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

dc.contributor.authorKaraca, Ferhat
dc.contributor.authorNikov, Alexander
dc.contributor.authorAlagha, Omar
dc.date.accessioned2011-06-14T12:03:42Z
dc.date.available2011-06-14T12:03:42Z
dc.date.issued2011-06-14
dc.description.abstractA 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 performanceen_US
dc.identifier.urihttps://hdl.handle.net/2139/10116
dc.language.isoenen_US
dc.subjectair pollutionen_US
dc.subjectmodellingen_US
dc.subjectbackpropagation algorithmsen_US
dc.subjectoptimisationen_US
dc.subjectenvironmental pollutionen_US
dc.subjectpollution evaluationen_US
dc.subjectpollution controlen_US
dc.subjectneural networksen_US
dc.subjectweather forecasting dataen_US
dc.subjectTurkeyen_US
dc.subjecttraining errorsen_US
dc.titleNN-AirPol: a neural-networks-based method for air pollution evaluation and controlen_US
dc.typeArticleen_US

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
airpol.html
Size:
402 B
Format:
Hypertext Markup Language
Description:
NN-AirPol: a neural-networks-based method for air pollution evaluation and control
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.78 KB
Format:
Item-specific license agreed upon to submission
Description: