NN-AirPol: a neural-networks-based method for air pollution evaluation and control

Show simple item record

dc.contributor.author Karaca, Ferhat
dc.contributor.author Nikov, Alexander
dc.contributor.author Alagha, Omar
dc.date.accessioned 2011-06-14T12:03:42Z
dc.date.available 2011-06-14T12:03:42Z
dc.date.issued 2011-06-14
dc.identifier.uri http://hdl.handle.net/2139/10116
dc.description.abstract A method for air pollution evaluation and control, based on one of the most popular neural networks – the backpropagation algorithm, is proposed. After the backpropagation training, the neural network, based on weather forecasting data, determines the future concentration of critical air pollution indicators. Depending on these concentrations, relevant episode warnings and actions are activated. A case study is carried out to illustrate and validate the method proposed, based on Istanbul air pollution data. Sulphur dioxide and inhalable particulate matter are selected as air pollution indicators (neural network outputs). Relevant episode measures are proposed. Among ten backpropagation algorithms, the BFGS algorithm (Quasi-Newton algorithms) is adopted since it showed the lowest training error. A comparison of NN-AirPol method against regression and perceptron models showed significantly better performance en_US
dc.language.iso en en_US
dc.subject air pollution en_US
dc.subject modelling en_US
dc.subject backpropagation algorithms en_US
dc.subject optimisation en_US
dc.subject environmental pollution en_US
dc.subject pollution evaluation en_US
dc.subject pollution control en_US
dc.subject neural networks en_US
dc.subject weather forecasting data en_US
dc.subject Turkey en_US
dc.subject training errors en_US
dc.title NN-AirPol: a neural-networks-based method for air pollution evaluation and control en_US
dc.type Article en_US


Files in this item

Files Size Format View Description
airpol.html 402bytes HTML View/Open NN-AirPol: a neural-networks-based method for air pollution evaluation and control

This item appears in the following Collection(s)

Show simple item record

Search UWISpace


Advanced Search

Browse

My Account