PM2.5 concentration prediction model of least squares support vector machine based on feature vector

doi:10.11772/j.issn.1001-9081.2014.08.2212

Journal of Computer Applications ›› 2014, Vol. 34 ›› Issue (8): 2212-2216.DOI: 10.11772/j.issn.1001-9081.2014.08.2212

Previous Articles Next Articles

PM2.5 concentration prediction model of least squares support vector machine based on feature vector

LI Long,MA Lei,HE Jianfeng,SHAO Dangguo,YI Sanli,XIANG Yan,LIU Lifang

School of Information Engineering and Automation, Kunming University of Science and Technology, Kunming Yunnan 650500, China

Received:2014-05-07 Revised:2014-05-12 Online:2014-08-10 Published:2014-08-01
Contact: LI Long

基于特征向量的最小二乘支持向量机PM2.5浓度预测模型

李龙,马磊,贺建峰,邵党国,易三莉,相艳,刘立芳

昆明理工大学信息工程与自动化学院，昆明650500

通讯作者: 李龙
作者简介:李龙（1988-），男，黑龙江大庆人，硕士研究生，主要研究方向：数据挖掘；马磊（1978-），男（回族），云南昆明人，讲师，硕士，主要研究方向：数据挖掘、生物信息学、医疗信息系统；贺建峰（1965-），男，云南昆明人，教授，主要研究方向：数据挖掘、医学图像处理。
基金资助:
国家自然科学基金资助项目;教育部留学回国人员科研启动基金资助项目

Abstract

Abstract:

To solve the problem of Fine Particulate Matter (PM2.5) concentration prediction, a PM2.5 concentration prediction model was proposed. First, through introducing the comprehensive meteorological index, the factors of wind, humidity, temperature were comprehensively considered; then the feature vector was conducted by combining the actual concentration of SO2, NO2, CO and PM10; finally the Least Squares Support Vector Machine (LS-SVM) prediction model was built based on feature vector and PM2.5 concentration data. The experimental results using the data from the city A and city B environmental monitoring centers in 2013 show that, the forecast accuracy is improved after the introduction of a comprehensive weather index, error is reduced by nearly 30%. The proposed model can more accurately predict the PM2.5 concentration and it has a high generalization ability. Furthermore, the author analyzed the relationship between PM2.5 concentration and the rate of hospitalization, hospital outpatient service amount, and found a high correlation between them.

摘要：

针对大气中细颗粒物(PM2.5)浓度预测的问题，提出一种预测模型。首先，通过引入综合气象指数综合考虑风力、湿度、温度等因素；然后，结合实际二氧化硫（SO2）浓度、二氧化氮（NO2）浓度、一氧化碳（CO）浓度和PM10浓度等，构成特征向量；最后，利用特征向量和PM2.5浓度数据来建立最小二乘支持向量机（LS-SVM）预测模型。经2013年城市A和城市B环境监测中心的数据预测分析表明，引入综合气象指数后预测的准确性提高，误差降低近30%。说明该模型能够较为准确地预测PM2.5浓度，并具有较高的泛化能力。此外还分析了PM2.5浓度与住院率、医院门诊量的关系，发现了它们的高度相关性。

CLC Number:

TP391.4
TP18

LI Long MA Lei HE Jianfeng SHAO Dangguo YI Sanli XIANG Yan LIU Lifang. PM2.5 concentration prediction model of least squares support vector machine based on feature vector[J]. Journal of Computer Applications, 2014, 34(8): 2212-2216.

李龙马磊贺建峰邵党国易三莉相艳刘立芳. 基于特征向量的最小二乘支持向量机PM2.5浓度预测模型[J]. 计算机应用, 2014, 34(8): 2212-2216.

