Cross-Scene Hyperspectral Feature Selection via Hybrid Whale Optimization Algorithm With Simulated Annealing
Hyperspectral images (HSIs) include hundreds of spectral bands, which lead to Hughes phenomenon in classification task and decrease the classification accuracy. Feature selection can remove redundant and noisy features in the HSIs to overcome this phenomenon. In real applications, we may face a HSI...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9345344/ |
| _version_ | 1818739067501674496 |
|---|---|
| author | Jianxi Wang Minchao Ye Fengchao Xiong Yuntao Qian |
| author_facet | Jianxi Wang Minchao Ye Fengchao Xiong Yuntao Qian |
| author_sort | Jianxi Wang |
| collection | DOAJ |
| description | Hyperspectral images (HSIs) include hundreds of spectral bands, which lead to Hughes phenomenon in classification task and decrease the classification accuracy. Feature selection can remove redundant and noisy features in the HSIs to overcome this phenomenon. In real applications, we may face a HSI scene with only a few labeled samples. Meanwhile, there are adequate labeled samples in a similar HSI scene. For example, they share the same land-cover classes. The shared information can be used to help the scene with a few labeled samples in feature selection. Traditional single-scene-based feature selection appears powerless in solving such problems. Cross-scene feature selection provides an attractive way to select feature subsets by simultaneously using the information from two HSI scenes. However, spectral distribution may change due to atmospheric conditions, yielding spectral shift. In order to tackle this problem, we propose a cross-domain algorithm based on hybrid whale optimization algorithm with simulated annealing (WOASA). The newly proposed algorithm is dubbed cross-domain WOASA (CDWOASA). CDWOASA simultaneously considers the separability of different land-cover classes and the consistency of selected features between two scenes, leading to discriminative and domain-invariant characters of selected feature subset. Moreover, since the original WOASA is not able to precisely control the dimension of selected features, we propose an improvement using a sorting strategy based on the fitness function value, thus making the output feature dimension precisely controlled. The experimental results on two cross-scene HSI datasets demonstrate the superiority of CDWOASA in cross-scene feature selection. |
| first_indexed | 2024-12-18T01:18:56Z |
| format | Article |
| id | doaj.art-0b3dc7860f794a77a6acae15c0610932 |
| institution | Directory Open Access Journal |
| issn | 2151-1535 |
| language | English |
| last_indexed | 2024-12-18T01:18:56Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj.art-0b3dc7860f794a77a6acae15c06109322022-12-21T21:25:52ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352021-01-01142473248310.1109/JSTARS.2021.30565939345344Cross-Scene Hyperspectral Feature Selection via Hybrid Whale Optimization Algorithm With Simulated AnnealingJianxi Wang0Minchao Ye1https://orcid.org/0000-0003-3608-7913Fengchao Xiong2https://orcid.org/0000-0002-9753-4919Yuntao Qian3https://orcid.org/0000-0002-7418-5891Key Laboratory of Electromagnetic Wave Information Technology and Metrology of Zhejiang Province, College of Information Engineering, China Jiliang University, Hangzhou, ChinaKey Laboratory of Electromagnetic Wave Information Technology and Metrology of Zhejiang Province, College of Information Engineering, China Jiliang University, Hangzhou, ChinaSchool of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, ChinaCollege of Computer Science, Zhejiang University, Hangzhou, ChinaHyperspectral images (HSIs) include hundreds of spectral bands, which lead to Hughes phenomenon in classification task and decrease the classification accuracy. Feature selection can remove redundant and noisy features in the HSIs to overcome this phenomenon. In real applications, we may face a HSI scene with only a few labeled samples. Meanwhile, there are adequate labeled samples in a similar HSI scene. For example, they share the same land-cover classes. The shared information can be used to help the scene with a few labeled samples in feature selection. Traditional single-scene-based feature selection appears powerless in solving such problems. Cross-scene feature selection provides an attractive way to select feature subsets by simultaneously using the information from two HSI scenes. However, spectral distribution may change due to atmospheric conditions, yielding spectral shift. In order to tackle this problem, we propose a cross-domain algorithm based on hybrid whale optimization algorithm with simulated annealing (WOASA). The newly proposed algorithm is dubbed cross-domain WOASA (CDWOASA). CDWOASA simultaneously considers the separability of different land-cover classes and the consistency of selected features between two scenes, leading to discriminative and domain-invariant characters of selected feature subset. Moreover, since the original WOASA is not able to precisely control the dimension of selected features, we propose an improvement using a sorting strategy based on the fitness function value, thus making the output feature dimension precisely controlled. The experimental results on two cross-scene HSI datasets demonstrate the superiority of CDWOASA in cross-scene feature selection.https://ieeexplore.ieee.org/document/9345344/Cross-domain WOASAcross-scene feature selectionhyperspectral images |
| spellingShingle | Jianxi Wang Minchao Ye Fengchao Xiong Yuntao Qian Cross-Scene Hyperspectral Feature Selection via Hybrid Whale Optimization Algorithm With Simulated Annealing IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Cross-domain WOASA cross-scene feature selection hyperspectral images |
| title | Cross-Scene Hyperspectral Feature Selection via Hybrid Whale Optimization Algorithm With Simulated Annealing |
| title_full | Cross-Scene Hyperspectral Feature Selection via Hybrid Whale Optimization Algorithm With Simulated Annealing |
| title_fullStr | Cross-Scene Hyperspectral Feature Selection via Hybrid Whale Optimization Algorithm With Simulated Annealing |
| title_full_unstemmed | Cross-Scene Hyperspectral Feature Selection via Hybrid Whale Optimization Algorithm With Simulated Annealing |
| title_short | Cross-Scene Hyperspectral Feature Selection via Hybrid Whale Optimization Algorithm With Simulated Annealing |
| title_sort | cross scene hyperspectral feature selection via hybrid whale optimization algorithm with simulated annealing |
| topic | Cross-domain WOASA cross-scene feature selection hyperspectral images |
| url | https://ieeexplore.ieee.org/document/9345344/ |
| work_keys_str_mv | AT jianxiwang crossscenehyperspectralfeatureselectionviahybridwhaleoptimizationalgorithmwithsimulatedannealing AT minchaoye crossscenehyperspectralfeatureselectionviahybridwhaleoptimizationalgorithmwithsimulatedannealing AT fengchaoxiong crossscenehyperspectralfeatureselectionviahybridwhaleoptimizationalgorithmwithsimulatedannealing AT yuntaoqian crossscenehyperspectralfeatureselectionviahybridwhaleoptimizationalgorithmwithsimulatedannealing |