Document Detail

Prediction models of CO, SPM and SO(2) concentrations in the Campo de Gibraltar Region, Spain: a multiple comparison strategy.
MedLine Citation:
PMID:  17929183     Owner:  NLM     Status:  MEDLINE    
The 'Campo de Gibraltar' region is a very industrialized area where very few air pollution studies have been carried out. Up to date, no model has been developed in order to predict air pollutant levels in the different towns spread in the region. Carbon monoxide (CO), Sulphur dioxide (SO(2)) and suspended particulate matter (SPM) series have been investigated (years 1999-2000-2001). Multilayer perceptron models (MLPs) with backpropagation learning rule have been used. A resampling strategy with two-fold crossvalidation allowed the statistical comparison of the different models considered in this study. Artificial neural networks (ANN) models were compared with Persistence and ARIMA models and also with models based on standard Multiple Linear Regression (MLR) over test sets with data that had not been used in the training stage. The models based on ANNs showed better capability of generalization than those based on MLR. The designed procedure of random resampling permits an adequate and robust multiple comparison of the tested models. Principal component analysis (PCA) is used to reduce the dimensionality of data and to transform exogenous variables into significant and independent components. Short-term predictions were better than medium-term predictions in the case of CO and SO(2) series. Conversely, medium-term predictions were better in the case of SPM concentrations. The predictions are significantly promising (e.g., d (SPM 24-ahead) = 0.906, d (CO 1-ahead) = 0.891, d (SO2 1-ahead) = 0.851).
Ignacio J Turias; Francisco J González; Ma Luz Martin; Pedro L Galindo
Related Documents :
22354193 - Effects of botulinum toxin type a on collagen deposition in hypertrophic scars.
19417463 - An inverse problem solution for undetermined electrostatic force microscopy setups usin...
23011053 - Psychometric analysis of the perceptions of computerized therapy questionnaire-patient ...
Publication Detail:
Type:  Comparative Study; Journal Article; Research Support, Non-U.S. Gov't     Date:  2007-10-11
Journal Detail:
Title:  Environmental monitoring and assessment     Volume:  143     ISSN:  0167-6369     ISO Abbreviation:  Environ Monit Assess     Publication Date:  2008 Aug 
Date Detail:
Created Date:  2008-07-08     Completed Date:  2008-10-27     Revised Date:  2009-05-11    
Medline Journal Info:
Nlm Unique ID:  8508350     Medline TA:  Environ Monit Assess     Country:  Netherlands    
Other Details:
Languages:  eng     Pagination:  131-46     Citation Subset:  IM    
Department of Computer Science - Research Group "Intelligent Systems", Polytechnic Engineering School of Algeciras, University of Cádiz, Algeciras, Spain.
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Air Pollution / analysis*
Carbon Monoxide / analysis*
Environmental Monitoring / methods
Models, Theoretical*
Particulate Matter / analysis*
Reproducibility of Results
Sulfur Dioxide / analysis*
Reg. No./Substance:
0/Particulate Matter; 630-08-0/Carbon Monoxide; 7446-09-5/Sulfur Dioxide

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine

Previous Document:  Continuous and filter-based measurements of PM 2.5 nitrate and sulfate at the Fresno Supersite.
Next Document:  Predicting photochemical pollution in an industrial area.