UPM Institutional Repository

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


Citation

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; ESSN: 1812-5646

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%.


Download File

[img]
Preview
PDF (Abstract)
A comparison of support vector machine and decision tree classifications using satellite data of Langkawi Island.pdf

Download (83kB) | Preview
Official URL or Download Paper: http://scialert.net/abstract/?doi=itj.2009.64.70

Additional Metadata

Item Type: Article
Subject: Remote-sensing - Malaysia
Subject: Decision trees - Malaysia
Subject: Plant diversity - Malaysia
Divisions: Faculty of Engineering
DOI Number: https://doi.org/10.3923/itj.2009.64.70
Publisher: Asian Network for Scientific Information
Keywords: Classifiers; Remote sensing; Artificial intelligence; Biodiversity
Depositing User: Anas Yahaya
Date Deposited: 08 Aug 2011 07:42
Last Modified: 23 Oct 2015 02:21
Altmetrics: http://www.altmetric.com/details.php?domain=psasir.upm.edu.my&doi=10.3923/itj.2009.64.70
URI: http://psasir.upm.edu.my/id/eprint/18007
Statistic Details: View Download Statistic

Actions (login required)

View Item View Item