A comparison of support vector machine and decision tree classifications using satellite data of Langkawi Island

Mohd Shafri, Helmi Zulhaidi and Ramle, F. S. H. (2009) A comparison of support vector machine and decision tree classifications using satellite data of Langkawi Island. Information Technology Journal, 8 (1). pp. 64-70. ISSN 1812-5638

[img] PDF
1409Kb

Abstract

This study investigates a new approach in image classification. Two classifiers were used to classify SPOT 5 satellite image; Decision Tree (DT) and Support Vector Machine (SVM). The Decision Tree rules were developed manually based on Normalized Difference Vegetation Index (NDVI) and Brightness Value (BV) variables. The classification using SVM method was implemented automatically by using four kernel types; linear, polynomial, radial basis function and sigmoid. The study indicates that the classification accuracy of SVM algorithm was better than DT algorithm. The overall accuracy of the SVM using four kernel types was above 73% and the overall accuracy of the DT method was 69%.

Item Type:Article
Keyword:Classifiers, Remote sensing, Artificial intelligence, Biodiversity
Subject:Remote-sensing - Malaysia
Subject:Decision trees - Malaysia
Subject:Plant diversity - Malaysia
Faculty or Institute:Faculty of Engineering
Publisher:Asian Network for Scientific Information
ID Code:18007
Deposited By: Anas Yahaya
Deposited On:08 Aug 2011 07:42
Last Modified:27 May 2013 07:57

Repository Staff Only: item control page

Document Download Statistics

This item has been downloaded for since 08 Aug 2011 07:42.

View statistics for "A comparison of support vector machine and decision tree classifications using satellite data of Langkawi Island"


Universiti Putra Malaysia Institutional Repository

Universiti Putra Malaysia Institutional Repository is an on-line digital archive that serves as a central collection and storage of scientific information and research at the Universiti Putra Malaysia.

Currently, the collections deposited in the IR consists of Master and PhD theses, Master and PhD Project Report, Journal Articles, Journal Bulletins, Conference Papers, UPM News, Newspaper Cuttings, Patents and Inaugural Lectures.

As the policy of the university does not permit users to view thesis in full text, access is only given to the first 24 pages only.