Cite Article
Utilization of Band Combination for Feature Selection in Machine Learning-Based Roof Material Types Identification
Choose citation formatBibTeX
@article{IJASEIT13102, author = {Ayom Widipaminto and Yohanes Fridolin Hestrio and Donna Monica and Yuvita Dian Safitri and Dedi Irawadi and - Rokhmatuloh and Djoko Triyono and Erna Sri Adiningsih}, title = {Utilization of Band Combination for Feature Selection in Machine Learning-Based Roof Material Types Identification}, journal = {International Journal on Advanced Science, Engineering and Information Technology}, volume = {11}, number = {5}, year = {2021}, pages = {1897--1902}, keywords = {Material identification; band combination; reflectance responses.}, abstract = {Land monitoring requires remote sensing data, which varies in its spectral and spatial resolution. Remote sensing data with the high spatial resolution is especially needed for urban monitoring. However, high spatial resolution data is usually expensive with limited coverage and complex analysis. This paper aims to find the most efficient way to do urban monitoring, specifically surface material identification. In material identification, the distinctive feature that can be used to differentiate one material surface from one another is its reflectance responses. This leads to a question of which absorption features are significant to different surface materials, especially roofing materials, and which absorption features are not discriminant enough to be used at classification. This paper proposed a machine learning-based identification of roof material types using band combinations as classification features. The experiment was done on Pleiades data, multispectral satellite imagery with very high spatial resolution. We first calculated the image’s reflectance values for each band and then grouped them based on their spectral range, yielding 11 possible combinations as the classification features. The experiment found that reflectance responses for band Red and NIR are the most distinctive trait of a material type and thus sufficient for material identification. We minimized the number of spectral responses used in material identification down to two bands, which can help the data collection and processing of material identification easier, cheaper, and less time-cost. Our experiment yields overall accuracy of 0.9959, with a computational time of 19.72 seconds.}, issn = {2088-5334}, publisher = {INSIGHT - Indonesian Society for Knowledge and Human Development}, url = {http://ijaseit.insightsociety.org/index.php?option=com_content&view=article&id=9&Itemid=1&article_id=13102}, doi = {10.18517/ijaseit.11.5.13102} }
EndNote
%A Widipaminto, Ayom %A Hestrio, Yohanes Fridolin %A Monica, Donna %A Safitri, Yuvita Dian %A Irawadi, Dedi %A Rokhmatuloh, - %A Triyono, Djoko %A Adiningsih, Erna Sri %D 2021 %T Utilization of Band Combination for Feature Selection in Machine Learning-Based Roof Material Types Identification %B 2021 %9 Material identification; band combination; reflectance responses. %! Utilization of Band Combination for Feature Selection in Machine Learning-Based Roof Material Types Identification %K Material identification; band combination; reflectance responses. %X Land monitoring requires remote sensing data, which varies in its spectral and spatial resolution. Remote sensing data with the high spatial resolution is especially needed for urban monitoring. However, high spatial resolution data is usually expensive with limited coverage and complex analysis. This paper aims to find the most efficient way to do urban monitoring, specifically surface material identification. In material identification, the distinctive feature that can be used to differentiate one material surface from one another is its reflectance responses. This leads to a question of which absorption features are significant to different surface materials, especially roofing materials, and which absorption features are not discriminant enough to be used at classification. This paper proposed a machine learning-based identification of roof material types using band combinations as classification features. The experiment was done on Pleiades data, multispectral satellite imagery with very high spatial resolution. We first calculated the image’s reflectance values for each band and then grouped them based on their spectral range, yielding 11 possible combinations as the classification features. The experiment found that reflectance responses for band Red and NIR are the most distinctive trait of a material type and thus sufficient for material identification. We minimized the number of spectral responses used in material identification down to two bands, which can help the data collection and processing of material identification easier, cheaper, and less time-cost. Our experiment yields overall accuracy of 0.9959, with a computational time of 19.72 seconds. %U http://ijaseit.insightsociety.org/index.php?option=com_content&view=article&id=9&Itemid=1&article_id=13102 %R doi:10.18517/ijaseit.11.5.13102 %J International Journal on Advanced Science, Engineering and Information Technology %V 11 %N 5 %@ 2088-5334
IEEE
Ayom Widipaminto,Yohanes Fridolin Hestrio,Donna Monica,Yuvita Dian Safitri,Dedi Irawadi,- Rokhmatuloh,Djoko Triyono and Erna Sri Adiningsih,"Utilization of Band Combination for Feature Selection in Machine Learning-Based Roof Material Types Identification," International Journal on Advanced Science, Engineering and Information Technology, vol. 11, no. 5, pp. 1897-1902, 2021. [Online]. Available: http://dx.doi.org/10.18517/ijaseit.11.5.13102.
