后,根据ε准则和偏最小二乘算法(partial least squares,PLS)进行规则化层神经元的增删,实现递归模糊神经网络结构的自动调整,并采用学习率自适应的梯度下降算法调整模型中心、宽度和权值等参数,建立PM2.5预测模型。最后,利用典型非线性系统辨识和实际PM2.5浓度预测实验进行验证。实验结果表明,所设计的自组织递归模糊神经网络结构精简且预测精度高,较好地满足了PM2.5实时预测的要求。
Abstract:
To address the nonlinear dynamic variation in the concentration of fine particulate matter (PM2.5), in this paper, we propose a novel self-organizing recurrent fuzzy neural network (SORFNN) for predicting the hourly PM2.5 concentration. First, we analyzed the factors affecting PM2.5 concentration by principal component analysis to identify the characteristic variables and used them as input variables in the neural network. Next, we added or deleted a nerve cell to the regularized layer, based on the ε criterion and partial least squares algorithm, to automatically adjust the recurrent fuzzy neural network. In addition, we applied the adaptive gradient descent algorithm to adjust parameters such as the centers, widths and weights to establish a PM2.5 model. Lastly, to verify the results, we conducted experiments in typical nonlinear system identification and actual PM2.5 concentration prediction. The experimental results show that the proposed SORFNN is compact in structure, has high prediction accuracy, and can satisfy the real-time prediction requirements of PM2.5 concentration.

参考文献/References:

