Forecasting of air pollution in urban areas by means of artificial neural networks

机译：人工神经网络预测城市空气污染

获取原文

获取原文并翻译 | 示例

页面导航

摘要
著录项
相似文献
相关主题

摘要

The paper addresses the problem of optimum data dimensionality reduction in relation to analysis of weather factors and their influence on the recorded air pollution concentrations in urban areas. Eight weather parameters and two air pollution factors, namely concentrations of SO_2 and suspended particulate are considered in the study. Principal component analysis, is the method used for an optimum decorrelation and dimensionality reduction of the analysed weather factors. The amount of information removed from the data due to dimensionality reduction is evaluated. Further in the study, a method for prediction of the concentration of suspended particulate and SO_2 based on the artificial neural networks was developed with a possibility to forecast the pollution level one day in advance. As input values the four uncorrelated components of the climatic vector in a given moment of time and the level of pollution from two previous days were taken. The training set consisted of 475 training data sets (including 5 previous years) and 80 test sets (covering forecasts made in advance). Mean accuracy of 5.6% for the test set and of 4.3% for test data was obtained.

机译：本文针对与天气因素分析有关的最佳数据降维问题及其对城市地区记录的空气污染浓度的影响。研究中考虑了八个天气参数和两个空气污染因子，即SO_2和悬浮颗粒物的浓度。主成分分析是用于对所分析的天气因素进行最佳去相关和降维的方法。评估由于降维而从数据中删除的信息量。进一步的研究中，开发了一种基于人工神经网络的悬浮颗粒物和SO_2浓度预测方法，可以提前一天预测污染水平。输入值是在给定时间内气候矢量的四个不相关成分以及前两天的污染水平作为输入值。培训集包括475个培训数据集（包括前5年）和80个测试集（包括预先做出的预测）。测试装置的平均准确度为5.6％，测试数据的平均准确度为4.3％。

著录项

来源
《Urban transport V : Urban transport and the envoronment for the 21st century》|2000年|115-124|共10页
会议地点 Cambridge(GB);Cambridge(GB)
作者
W. Kaminski; J. Skrzypski; P. Strumillo;
展开▼
作者单位

Faculty of Process and Environmental Engineering, Technical University of Lodz, Wolczanska 213, 93-005 Lodz, Poland;

Faculty of Process and Environmental Engineering, Technical University of Lodz, Wolczanska 213, 93-005 Lodz, Poland;

Faculty of Electrical and Electronics Engineering, Technical University of Lodz, Stefanowskiego 18/22, 90-537 Lodz, Poland;

展开▼
会议组织
原文格式 PDF
正文语种 eng
中图分类综合运输;
关键词

相似文献

外文文献
中文文献
专利

1. EXPERIMENTAL AND ARTIFICIAL NEURAL NETWORK APPROACH FOR FORECASTING OF TRAFFIC AIR POLLUTION IN URBAN AREAS: THE CASE OF SUBOTICA [J] . Bogdana B. VUJIĆ, Srđan M. VUKMIROVIĆ, Goran V. VUJIĆ, Thermal science . 2010,第SUPPLa期

机译：城市人工交通空气污染预测的实验和人工神经网络方法：以Subotica为例
2. Experimental and artificial neural network approach for forecasting of traffic air pollution in urban areas: The case of Subotica [J] . Vuji? Bogdana, Vukmirovi? Sr?an, Vuji? Goran, Thermal science . 2010,第suppla期

机译：实验和人工神经网络方法预测城市交通空气污染：以苏博蒂察为例
3. An Outlook of Ozone Air Pollution through Comparative Analysis of Artificial Neural Network, Regression, and Sensitivity ModelsAn Outlook of Ozone Air Pollution Through Comparative Analysis of Artificial Neural Network, Regression, and Sensitivity Models [J] . J. S. Khan, S. Khoso, Z. Iqbal, Engineering Technology and Applied Science Research . 2018,第5期

机译：通过人工神经网络，回归和敏感性模型的比较分析，对臭氧空气污染的展望通过人工神经网络，回归和敏感性模型的比较分析，对臭氧空气污染的展望。
4. Forecasting of air pollution in urban areas by means of artificial neural networks [C] . International conference on urban transport and the environment for the 21st century . 2000

机译：通过人工神经网络预测城市地区空气污染
5. Modelling of urban air pollution in the Edmonton Strathconoa Industrial Area using artificial neural networks. [D] . Hasham, Faizal Ali. 1998

机译：使用人工神经网络对埃德蒙顿Strathconoa工业区的城市空气污染进行建模。
6. Multi-Horizon Air Pollution Forecasting with Deep Neural Networks [O] . Mirche Arsov, Eftim Zdravevski, Petre Lameski, 2021

机译：深神经网络多地平气污染预测
7. Experimental and artificial neural network approach for forecasting of traffic air pollution in urban areas: The case of Subotica [O] . Bogdana Vujic, Srdjan Vukmirovic, Goran Vujic, 2010

机译：城市交通空气污染预测的实验和人工神经网络方法：沉皮病的情况

Forecasting of air pollution in urban areas by means of artificial neural networks

摘要

著录项

相似文献

相关主题

期刊订阅