Hyperspectral Image Band Selection Based on CNN Embedded GA (CNNeGA)
Hyperspectral images (HSIs) are a powerful source of reliable data in various remote sensing applications. But due to the large number of bands, HSI has information redundancy, and methods are often used to reduce the number of spectral bands. Band selection (BS) is used as a preprocessing solution...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2023-01-01
|
Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/10037182/ |
_version_ | 1797894950350749696 |
---|---|
author | Mohammad Esmaeili Dariush Abbasi-Moghadam Alireza Sharifi Aqil Tariq Qingting Li |
author_facet | Mohammad Esmaeili Dariush Abbasi-Moghadam Alireza Sharifi Aqil Tariq Qingting Li |
author_sort | Mohammad Esmaeili |
collection | DOAJ |
description | Hyperspectral images (HSIs) are a powerful source of reliable data in various remote sensing applications. But due to the large number of bands, HSI has information redundancy, and methods are often used to reduce the number of spectral bands. Band selection (BS) is used as a preprocessing solution to reduce data volume, increase processing speed, and improve methodology accuracy. However, most conventional BS approaches are unable to fully explain the interaction between spectral bands and evaluate the representation and redundancy of the selected band subset. This study first examines a supervised BS method that allows the selection of the required number of bands. A deep network with 3D-convolutional layers embedded in a genetic algorithm (GA). The GA uses embedded 3D-CNN (CNNeGA) as a fitness function. GA also considers the parent check box. The parent check box (parent subbands) is designed to make genetic operators more effective. In addition, the effectiveness of increasing the attention layer to a 3D-CNN and converting this model to spike neural networks has been investigated in terms of accuracy and complexity over time. The evaluation of the proposed method and the obtained results are satisfactory. The accuracy improved from 6% to 21%. Accuracy between 90% and 99% has been obtained in each evaluation mode. |
first_indexed | 2024-04-10T07:18:42Z |
format | Article |
id | doaj.art-91c1f7495c744e67b617b4d78e9b4210 |
institution | Directory Open Access Journal |
issn | 2151-1535 |
language | English |
last_indexed | 2024-04-10T07:18:42Z |
publishDate | 2023-01-01 |
publisher | IEEE |
record_format | Article |
series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
spelling | doaj.art-91c1f7495c744e67b617b4d78e9b42102023-02-25T00:00:17ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352023-01-01161927195010.1109/JSTARS.2023.324231010037182Hyperspectral Image Band Selection Based on CNN Embedded GA (CNNeGA)Mohammad Esmaeili0Dariush Abbasi-Moghadam1https://orcid.org/0000-0003-2228-0595Alireza Sharifi2https://orcid.org/0000-0001-7110-7516Aqil Tariq3https://orcid.org/0000-0003-1196-1248Qingting Li4https://orcid.org/0000-0002-6322-8307Department of Electrical Engineering, Shahid Bahonar University of Kerman, Kerman, IranDepartment of Electrical Engineering, Shahid Bahonar University of Kerman, Kerman, IranDepartment of Surveying Engineering, Faculty of Civil Engineering, Shahid Rajaee Teacher Training University, Tehran, IranState Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan, ChinaAirborne Remote Sensing Center, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, ChinaHyperspectral images (HSIs) are a powerful source of reliable data in various remote sensing applications. But due to the large number of bands, HSI has information redundancy, and methods are often used to reduce the number of spectral bands. Band selection (BS) is used as a preprocessing solution to reduce data volume, increase processing speed, and improve methodology accuracy. However, most conventional BS approaches are unable to fully explain the interaction between spectral bands and evaluate the representation and redundancy of the selected band subset. This study first examines a supervised BS method that allows the selection of the required number of bands. A deep network with 3D-convolutional layers embedded in a genetic algorithm (GA). The GA uses embedded 3D-CNN (CNNeGA) as a fitness function. GA also considers the parent check box. The parent check box (parent subbands) is designed to make genetic operators more effective. In addition, the effectiveness of increasing the attention layer to a 3D-CNN and converting this model to spike neural networks has been investigated in terms of accuracy and complexity over time. The evaluation of the proposed method and the obtained results are satisfactory. The accuracy improved from 6% to 21%. Accuracy between 90% and 99% has been obtained in each evaluation mode.https://ieeexplore.ieee.org/document/10037182/Attention layerband selection (BS)convolution neural networks (CNNs)embedded algorithmgenetic algorithm (GA)hyperspectral image (HSI) |
spellingShingle | Mohammad Esmaeili Dariush Abbasi-Moghadam Alireza Sharifi Aqil Tariq Qingting Li Hyperspectral Image Band Selection Based on CNN Embedded GA (CNNeGA) IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Attention layer band selection (BS) convolution neural networks (CNNs) embedded algorithm genetic algorithm (GA) hyperspectral image (HSI) |
title | Hyperspectral Image Band Selection Based on CNN Embedded GA (CNNeGA) |
title_full | Hyperspectral Image Band Selection Based on CNN Embedded GA (CNNeGA) |
title_fullStr | Hyperspectral Image Band Selection Based on CNN Embedded GA (CNNeGA) |
title_full_unstemmed | Hyperspectral Image Band Selection Based on CNN Embedded GA (CNNeGA) |
title_short | Hyperspectral Image Band Selection Based on CNN Embedded GA (CNNeGA) |
title_sort | hyperspectral image band selection based on cnn embedded ga cnnega |
topic | Attention layer band selection (BS) convolution neural networks (CNNs) embedded algorithm genetic algorithm (GA) hyperspectral image (HSI) |
url | https://ieeexplore.ieee.org/document/10037182/ |
work_keys_str_mv | AT mohammadesmaeili hyperspectralimagebandselectionbasedoncnnembeddedgacnnega AT dariushabbasimoghadam hyperspectralimagebandselectionbasedoncnnembeddedgacnnega AT alirezasharifi hyperspectralimagebandselectionbasedoncnnembeddedgacnnega AT aqiltariq hyperspectralimagebandselectionbasedoncnnembeddedgacnnega AT qingtingli hyperspectralimagebandselectionbasedoncnnembeddedgacnnega |