Effects of hyperspectral data transformations on urban inter-class separations using a support vector machine

This study investigated the performance of different data types used in a hyperspectral data classification process. Data in the form of spectral reflectance, first derivative spectra and wavelet coefficients were used as inputs for the Support Vector Machine (SVM) algorithm used to classify five di...

Full description

Bibliographic Details
Main Authors: Misman, Muhamad Afizzul, Mohd Shafri, Helmi Zulhaidi, Raja Ahmad, Raja Mohd Kamil
Format: Article
Language:English
Published: Asian Network for Scientific Information 2010
Online Access:http://psasir.upm.edu.my/id/eprint/14357/
http://psasir.upm.edu.my/id/eprint/14357/1/Effects%20of%20hyperspectral%20data%20transformations%20on%20urban%20inter-class%20separations%20using%20a%20support%20vector%20machine.pdf
_version_ 1848842371226140672
author Misman, Muhamad Afizzul
Mohd Shafri, Helmi Zulhaidi
Raja Ahmad, Raja Mohd Kamil
author_facet Misman, Muhamad Afizzul
Mohd Shafri, Helmi Zulhaidi
Raja Ahmad, Raja Mohd Kamil
author_sort Misman, Muhamad Afizzul
building UPM Institutional Repository
collection Online Access
description This study investigated the performance of different data types used in a hyperspectral data classification process. Data in the form of spectral reflectance, first derivative spectra and wavelet coefficients were used as inputs for the Support Vector Machine (SVM) algorithm used to classify five different classes. The first derivative spectra gave a lower classification accuracy (35.6%) than the spectral reflectance (82%) and the use of wavelet coefficients further improved the classification accuracy to 100%. Proper selection of the wavelet transformation method, the mother wavelet, the number of vanishing moments and the decomposition level could improve classification accuracy. In summary, wavelet coefficients could maximise discrimination capability as compared to the spectral reflectance and first derivative spectra.
first_indexed 2025-11-15T07:58:04Z
format Article
id upm-14357
institution Universiti Putra Malaysia
institution_category Local University
language English
last_indexed 2025-11-15T07:58:04Z
publishDate 2010
publisher Asian Network for Scientific Information
recordtype eprints
repository_type Digital Repository
spelling upm-143572019-04-08T08:33:48Z http://psasir.upm.edu.my/id/eprint/14357/ Effects of hyperspectral data transformations on urban inter-class separations using a support vector machine Misman, Muhamad Afizzul Mohd Shafri, Helmi Zulhaidi Raja Ahmad, Raja Mohd Kamil This study investigated the performance of different data types used in a hyperspectral data classification process. Data in the form of spectral reflectance, first derivative spectra and wavelet coefficients were used as inputs for the Support Vector Machine (SVM) algorithm used to classify five different classes. The first derivative spectra gave a lower classification accuracy (35.6%) than the spectral reflectance (82%) and the use of wavelet coefficients further improved the classification accuracy to 100%. Proper selection of the wavelet transformation method, the mother wavelet, the number of vanishing moments and the decomposition level could improve classification accuracy. In summary, wavelet coefficients could maximise discrimination capability as compared to the spectral reflectance and first derivative spectra. Asian Network for Scientific Information 2010 Article PeerReviewed text en http://psasir.upm.edu.my/id/eprint/14357/1/Effects%20of%20hyperspectral%20data%20transformations%20on%20urban%20inter-class%20separations%20using%20a%20support%20vector%20machine.pdf Misman, Muhamad Afizzul and Mohd Shafri, Helmi Zulhaidi and Raja Ahmad, Raja Mohd Kamil (2010) Effects of hyperspectral data transformations on urban inter-class separations using a support vector machine. Journal of Applied Sciences, 10 (19). pp. 2241-2250. ISSN 1812-5654; ESSN: 1812-5662 https://scialert.net/abstract/?doi=jas.2010.2241.2250 10.3923/jas.2010.2241.2250
spellingShingle Misman, Muhamad Afizzul
Mohd Shafri, Helmi Zulhaidi
Raja Ahmad, Raja Mohd Kamil
Effects of hyperspectral data transformations on urban inter-class separations using a support vector machine
title Effects of hyperspectral data transformations on urban inter-class separations using a support vector machine
title_full Effects of hyperspectral data transformations on urban inter-class separations using a support vector machine
title_fullStr Effects of hyperspectral data transformations on urban inter-class separations using a support vector machine
title_full_unstemmed Effects of hyperspectral data transformations on urban inter-class separations using a support vector machine
title_short Effects of hyperspectral data transformations on urban inter-class separations using a support vector machine
title_sort effects of hyperspectral data transformations on urban inter-class separations using a support vector machine
url http://psasir.upm.edu.my/id/eprint/14357/
http://psasir.upm.edu.my/id/eprint/14357/
http://psasir.upm.edu.my/id/eprint/14357/
http://psasir.upm.edu.my/id/eprint/14357/1/Effects%20of%20hyperspectral%20data%20transformations%20on%20urban%20inter-class%20separations%20using%20a%20support%20vector%20machine.pdf