Cover Image

Spectral feature selection and classification of roofing materials using field spectroscopy data

Impervious surface discrimination and mapping are important in urban and environ-mental studies. Confusion in discriminating urban materials using multispectral systems has led to the use of hyperspectral remote sensing data as an effective way to improve urban analysis. However, the high dimensiona...

Full description

Saved in:
Bibliographic Details
Main Authors: Samsudin, Sarah Hanim, M. Shafri, Helmi Z., Hamedianfar, Alireza, Mansor, Shattri
Format: Article
Language:English
Published: Society of Photo-optical Instrumentation Engineers 2015
Online Access:http://psasir.upm.edu.my/id/eprint/46361/1/Spectral%20feature%20selection%20and%20classification%20of%20roofing%20materials%20using%20field%20spectroscopy%20data.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
id oai:psasir.upm.edu.my:46361
record_format eprints
spelling oai:psasir.upm.edu.my:46361 http://psasir.upm.edu.my/id/eprint/46361/ Spectral feature selection and classification of roofing materials using field spectroscopy data Samsudin, Sarah Hanim M. Shafri, Helmi Z. Hamedianfar, Alireza Mansor, Shattri Impervious surface discrimination and mapping are important in urban and environ-mental studies. Confusion in discriminating urban materials using multispectral systems has led to the use of hyperspectral remote sensing data as an effective way to improve urban analysis. However, the high dimensionality of these data needs to be reduced to extract significant wave-lengths useful in roof discrimination. Therefore, this research used feature selection algorithms of the support vector machine (SVM), genetic algorithm (GA), and random forest (RF) to select the most significant wavelengths, and the separability between classes was assessed using the SVM classification. Accordingly, the visible, shortwave infrared-1, and shortwave infrared-2regions were most important in distinguishing different roofing materials and conditions. A comparative analysis of the feature selection models showed that the highest accuracy of 97.53% was obtained using significant wavelengths produced by RF. Accuracy of spectra without feature selection was also investigated, and the result was lower compared with classification using significant wavelengths, except for the accuracy of roof type classification, which produced an accuracy similar to SVM and GA (96.30%). This study offers new insight into within-class urban spectral classification, and the results may be used as the basis for the development of urban material indices in the future. Society of Photo-optical Instrumentation Engineers 2015-05 Article PeerReviewed text en http://psasir.upm.edu.my/id/eprint/46361/1/Spectral%20feature%20selection%20and%20classification%20of%20roofing%20materials%20using%20field%20spectroscopy%20data.pdf Samsudin, Sarah Hanim and M. Shafri, Helmi Z. and Hamedianfar, Alireza and Mansor, Shattri (2015) Spectral feature selection and classification of roofing materials using field spectroscopy data. Journal of Applied Remote Sensing, 9 (1). 095079-1. ISSN 1931-3195 https://www.spiedigitallibrary.org/journals/journal-of-applied-remote-sensing/volume-9/issue-1/095079/Spectral-feature-selection-and-classification-of-roofing-materials-using-field/10.1117/1.JRS.9.095079.short?SSO=1 10.1117/1.JRS.9.095079
institution UPM IR
collection UPM IR
language English
description Impervious surface discrimination and mapping are important in urban and environ-mental studies. Confusion in discriminating urban materials using multispectral systems has led to the use of hyperspectral remote sensing data as an effective way to improve urban analysis. However, the high dimensionality of these data needs to be reduced to extract significant wave-lengths useful in roof discrimination. Therefore, this research used feature selection algorithms of the support vector machine (SVM), genetic algorithm (GA), and random forest (RF) to select the most significant wavelengths, and the separability between classes was assessed using the SVM classification. Accordingly, the visible, shortwave infrared-1, and shortwave infrared-2regions were most important in distinguishing different roofing materials and conditions. A comparative analysis of the feature selection models showed that the highest accuracy of 97.53% was obtained using significant wavelengths produced by RF. Accuracy of spectra without feature selection was also investigated, and the result was lower compared with classification using significant wavelengths, except for the accuracy of roof type classification, which produced an accuracy similar to SVM and GA (96.30%). This study offers new insight into within-class urban spectral classification, and the results may be used as the basis for the development of urban material indices in the future.
format Article
author Samsudin, Sarah Hanim
M. Shafri, Helmi Z.
Hamedianfar, Alireza
Mansor, Shattri
spellingShingle Samsudin, Sarah Hanim
M. Shafri, Helmi Z.
Hamedianfar, Alireza
Mansor, Shattri
Spectral feature selection and classification of roofing materials using field spectroscopy data
author_facet Samsudin, Sarah Hanim
M. Shafri, Helmi Z.
Hamedianfar, Alireza
Mansor, Shattri
author_sort Samsudin, Sarah Hanim
title Spectral feature selection and classification of roofing materials using field spectroscopy data
title_short Spectral feature selection and classification of roofing materials using field spectroscopy data
title_full Spectral feature selection and classification of roofing materials using field spectroscopy data
title_fullStr Spectral feature selection and classification of roofing materials using field spectroscopy data
title_full_unstemmed Spectral feature selection and classification of roofing materials using field spectroscopy data
title_sort spectral feature selection and classification of roofing materials using field spectroscopy data
publisher Society of Photo-optical Instrumentation Engineers
publishDate 2015
url http://psasir.upm.edu.my/id/eprint/46361/1/Spectral%20feature%20selection%20and%20classification%20of%20roofing%20materials%20using%20field%20spectroscopy%20data.pdf
_version_ 1782722271368970240
score 12.933938

Similar Items