[1] TAO Minghui, CHEN Liangfu, WANG Zifeng, et al. A study of urban pollution and haze clouds over northern China during the dusty season based on satellite and surface observations[J]. Atmospheric environment, 2014, 82:183-192.
[2] QIAO Liping, CAI Jing, WANG Hongqi, et al. PM2.5 constituents and hospital emergency-room visits in Shanghai, China[J]. Environmental science and technology, 2014, 48(17):10406-10414.
[3] XIAO S, WANG Q Y, CAO J J, et al. Long-term trends in visibility and impacts of aerosol composition on visibility impairment in Baoji, China[J]. Atmospheric research, 2014, 149:88-95.
[4] SAIDE P E, CARMICHAEL G R, SPAK S N, et al. Forecasting urban PM10 and PM2.5 pollution episodes in very stable nocturnal conditions and complex terrain using WRF-Chem CO tracer model[J]. Atmospheric environment, 2011, 45(16):2769-2780.
[5] RICCIO A, CHIANESE E, AGRILLO G, et al. Source apportion of atmospheric particulate matter:a joint Eulerian/Lagrangian approach[J]. Environmental science and pollution research, 2014, 21(23):13160-13168.
[6] CHEN Yuanyuan, SHI Runhe, SHU Shijie, et al. Ensemble and enhanced PM10 concentration forecast model based on stepwise regression and wavelet analysis[J]. Atmospheric environment, 2013, 74:346-359.
[7] ELBAYOUMI M, RAMLI N A, MD YUSOF N F F, et al. Multivariate methods for indoor PM10 and PM2.5 modelling in naturally ventilated schools buildings[J]. Atmospheric environment, 2014, 94:11-21.
[8] ORDIERES J B, VERGARA E P, CAPUZ R S, et al. Neural network prediction model for fine particulate matter (PM2.5) on the US-Mexico border in El Paso (Texas) and Ciudad Juárez (Chihuahua)[J]. Environmental modelling and software, 2005, 20(5):547-559.
[9] XU Zhao, XIA Xiaopeng, LIU Xiangnan, et al. Combining DMSP/OLS nighttime light with echo state network for prediction of daily PM2.5 average concentrations in Shanghai, China[J]. Atmosphere, 2015, 6(10):1507-1520.
[10] MISHRA D, GOYAL P, UPADHYAY A. Artificial intelligence based approach to forecast PM2.5 during haze episodes:a case study of Delhi, India[J]. Atmospheric environment, 2015, 102:239-248.
[11] QIAO Junfei, CAI Jie, HAN Honggui, et al. Predicting PM2.5 concentrations at a regional background station using second order self-organizing fuzzy neural network[J]. Atmosphere, 2017, 8(1):10.
[12] HAN Honggui, LI Ying, GUO Yanan, et al. A soft computing method to predict sludge volume index based on a recurrent self-organizing neural network[J]. Applied soft computing, 2016, 38:477-486.
[13] HAN Honggui, WANG Lidan, QIAO Junfei, et al. A spiking-based mechanism for self-organizing RBF neural networks[C]//2014 International Joint Conference on Neural Networks (IJCNN). Beijing, China, 2014:3775-3782.
[14] HAN Honggui, WU Xiaolong, QIAO Junfei. Nonlinear systems modeling based on self-organizing fuzzy-neural-network with adaptive computation algorithm[J]. IEEE transactions on cybernetics, 2014, 44(4):554-564.
[15] LENG Gang, MCGINNITY T M, PRASAD G. An approach for on-line extraction of fuzzy rules using a self-organising fuzzy neural network[J]. Fuzzy sets and systems, 2005, 150(2):211-243.
[16] WU Shiqian, ER M J. Dynamic fuzzy neural networks-a novel approach to function approximation[J]. IEEE transactions on systems, man, and cybernetics, part B (cybernetics), 2000, 30(2):358-364.
[17] WU Shiqian, ER M J, GAO Yang. A fast approach for automatic generation of fuzzy rules by generalized dynamic fuzzy neural networks[J]. IEEE transactions on fuzzy systems, 2001, 9(4):578-594.
[18] 陈冠益, 张雯, 侯立安, 等. 天津蓟县夏季PM2.5污染特征及影响因素[J]. 天津大学学报:自然科学与工程技术版, 2015, 48(2):95-102. CHEN Guanyi, ZHANG Wen, HOU Lian, et al. Pollution characteristics and influence factors of PM2.5 in summer in Jixian county of Tianjin[J]. Journal of Tianjin university:science and technology, 2015, 48(2):95-102.
[19] ZHENG Yu, YI Xiuwen, LI Ming, et al. Forecasting fine-grained air quality based on big data[C]//Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York, NY, USA, 2015:2267-2276.
[20] AZID A, JUAHIR H, TORIMAN M E, et al. Prediction of the level of air pollution using principal component analysis and artificial neural network techniques:A case study in Malaysia[J]. Water, air, and soil pollution, 2014, 225:2063.
[21] VOUKANTSIS D, KARATZAS K, KUKKONEN J, et al. Intercomparison of air quality data using principal component analysis, and forecasting of PM10 and PM2.5 concentrations using artificial neural networks, in Thessaloniki and Helsinki[J]. Science of the total environment, 2011, 409(7):1266-1276.
[22] HAN Honggui, GUO Yanan, QIAO Junfei. Self-organization of a recurrent RBF neural network using an information-oriented algorithm[J]. Neurocomputing, 2017, 225:80-91.
[23] QIAO Junfei, ZHANG Wei, HAN Honggui. Self-organizing fuzzy control for dissolved oxygen concentration using fuzzy neural network1[J]. Journal of intelligent and fuzzy systems, 2016, 30(6):3411-3422.
[24] WANG Ning, ER M J, MENG Xianyao. A fast and accurate online self-organizing scheme for parsimonious fuzzy neural networks[J]. Neurocomputing, 2009, 72(16/17/18):3818-3829.
[25] 余辉, 袁晶, 于旭耀, 等. 基于ARMAX的PM2.5 小时浓度跟踪预测模型[J]. 天津大学学报:自然科学与工程技术版, 2017, 50(1):105-111. YU Hui, YUAN Jing, YU Xuyao, et al. Tracking prediction model for PM2.5 hourly concentration based on ARMAX[J]. Journal of Tianjin university:science and technology, 2017, 50(1):105-111.
[26] ZOU Bin, WANG Min, WAN Neng, et al. Spatial modeling of PM2.5 concentrations with a multifactoral radial basis function neural network[J]. Environmental science and pollution research, 2015, 22(14):10395-10404.
[27] MISHRA D, GOYAL P. Neuro-fuzzy approach to forecast NO2 pollutants addressed to air quality dispersion model over Delhi, India[J]. Aerosol and air quality research, 2016, 16(1):166-174.
[28] FU Minglei, WANG Weiwen, LE Zichun, et al. Prediction of particular matter concentrations by developed feed-forward neural network with rolling mechanism and gray model[J]. Neural computing and applications, 2015, 26(8):1789-1797.
[29] ELANGASINGHE M A, SINGHAL N, DIRKS K N, et al. Complex time series analysis of PM10 and PM2.5 for a coastal site using artificial neural network modelling and k-means clustering[J]. Atmospheric environment, 2014, 94:106-116.
[30] PEREZ P, GRAMSCH E. Forecasting hourly PM2.5 in Santiago de Chile with emphasis on night episodes[J]. Atmospheric environment, 2016, 124:22-27.
[31] WU G D, HUANG P H. A maximizing-discriminability-based self-organizing fuzzy network for classification problems[J]. IEEE transactions on fuzzy systems, 2010, 18(2):362-373.
[32] 许少鹏, 韩红桂, 乔俊飞. 基于模糊递归神经网络的污泥容积指数预测模型[J]. 化工学报, 2013, 64(12):4550-4556. XU Shaopeng, HAN Honggui, QIAO Junfei. Prediction of activated sludge bulking based on recurrent fuzzy neural network[J]. CIESC journal, 2013, 64(12):4550-4556.
[33] MADRIGANO J, KLOOG I, GOLDBERG R, et al. Long-term exposure to PM2.5 and incidence of acute myocardial infarction[J]. Environmental health perspectives, 2013, 121(2):192-196.
[34] 城市计算[EB/OL]. (2008–03–18). https://www.microsoft.com/en-us/research/project/城市计算.

