Estimation of air pollutant index (API) in Klang valley using artificial neural network (ANN) / Roshaslinie Amdam@Ramli

The air pollution problems has received more attention during the last decades whereby there has been a significant increase in public awareness of the potential dangers caused by chemical pollutants and their effects both human beings and the environment. To overcome these problems, the need for ac...

Full description

Saved in:
Bibliographic Details
Main Author: Amdam@Ramli, Roshaslinie
Format: Thesis
Language:English
Published: 2009
Online Access:https://ir.uitm.edu.my/id/eprint/81945/1/81945.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The air pollution problems has received more attention during the last decades whereby there has been a significant increase in public awareness of the potential dangers caused by chemical pollutants and their effects both human beings and the environment. To overcome these problems, the need for accurate estimates of air pollutant index (API) becomes important. To achieve such estimation tasks, the use of artificial neural network (ANN) is regarded as an effective technique. The purpose of this paper, ANN trained with feed-forward back-propagation algorithm is used to estimate the air pollutant index (API). The API system normally includes the major air pollutants which are ozone (O3), carbon monoxide (CO), nitrogen dioxide (NO2), sulphur dioxide (SO2) and suspended particulate matter of less than 10 microns in size (PM10). This method uses the past raw data values to estimate the API. The data collected comprises of data for the previous three month, beginning from October 2006 for Klang Valley areas which are Shah Alam, Klang, Petaling Jaya and Kuala Lumpur. The results indicate that the ANN model estimated API with good accuracy to more than 90%.