RefMan/ProCite (RIS)
TY - JOUR AU - Widipaminto, Ayom AU - Hestrio, Yohanes Fridolin AU - Monica, Donna AU - Safitri, Yuvita Dian AU - Irawadi, Dedi AU - Rokhmatuloh, - AU - Triyono, Djoko AU - Adiningsih, Erna Sri PY - 2021 TI - Utilization of Band Combination for Feature Selection in Machine Learning-Based Roof Material Types Identification JF - International Journal on Advanced Science, Engineering and Information Technology; Vol. 11 (2021) No. 5 Y2 - 2021 SP - 1897 EP - 1902 SN - 2088-5334 PB - INSIGHT - Indonesian Society for Knowledge and Human Development KW - Material identification; band combination; reflectance responses. N2 - Land monitoring requires remote sensing data, which varies in its spectral and spatial resolution. Remote sensing data with the high spatial resolution is especially needed for urban monitoring. However, high spatial resolution data is usually expensive with limited coverage and complex analysis. This paper aims to find the most efficient way to do urban monitoring, specifically surface material identification. In material identification, the distinctive feature that can be used to differentiate one material surface from one another is its reflectance responses. This leads to a question of which absorption features are significant to different surface materials, especially roofing materials, and which absorption features are not discriminant enough to be used at classification. This paper proposed a machine learning-based identification of roof material types using band combinations as classification features. The experiment was done on Pleiades data, multispectral satellite imagery with very high spatial resolution. We first calculated the image’s reflectance values for each band and then grouped them based on their spectral range, yielding 11 possible combinations as the classification features. The experiment found that reflectance responses for band Red and NIR are the most distinctive trait of a material type and thus sufficient for material identification. We minimized the number of spectral responses used in material identification down to two bands, which can help the data collection and processing of material identification easier, cheaper, and less time-cost. Our experiment yields overall accuracy of 0.9959, with a computational time of 19.72 seconds. UR - http://ijaseit.insightsociety.org/index.php?option=com_content&view=article&id=9&Itemid=1&article_id=13102 DO - 10.18517/ijaseit.11.5.13102
RefWorks
RT Journal Article ID 13102 A1 Widipaminto, Ayom A1 Hestrio, Yohanes Fridolin A1 Monica, Donna A1 Safitri, Yuvita Dian A1 Irawadi, Dedi A1 Rokhmatuloh, - A1 Triyono, Djoko A1 Adiningsih, Erna Sri T1 Utilization of Band Combination for Feature Selection in Machine Learning-Based Roof Material Types Identification JF International Journal on Advanced Science, Engineering and Information Technology VO 11 IS 5 YR 2021 SP 1897 OP 1902 SN 2088-5334 PB INSIGHT - Indonesian Society for Knowledge and Human Development K1 Material identification; band combination; reflectance responses. AB Land monitoring requires remote sensing data, which varies in its spectral and spatial resolution. Remote sensing data with the high spatial resolution is especially needed for urban monitoring. However, high spatial resolution data is usually expensive with limited coverage and complex analysis. This paper aims to find the most efficient way to do urban monitoring, specifically surface material identification. In material identification, the distinctive feature that can be used to differentiate one material surface from one another is its reflectance responses. This leads to a question of which absorption features are significant to different surface materials, especially roofing materials, and which absorption features are not discriminant enough to be used at classification. This paper proposed a machine learning-based identification of roof material types using band combinations as classification features. The experiment was done on Pleiades data, multispectral satellite imagery with very high spatial resolution. We first calculated the image’s reflectance values for each band and then grouped them based on their spectral range, yielding 11 possible combinations as the classification features. The experiment found that reflectance responses for band Red and NIR are the most distinctive trait of a material type and thus sufficient for material identification. We minimized the number of spectral responses used in material identification down to two bands, which can help the data collection and processing of material identification easier, cheaper, and less time-cost. Our experiment yields overall accuracy of 0.9959, with a computational time of 19.72 seconds. LK http://ijaseit.insightsociety.org/index.php?option=com_content&view=article&id=9&Itemid=1&article_id=13102 DO - 10.18517/ijaseit.11.5.13102