Prediction of drinking water quality using back-propagation neural network / Wan Radziah Wan Abdul Rahim

Wan Abdul Rahim, Wan Radziah (2006) Prediction of drinking water quality using back-propagation neural network / Wan Radziah Wan Abdul Rahim. Degree thesis, Universiti Teknologi MARA.

[img]
Preview
Text
TB_WAN RADZIAH WAN ABDUL RAHIM CS 06_5 P01.pdf

Download (55kB) | Preview

Abstract

Water is very important in our daily life. Without safety water every living thing in this planet will die. People can survive 7 to 10 days without foods but can survive 1 to 3 days without water ("National Ag Safety Database", 2002). Human bodies consist of 70% of water. This statement proved that water is very important element in this planet to make sure every living thing can continue their life. Nowadays, people are concerned about water sources such as from fresh water, ground water and river for drink. Some of them are not safe and does not achieve standard of safe and healthy to drink and use. The purposed of this project is to solve this problem by predict the drinking water quality using Artificial Neural Network (ANN). It is focus on pH, manganese, iron and turbidity of water. A Back-propagation neural network is used in this project and it is fully develop using MATLAB. With the development of drinking water quality prediction, it provides the result either the water quality or not based on the trained water data. Within this result, the water company can improved the drinking water quality level to make sure the consumer get the healthy water.

Item Type: Thesis (Degree)
Creators:
CreatorsEmail
Wan Abdul Rahim, Wan RadziahUNSPECIFIED
Subjects: Q Science > QA Mathematics > Instruments and machines > Electronic computers. Computer science
Q Science > QA Mathematics > Instruments and machines > Electronic computers. Computer science
Divisions: Faculty of Information Technology and Quantitative Sciences
Item ID: 1009
Last Modified: 19 Oct 2018 07:17
Depositing User: Staf Pendigitalan 1
URI: http://ir.uitm.edu.my/id/eprint/1009

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year