References

［1］QIN X, LEI L, YAO X. Methods to improve the generalization of BP neural network applied in air pollution forecasting ［J］. Journal of Beijing University of Technology, 2007, 33(8): 849-852.(秦侠,雷蕾,姚小丽.大气污染预测中提高BP网络泛化能力的方法［J］.北京工业大学学报,2007,33(8):849-852.)
［2］CHEN L, WU D, CHEN Q. Wavelet analysis and support vector machine used in predicting atmospheric pollution ［J］. Xi'an University of Science and Technology, 2010, 30(6): 726-730.(陈柳,吴冬梅,陈俏.小波分析及支持向量机应用于大气污染预测［J］.西安科技大学学报,2010,30(6):726-730.)
［3］SU J, QIN X, LEI L, et al. Study of neural networks in air pollution forecasting application ［J］. Sichuan Environment, 2008, 27(2): 98-101.(苏静芝,秦侠,雷蕾,等.神经网络在空气污染预报中的应用研究［J］.四川环境,2008,27(2):98-101.)
［4］CHEN Q, CAO G, CHEN L. SVM applied to predict the concentration of atmospheric pollutants ［J］. Computer Technology and Development, 2010, 20(1): 250-252.(陈俏,曹根牛,陈柳.支持向量机应用于大气污染物浓度预测［J］.计算机技术与发展,2010,20(1):250-252.)
［5］WEI Z, GUO Z, ZHANG L, et al. The application of an air pollution model based on the Gauss mode ［J］. China Ocean University: Natural Science, 2008, 38(2): 327-330.(魏振钢,郭遵强,张琳,等.基于高斯模式的大气污染模型的应用［J］.中国海洋大学学报:自然科学版,2008,38(2):327-330.)

［6］WANG Y, DONG L, CHEN J. The study of three-dimensional multi-box model of prediction of atmospheric environment ［C］// Proceedings of the 2007 China Environmental Science Society Annual Conference. Beijing: China Environmental Science Press, 2007: 621-625.(王燕,董丽,陈剑.三维多箱模型预测大气环境的研究［C］// 2007中国环境科学学会学术年会优秀论文集.北京:中国环境科学出版社,2007:621-625.)
［7］CHARRON A, HARRISON R. Fine (PM2. 5) and coarse (PM2.5-10) particulate matter on a heavily trafficked London highway: sources and processes ［J］. Environmental Science and Technology, 2005, 39(20): 7768-7776.
［8］YAN L. Correlation coefficient and partial correlation coefficient in the relevant analysis ［J］. Journal of Yunnan Institute of Finance, 2003, 19(3): 78-80.(严丽坤.相关系数与偏相关系数在相关分析中的应用［J］.云南财贸学院学报,2003,19(3)78-80.)
［9］HE H, ZHOU X, ZENG J. Short-term load forecasting simplified LS-SVM model and implementation ［J］. Computer Simulation, 2011, 28(1): 302-306.(贺红林,周翔,曾劲松.短期负荷预测的简化LS-SVM模型及实现［J］.计算机仿真,2011,28(1):302-306.)
［10］YAN W, SHAO H. Support vector machines and comparison and application of least squares support vector machine ［J］. Control and Decision, 2003, 18(3): 358-360.(阎威武,邵惠鹤.支持向量机和最小二乘支持向量机的比较及应用研究［J］.控制与决策,2003,18(3):358-360.)
［11］LIU Y, PACIOREK C, KOUTRAKIS P. Estimating regional spatial and temporal variability of PM2. 5 concentrations using satellite data, meteorology, and land use information ［J］. Environmental Health Perspectives, 2009, 117(6): 886-892.
［12］TURPIN B, LIM H. Species contributions to PM2. 5 mass concentrations: revisiting common assumptions for estimating organic mass ［J］. Aerosol Science and Technology, 2001, 35(1): 602-610.
［13］McKENDRY I. Evaluation of artificial neural networks for fine particulate pollution (PM10 and PM2. 5) forecasting ［J］. Journal of the Air and Waste Management Association, 2002, 52(9): 1096-1101.
［14］Xi'an Environmental Monitoring Station. Daily air quality [EB/OL]. (2013-09-20) [2014-01-05]. http://www.xianemc.gov.cn/.(西安市环境监测站.空气质量日报[EB/OL]. (2013-09-20) [2014-01-05]. http://www.xianemc.gov.cn/.)
［15］Wuhan Environmental Monitoring Station. Daily air quality [EB/OL]. (2013-09-20) [2014-01-05]. http://www.whemc.cn/.(武汉市环境监测站.空气质量日报[EB/OL]. (2013-09-20) [2014-01-05]. http://www.whemc.cn/.)
［16］Ningbo Environmental Monitoring Station. Daily air quality [EB/OL]. (2013-12-20) [2014-01-05]. http://www.nbemc.gov.cn/.(宁波市环境监测站. 空气质量日报[EB/OL]. (2013-12-20) [2014-01-05]. http://www.nbemc.gov.cn/.)
［17］SHANG Y, SUN Z, CAO J, et al.. Systematic review of Chinese studies of short-term exposure to air pollution and daily mortality ［J］. Environment International, 2013, 54: 100-111.
［18］WANG D, WANG B, BAI Z. PM2.5 pollution and daily mortality residents meta analysis of the relationship ［J］. Journal of Environment and Health, 2012, 29(6): 529-532.(王德庆,王宝庆,白志鹏.PM2.5污染与居民每日死亡率关系的Meta分析［J］.环境与健康杂志,2012,29(6):529-532.)

