UM  > 科技學院  > 土木及環境工程系
Is a complex neural network based air quality prediction model better than a simple one? A Bayesian point of view
Hoi K.I.; Yuen K.V.; Mok K.M.
2010-08-24
Conference Name2nd International Symposium on Computational Mechanics 12th International Conference on the Enhancement and Promotion of Computational Methods in Engineering and Science
Source PublicationAIP Conference Proceedings
Volume1233
IssuePART 1
Pages764-769
Conference DateNOV 30-DEC 03, 2009 & DEC 02-03, 2009
Conference PlaceHong Kong & Macau, PEOPLES R CHINA
PublisherAMER INST PHYSICS, 2 HUNTINGTON QUADRANGLE, STE 1NO1, MELVILLE, NY 11747-4501 USA
Abstract

In this study the neural network based air quality prediction model was tested in a typical coastal city, Macau, with Latitude 22°10'N and Longitude 113°34'E. By using five years of air quality and meteorological data recorded at an ambient air quality monitoring station between 2001 and 2005, it was found that the performance of the ANN model was generally improved by increasing the number of hidden neurons in the training phase. However, the performance of the ANN model was not sensitive to the change in the number of hidden neurons during the prediction phase. Therefore, the improvement in the error statistics for a complex ANN model in the training phase may be only caused by the overfitting of the data. In addition, the posterior PDF of the parameter vector conditional on the training dataset was investigated for different number of hidden neurons. It was found that the parametric space for a simple ANN model was globally identifiable and the Levenberg-Marquardt backpropagation algorithm was able to locate the optimal parameter vector. However, the parameter vector might contain redundant parameters and the parametric space was not globally identifiable when the model class became complex. In addition, the Levenberg-Marquardt backpropagation algorithm was unable to locate the most optimal parameter vector in this situation. Finally, it was concluded that the a more complex MLP model, that fits the data better, is not necessarily better than a simple one. 

KeywordAir Quality Prediction Artificial Neural Network Bayesian Approach Macau Pm10
DOIhttps://doi.org/10.1063/1.3452273
URLView the original
Indexed BySCI
Language英语
WOS Research AreaEngineering ; Mathematics ; Mechanics
WOS SubjectEngineering, Civil ; Engineering, Mechanical ; Mathematics, Applied ; Mechanics
WOS IDWOS:000283003800131
Fulltext Access
Citation statistics
Document TypeConference paper
CollectionDEPARTMENT OF CIVIL AND ENVIRONMENTAL ENGINEERING
AffiliationDepartment of Civil and Environmental Engineering, University of Macau
First Author AffilicationUniversity of Macau
Recommended Citation
GB/T 7714
Hoi K.I.,Yuen K.V.,Mok K.M.. Is a complex neural network based air quality prediction model better than a simple one? A Bayesian point of view[C]:AMER INST PHYSICS, 2 HUNTINGTON QUADRANGLE, STE 1NO1, MELVILLE, NY 11747-4501 USA,2010:764-769.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Hoi K.I.]'s Articles
[Yuen K.V.]'s Articles
[Mok K.M.]'s Articles
Baidu academic
Similar articles in Baidu academic
[Hoi K.I.]'s Articles
[Yuen K.V.]'s Articles
[Mok K.M.]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Hoi K.I.]'s Articles
[Yuen K.V.]'s Articles
[Mok K.M.]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.