二氧化氮浓度时空预测：一种区间二型直觉模糊神经网络方法

赵亮; 李梦威; 郑玉卿; 崔贝贝; 朱献超

doi:10.11959/j.issn.2096-6652.202425

您当前的位置：

首页 >

文章列表页 >

二氧化氮浓度时空预测：一种区间二型直觉模糊神经网络方法

学术论文 | 更新时间：2024-08-06

- 二氧化氮浓度时空预测：一种区间二型直觉模糊神经网络方法
- Spatiotemporal prediction of nitrogen dioxide concentration: an interval type-2 intuitionistic fuzzy neural network approach
- 智能科学与技术学报 2024年6卷第2期页码：253-261
- 作者机构：
  
  1.河南工业大学电气工程学院，河南郑州 450001
  2.河南工业大学人工智能与大数据学院，河南郑州 450001
- 作者简介：
  
  [ "赵亮（1978- ），男，博士，河南工业大学电气工程学院副教授，主要研究方向为深度学习、平行学习。" ]
  [ "李梦威（1998- ），男，河南工业大学电气工程学院硕士生，主要研究方向为深度学习。" ]
  [ "郑玉卿（1987- ），男，博士，河南工业大学电气工程学院讲师，主要研究方向为数据驱动控制、智能控制、自适应控制。" ]
  [ "崔贝贝（1990- ），女，博士，河南工业大学电气工程学院讲师，主要研究方向为深度学习、图像处理。" ]
  [ "朱献超（1990- ），男，博士，河南工业大学人工智能与大数据学院讲师，主要研究方向为强化学习、量子强化学习和机器学习。" ]
- 基金信息：
  
  国家自然科学基金项目(61473114);河南省科技厅科技攻关项目(242102211040);河南省教育厅科学技术重点研究项目(24B520006;24A520014)
- DOI：10.11959/j.issn.2096-6652.202425
  中图分类号： TP399
- 收稿：2024-04-07，
  
  修回：2024-05-23，
  
  纸质出版：2024-06-15
- 稿件说明：
移动端阅览
赵亮,李梦威,郑玉卿等.二氧化氮浓度时空预测：一种区间二型直觉模糊神经网络方法[J].智能科学与技术学报,2024,06(02):253-261.

ZHAO Liang,LI Mengwei,ZHENG Yuqing,et al.Spatiotemporal prediction of nitrogen dioxide concentration: an interval type-2 intuitionistic fuzzy neural network approach[J].Chinese Journal of Intelligent Science and Technology,2024,06(02):253-261.
赵亮,李梦威,郑玉卿等.二氧化氮浓度时空预测：一种区间二型直觉模糊神经网络方法[J].智能科学与技术学报,2024,06(02):253-261. DOI： 10.11959/j.issn.2096-6652.202425.

ZHAO Liang,LI Mengwei,ZHENG Yuqing,et al.Spatiotemporal prediction of nitrogen dioxide concentration: an interval type-2 intuitionistic fuzzy neural network approach[J].Chinese Journal of Intelligent Science and Technology,2024,06(02):253-261. DOI： 10.11959/j.issn.2096-6652.202425.

摘要

空气中二氧化氮浓度的高低对环境保护和公共健康具有重要影响。目前二氧化氮浓度预测方法在表征时空关联性方面存在不足。鉴于此，提出了新的使用区间二型直觉模糊神经网络时空预测二氧化氮浓度的方法。首先，阐述了该区间二型直觉模糊神经网络框架，引入可变系数加权其隶属部分和非隶属部分的输出，并采用随机向量泛函链接神经网络作为规则后件；然后，为确定网络结构和参数，采用分层聚类算法得到模糊规则库，并通过最小二乘法优化网络后件的输出权值；最后，使用2018年1月至3月采集的北京市二氧化氮浓度真实数据进行数值验证。实验结果表明，与现有方法相比，该方法在短期和长期时空预测方面均取得了较高的预测精度和效率。

Abstract

The concentration of nitrogen dioxide (NO

) in the air significantly affects environmental protection and public health. Current methods for NO

concentration prediction lack sufficient characterization of spatiotemporal correlations. Therefore

this study proposes a novel approach using interval type-2 intuitionistic fuzzy neural networks (IT2IFNNs) for spatiotemporal prediction of NO

concentrations. Firstly

the framework of IT2IFNNs is elucidated

incorporating

variable coefficient weighting for its membership and non-membership outputs

and employing a random vector functional-link neural network (RVFLNN) as the rule consequent. Secondly

a hierarchical clustering algori

thm is employed to determine the fuzzy rule base and optimize the output weight values of the network consequents using least squares estimation. Finally

numerical validation is conducted using real NO

concentration data collected in Beijing from January to March 2018. Experimental results demonstrate that compared to existing methods

the proposed approach achieves superior prediction accuracy and efficiency in both short-term and long-term spatiotemporal prediction tasks.

关键词

Keywords

references

TAO C L, JIA M, WANG G Q, et al. Time-sensitive prediction of NO 2 concentration in China using an ensemble machine learning model from multi-source data[J ] . Journal of Environmental Sciences (China), 2024, 137: 30-40.