相似文献/References:

[1]雷森,史振威,石天阳,等.基于递归神经网络的风暴潮增水预测[J].智能系统学报,2017,12(05):640.[doi:10.11992/tis.201706015]
 LEI Sen,SHI Zhenwei,SHI Tianyang,et al.Prediction of storm surge based on recurrent neural network[J].CAAI Transactions on Intelligent Systems,2017,12(04):640.[doi:10.11992/tis.201706015]

备注/Memo

备注/Memo:
收稿日期:2017-10-17。
基金项目:国家自然科学基金项目(61533002,61603009);北京工业大学“日新人才”计划项目(2017-RX(1)-04);北京市自然科学基金项目(4182007).
作者简介:周杉杉,女,1992年生,硕士研究生,主要研究方向为智能信息处理与神经网络非线性系统建模。获得软件著作权1项。发表学术论文1篇;李文静,女,1985年生,副教授,博士,主要研究方向为神经计算、人工神经网络、模式识别。主持国家自然科学基金青年项目、中国博士后第57批面上资助项目、北京市博士后科研活动经费资助项目各1项。申请美国发明专利1项。近5年来发表学术论文10余篇,其中SCI收录8篇;乔俊飞,男,1968年生,教授,博士生导师,国家杰出青年基金获得者,教育部长江学者特聘教授,教育部新世纪优秀人才,中国人工智能学会科普工作委员会主任,主要研究方向为智能信息处理、智能控制理论与应用。获教育部科技进步奖一等奖和北京市科学技术奖三等奖各1项。获得发明专利20余项。发表学术论文100余篇,其中被SCI收录20余篇,EI收录60余篇。
通讯作者:周杉杉.E-mail:18810337855@163.com.
更新日期/Last Update: 2018-08-25