Simple Search:

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


Citation

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

Abstract / Synopsis

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.


Download File

[img]
Preview
PDF (Abstract)
Effects of hyperspectral data transformations on urban inter-class separations using a support vector machine.pdf

Download (35kB) | Preview

Additional Metadata

Item Type: Article
Divisions: Faculty of Engineering
Institute of Advanced Technology
DOI Number: https://doi.org/10.3923/jas.2010.2241.2250
Publisher: Asian Network for Scientific Information
Keywords: Hyperspectral; First derivative; Wavelet coefficients; Support vector machine
Depositing User: Nabilah Mustapa
Date Deposited: 08 Apr 2019 16:33
Last Modified: 08 Apr 2019 16:33
Altmetrics: http://www.altmetric.com/details.php?domain=psasir.upm.edu.my&doi=10.3923/jas.2010.2241.2250
URI: http://psasir.upm.edu.my/id/eprint/14357
Statistic Details: View Download Statistic

Actions (login required)

View Item View Item