Date of Award

1-1-2012

Thesis Type

masters

Document Type

Thesis

Divisions

science

Department

Institute of Biological Sciences

Institution

University of Malaya

Abstract

Water quality monitoring is very important to control the quality of water. Lake Bera and Lake Chini which are known as a very important wetland are used to apply SVM method to predict its water quality. The output used to predict the classification of high medium and low is the dissolved oxygen according to the standard provided by the Interim National Water Quality Standard of Malaysia and Department of Environment. The training and test data is divided to 80% for training data and 20% for testing data. The SVM is implemented using R software package kernlab which used ksvm as its implementation to do prediction. Kernel Anova was used to create the model. The result shows that the predicted accuracy is about 74%.

Note

Dissertation submitted in fulfilment of the requirement for the degree of Master of Science

Share

COinS