MUTHUKRISHNAN P, SHARMA R K. A short-term autoregressive model for the prediction of daily average NO 2 concentration in nagercoil, Tamil Nadu, India[J ] . Nature Environment and Pollution Technology, 2024, 23(1): 525-535.

ZHANG C X, LIU C, LI B, et al. Spatiotemporal neural network for estimating surface NO 2 concentrations over north China and their human health impact[J ] . Environmental Pollution, 2022, 307: Article No. 119510.

DOMHNAILL A Ó, BRODERICK B, O'MAHONY M. Integrated transportation and land use regression modelling for nitrogen dioxide mitigation[J]. Transportation Research Part D: Transport and Environment, 2023, 115: Article No. 103572.

VERMA A, RANGA V, VISHWAKARMA D K. BREATH-Net: a novel deep learning framework for NO 2 prediction using bi-directional encoder with transformer[J ] . Environmental Monitoring and Assessment, 2024, 196(4): 340.

LIU C H, WU S S, DAI Z, et al. High-resolution daily spatiotemporal distribution and evaluation of ground-level nitrogen dioxide concentration in the Beijing-Tianjin-Hebei region based on TROPOMI data[J]. Remote Sensing, 2023, 15(15): 3878.

伍冬睿, 曾志刚, 莫红, 等. 区间二型模糊集和模糊系统: 综述与展望[J]. 自动化学报, 2020, 46(8): 1539-1556.

WU D R, ZENG Z G, MO H, et al. Interval type-2 fuzzy sets and systems: overview and outlook[J]. Acta Automatica Sinica, 2020, 46(8): 1539-1556.

ABIYEV R, IDOKO J B, ALTIPARMAK H, et al. Fetal health state detection using interval type-2 fuzzy neural networks[J]. Diagnostics, 2023, 13(10): 1690.

ZHAO L. Application of interval type-2 fuzzy neural networks to predict short-term traffic flow[J]. International Journal of Computer Applications in Technology, 2012, 43(1): 67-75.

BAI K Y, ZHANG W Y, WEN S P, et al. A data-knowledge-driven interval type-2 fuzzy neural network with interpretability and self-adaptive structure[J]. Information Sciences, 2024, 660: Article No. 120133.

QIAO J F, SUN Z J, MENG X. A comprehensively improved interval type-2 fuzzy neural network for NO x emissions pre diction in MSWI process[J ] . IEEE Transactions on Industrial Informatics, 2023, 19(11): 11286-11297.

LIU C F, YEH C Y, LEE S J. Application of type-2 neuro-fuzzy modeling in stock price prediction[J]. Applied Soft Computing, 2012, 12(4): 1348-1358.

赵亮, 谢志峰, 张坤鹏, 等. 无线网络信号传输建模:一种区间二型模糊集成深度学习方法[J]. 智能科学与技术学报, 2020, 2(4): 401-411.

ZHAO L, XIE Z F, ZHANG K P, et al. Modeling signal propagation in wireless network: an interval type-2 fuzzy ensemble deep learning approach[J]. Journal of Intelligent Science and Technology, 2020, 2(4): 401-411.

SUN C X, LIU Z, WU X L, et al. Information orientation-based modular type-2 fuzzy neural network[J]. Information Sciences, 2024, 672: Article No. 120716.

LIU X, ZHAO T Y, CAO J T, et al. Design and prediction of self-organizing interval type-2 fuzzy wavelet neural network[J]. Information Sciences, 2024, 661: Article No. 120157.

ATANASSOV K T. Intuitionistic fuzzy sets[M]//Intuitionistic Fuzzy Sets. Heidelberg: Physica-Verlag HD, 1999: 1-137.

赵涛, 肖建. 二型直觉模糊集[J]. 控制理论与应用, 2012, 29(9): 1215-1222.

ZHAO T, XIAO J. Type-2 intuitionistic fuzzy sets[J]. Control Theory & Applications, 2012, 29(9): 1215-1222.

LI L, YANG J, WU W. Intuitionistic fuzzy hopfield neural network and its stability[J]. Neural Network World, 2011, 21(5): 461-472.

HÁJEK P, OLEJ V. Intuitionistic fuzzy neural network: the case of credit scoring using text information[C]//Proceedings of the International Conference on Engineering Applications of Neural Networks. Cham: Springer, 2015: 337-346.

PAO Y H, PARK G H, SOBAJIC D J. Learning and generalization characteristics of the random vector functional-link net[J]. Neurocomputing, 1994, 6(2): 163-180.

ATANASSOV K, GARGOV G. Interval valued intuitionistic fuzzy sets[J]. Fuzzy Sets and Systems, 1989, 31(3): 343-349.

SUYKENS J A K, VANDEWALLE J. Least squares support vector machine classifiers[J]. Neural Processing Letters, 1999, 9(3): 293-300.

HUANG G B, ZHU Q Y, SIEW C K. Extreme learning machine: theory and applications[J]. Neurocomputing, 2006, 70: 489-501.

浏览量

295

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

Cerberus：基于深度学习的跨站社交网络机器人检测系统