A Novel Semi-Supervised Learning Method Based on Fast Search and Density Peaks
Radar image recognition is a hotspot in the field of remote sensing. Under the condition of sufficiently labeled samples, recognition algorithms can achieve good classification results. However, labeled samples are scarce and costly to obtain. Our major interest in this paper is how to use these unl...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2019-01-01
|
| Series: | Complexity |
| Online Access: | http://dx.doi.org/10.1155/2019/6876173 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832554266923892736 |
|---|---|
| author | Fei Gao Teng Huang Jinping Sun Amir Hussain Erfu Yang Huiyu Zhou |
| author_facet | Fei Gao Teng Huang Jinping Sun Amir Hussain Erfu Yang Huiyu Zhou |
| author_sort | Fei Gao |
| collection | DOAJ |
| description | Radar image recognition is a hotspot in the field of remote sensing. Under the condition of sufficiently labeled samples, recognition algorithms can achieve good classification results. However, labeled samples are scarce and costly to obtain. Our major interest in this paper is how to use these unlabeled samples to improve the performance of a recognition algorithm in the case of limited labeled samples. This is a semi-supervised learning problem. However, unlike the existing semi-supervised learning methods, we do not use unlabeled samples directly and, instead, look for safe and reliable unlabeled samples before using them. In this paper, two new semi-supervised learning methods are proposed: a semi-supervised learning method based on fast search and density peaks (S2DP) and an iterative S2DP method (IS2DP). When the labeled samples satisfy a certain requirement, S2DP uses fast search and a density peak clustering method to detect reliable unlabeled samples based on the weighted kernel Fisher discriminant analysis (WKFDA). Then, a labeling method based on clustering information (LCI) is designed to label the unlabeled samples. When the labeled samples are insufficient, IS2DP is used to iteratively search for reliable unlabeled samples for semi-supervision. Then, these samples are added to the labeled samples to improve the recognition performance of S2DP. In the experiments, real radar images are used to verify the performance of our proposed algorithm in dealing with the scarcity of the labeled samples. In addition, our algorithm is compared against several semi-supervised deep learning methods with similar structures. Experimental results demonstrate that the proposed algorithm has better stability than these methods. |
| format | Article |
| id | doaj-art-08b66b93c13648678158862938f5de26 |
| institution | Kabale University |
| issn | 1076-2787 1099-0526 |
| language | English |
| publishDate | 2019-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Complexity |
| spelling | doaj-art-08b66b93c13648678158862938f5de262025-02-03T05:51:50ZengWileyComplexity1076-27871099-05262019-01-01201910.1155/2019/68761736876173A Novel Semi-Supervised Learning Method Based on Fast Search and Density PeaksFei Gao0Teng Huang1Jinping Sun2Amir Hussain3Erfu Yang4Huiyu Zhou5School of Electronic and Information Engineering, Beihang University, Beijing 101191, ChinaSchool of Electronic and Information Engineering, Beihang University, Beijing 101191, ChinaSchool of Electronic and Information Engineering, Beihang University, Beijing 101191, ChinaCognitive Big Data and Cyber-Informatics (CogBID) Laboratory, School of Computing, Edinburgh Napier University, Edinburgh EH10 5DT, Scotland, UKDepartment of Design, Manufacture and Engineering Management, University of Strathclyde, Glasgow G1 1XJ, UKDepartment of Informatics, University of Leicester, Leicester LE1 7RH, UKRadar image recognition is a hotspot in the field of remote sensing. Under the condition of sufficiently labeled samples, recognition algorithms can achieve good classification results. However, labeled samples are scarce and costly to obtain. Our major interest in this paper is how to use these unlabeled samples to improve the performance of a recognition algorithm in the case of limited labeled samples. This is a semi-supervised learning problem. However, unlike the existing semi-supervised learning methods, we do not use unlabeled samples directly and, instead, look for safe and reliable unlabeled samples before using them. In this paper, two new semi-supervised learning methods are proposed: a semi-supervised learning method based on fast search and density peaks (S2DP) and an iterative S2DP method (IS2DP). When the labeled samples satisfy a certain requirement, S2DP uses fast search and a density peak clustering method to detect reliable unlabeled samples based on the weighted kernel Fisher discriminant analysis (WKFDA). Then, a labeling method based on clustering information (LCI) is designed to label the unlabeled samples. When the labeled samples are insufficient, IS2DP is used to iteratively search for reliable unlabeled samples for semi-supervision. Then, these samples are added to the labeled samples to improve the recognition performance of S2DP. In the experiments, real radar images are used to verify the performance of our proposed algorithm in dealing with the scarcity of the labeled samples. In addition, our algorithm is compared against several semi-supervised deep learning methods with similar structures. Experimental results demonstrate that the proposed algorithm has better stability than these methods.http://dx.doi.org/10.1155/2019/6876173 |
| spellingShingle | Fei Gao Teng Huang Jinping Sun Amir Hussain Erfu Yang Huiyu Zhou A Novel Semi-Supervised Learning Method Based on Fast Search and Density Peaks Complexity |
| title | A Novel Semi-Supervised Learning Method Based on Fast Search and Density Peaks |
| title_full | A Novel Semi-Supervised Learning Method Based on Fast Search and Density Peaks |
| title_fullStr | A Novel Semi-Supervised Learning Method Based on Fast Search and Density Peaks |
| title_full_unstemmed | A Novel Semi-Supervised Learning Method Based on Fast Search and Density Peaks |
| title_short | A Novel Semi-Supervised Learning Method Based on Fast Search and Density Peaks |
| title_sort | novel semi supervised learning method based on fast search and density peaks |
| url | http://dx.doi.org/10.1155/2019/6876173 |
| work_keys_str_mv | AT feigao anovelsemisupervisedlearningmethodbasedonfastsearchanddensitypeaks AT tenghuang anovelsemisupervisedlearningmethodbasedonfastsearchanddensitypeaks AT jinpingsun anovelsemisupervisedlearningmethodbasedonfastsearchanddensitypeaks AT amirhussain anovelsemisupervisedlearningmethodbasedonfastsearchanddensitypeaks AT erfuyang anovelsemisupervisedlearningmethodbasedonfastsearchanddensitypeaks AT huiyuzhou anovelsemisupervisedlearningmethodbasedonfastsearchanddensitypeaks AT feigao novelsemisupervisedlearningmethodbasedonfastsearchanddensitypeaks AT tenghuang novelsemisupervisedlearningmethodbasedonfastsearchanddensitypeaks AT jinpingsun novelsemisupervisedlearningmethodbasedonfastsearchanddensitypeaks AT amirhussain novelsemisupervisedlearningmethodbasedonfastsearchanddensitypeaks AT erfuyang novelsemisupervisedlearningmethodbasedonfastsearchanddensitypeaks AT huiyuzhou novelsemisupervisedlearningmethodbasedonfastsearchanddensitypeaks |