[1]	. Pavement defect detection algorithm with enhanced morphological perception [J]. Journal of Computer Applications, 0, (): 0-0.
[2]	YANG Jianfeng, CHEN Bin, LI Yuxuan. Self-supervised point cloud anomaly detection method based on point cloud reconstruction [J]. Journal of Computer Applications, 0, (): 0-0.
[3]	. Binocular vision object location algorithm for robot arm grasping [J]. Journal of Computer Applications, 0, (): 0-0.
[4]	. Multi-attention contrastive learning for infrared small target detection [J]. Journal of Computer Applications, 0, (): 0-0.
[5]	LI Zhonghua, ZHONG Gengxin, FAN Ping, ZHU Hengliang. Camouflaged object detection by boundary mining and background guidance [J]. Journal of Computer Applications, 0, (): 0-0.
[6]	. Multi-view difficult airway recognition based on discriminant region guidance [J]. Journal of Computer Applications, 0, (): 0-0.
[7]	. Privacy preserving localization of surveillance images based on large vision models [J]. Journal of Computer Applications, 0, (): 0-0.
[8]	. Data augmentation method for abnormal passenger behavior in elevators based on dynamic graph convolutional network [J]. Journal of Computer Applications, 0, (): 0-0.
[9]	. Text-based person retrieval method based on multi-granularity shared semantic center association [J]. Journal of Computer Applications, 0, (): 0-0.
[10]	. Distribution adaptation and dynamic curriculum pseudo-labeling framework for semi-supervised fire detection [J]. Journal of Computer Applications, 0, (): 0-0.
[11]	. Image Caption Method Based on Swin-Transformer and Multi-Scale Feature Fusion [J]. Journal of Computer Applications, 0, (): 0-0.
[12]	Wei XIONG, Yibo CHEN, Lizhen ZHANG, Qian YANG, Qin ZOU. Self-supervised monocular depth estimation using multi-frame sequence images [J]. Journal of Computer Applications, 2024, 44(12): 3907-3914.
[13]	Keyi FU, Gaocai WANG, Man WU. Few-shot object detection method based on improved region proposal network and feature aggregation [J]. Journal of Computer Applications, 2024, 44(12): 3790-3797.
[14]	Chenghao YANG, Jie HU, Hongjun WANG, Bo PENG. Incomplete multi-view clustering algorithm based on attention mechanism [J]. Journal of Computer Applications, 2024, 44(12): 3784-3789.
[15]	Peng FANG, Fan ZHAO, Baoquan WANG, Yi WANG, Tonghai JIANG. Development， technologies and applications of blockchain 3.0 [J]. Journal of Computer Applications, 2024, 44(12): 3647-3657.

PM2.5 concentration prediction model of least squares support vector machine based on feature vector

基于特征向量的最小二乘支持向量机PM2.5浓度预测模型

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics