Estimation of wastewater pollution levels by machine learning

Pao Yue-kong Library Electronic Theses Database

Estimation of wastewater pollution levels by machine learning


Author: Hon, W. K. Haney
Title: Estimation of wastewater pollution levels by machine learning
Degree: M.Sc.
Year: 1996
Subject: Sewage -- Environmental aspects
Water -- Pollution
Hong Kong Polytechnic University -- Dissertations
Department: Multi-disciplinary Studies
Pages: iii, 103 p. : ill. ; 30 cm
Language: English
InnoPac Record:
Abstract: To protect the aquatic environment, the discharges of polluting substance in domestic sewage and industrial wastewater must be carefully monitored and controlled. Therefore, samples are to be taken from wastewater discharged and domestic sewage for determination of pollution levels. With the huge number of wastewater samples to be analyzed, methods able to estimate the pollution levels in these wastewater samples urgently needed. Those methods should be easy to be operated, economical, fast and able to adapt to the rapidly changing properties of the wastewater samples. Theoretically, both the pollution levels and the observable properties of the wastewater samples are originated from their chemical natures, there might be some relationship, direct or indirect between these two sets of properties in the wastewater samples. In this study, machine learning systems specifically artificial neural networks and ID3 algorithm were used to find the hidden relationship and attempted to be used for estimation of the pollution levels of wastewater samples from their observable properties. The results revealed that artificial neural networks were capable of storing the knowledge and performed quite well in the estimation of pollution levels in wastewater samples within the training set. However, with the training data in this study, neither artificial neural networks nor ID3 algorithm could effectively generalize the knowledge and accurately predict the pollution levels in wastewater samples outside the training set.

Files in this item

Files Size Format
b12339775.pdf 7.285Mb PDF
Copyright Undertaking
As a bona fide Library user, I declare that:
  1. I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
  2. I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
  3. I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.
By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.


Quick Search


More Information