Active Learning Algorithms for the Classification of Hyperspectral Sea Ice Images
Sea ice is one of the most critical marine disasters, especially in the polar and high latitude regions. Hyperspectral image is suitable for monitoring the sea ice, which contains continuous spectrum information and has better ability of target recognition. The principal bottleneck for the classific...
Published in: | Mathematical Problems in Engineering |
---|---|
Main Authors: | , , , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Hindawi Limited
2015
|
Subjects: | |
Online Access: | https://doi.org/10.1155/2015/124601 https://doaj.org/article/745d6bda0c8d4ab9b1dda85d63f8a21b |
id |
ftdoajarticles:oai:doaj.org/article:745d6bda0c8d4ab9b1dda85d63f8a21b |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:745d6bda0c8d4ab9b1dda85d63f8a21b 2023-05-15T15:35:04+02:00 Active Learning Algorithms for the Classification of Hyperspectral Sea Ice Images Yanling Han Jing Ren Zhonghua Hong Yun Zhang Long Zhang Wanting Meng Qiming Gu 2015-01-01T00:00:00Z https://doi.org/10.1155/2015/124601 https://doaj.org/article/745d6bda0c8d4ab9b1dda85d63f8a21b EN eng Hindawi Limited http://dx.doi.org/10.1155/2015/124601 https://doaj.org/toc/1024-123X https://doaj.org/toc/1563-5147 1024-123X 1563-5147 doi:10.1155/2015/124601 https://doaj.org/article/745d6bda0c8d4ab9b1dda85d63f8a21b Mathematical Problems in Engineering, Vol 2015 (2015) Engineering (General). Civil engineering (General) TA1-2040 Mathematics QA1-939 article 2015 ftdoajarticles https://doi.org/10.1155/2015/124601 2022-12-31T02:15:26Z Sea ice is one of the most critical marine disasters, especially in the polar and high latitude regions. Hyperspectral image is suitable for monitoring the sea ice, which contains continuous spectrum information and has better ability of target recognition. The principal bottleneck for the classification of hyperspectral image is a large number of labeled training samples required. However, the collection of labeled samples is time consuming and costly. In order to solve this problem, we apply the active learning (AL) algorithm to hyperspectral sea ice detection which can select the most informative samples. Moreover, we propose a novel investigated AL algorithm based on the evaluation of two criteria: uncertainty and diversity. The uncertainty criterion is based on the difference between the probabilities of the two classes having the highest estimated probabilities, while the diversity criterion is based on a kernel k-means clustering technology. In the experiments of Baffin Bay in northwest Greenland on April 12, 2014, our proposed AL algorithm achieves the highest classification accuracy of 89.327% compared with other AL algorithms and random sampling, while achieving the same classification accuracy, the proposed AL algorithm needs less labeling cost. Article in Journal/Newspaper Baffin Bay Baffin Bay Baffin Greenland Sea ice Directory of Open Access Journals: DOAJ Articles Baffin Bay Greenland Mathematical Problems in Engineering 2015 1 10 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
Engineering (General). Civil engineering (General) TA1-2040 Mathematics QA1-939 |
spellingShingle |
Engineering (General). Civil engineering (General) TA1-2040 Mathematics QA1-939 Yanling Han Jing Ren Zhonghua Hong Yun Zhang Long Zhang Wanting Meng Qiming Gu Active Learning Algorithms for the Classification of Hyperspectral Sea Ice Images |
topic_facet |
Engineering (General). Civil engineering (General) TA1-2040 Mathematics QA1-939 |
description |
Sea ice is one of the most critical marine disasters, especially in the polar and high latitude regions. Hyperspectral image is suitable for monitoring the sea ice, which contains continuous spectrum information and has better ability of target recognition. The principal bottleneck for the classification of hyperspectral image is a large number of labeled training samples required. However, the collection of labeled samples is time consuming and costly. In order to solve this problem, we apply the active learning (AL) algorithm to hyperspectral sea ice detection which can select the most informative samples. Moreover, we propose a novel investigated AL algorithm based on the evaluation of two criteria: uncertainty and diversity. The uncertainty criterion is based on the difference between the probabilities of the two classes having the highest estimated probabilities, while the diversity criterion is based on a kernel k-means clustering technology. In the experiments of Baffin Bay in northwest Greenland on April 12, 2014, our proposed AL algorithm achieves the highest classification accuracy of 89.327% compared with other AL algorithms and random sampling, while achieving the same classification accuracy, the proposed AL algorithm needs less labeling cost. |
format |
Article in Journal/Newspaper |
author |
Yanling Han Jing Ren Zhonghua Hong Yun Zhang Long Zhang Wanting Meng Qiming Gu |
author_facet |
Yanling Han Jing Ren Zhonghua Hong Yun Zhang Long Zhang Wanting Meng Qiming Gu |
author_sort |
Yanling Han |
title |
Active Learning Algorithms for the Classification of Hyperspectral Sea Ice Images |
title_short |
Active Learning Algorithms for the Classification of Hyperspectral Sea Ice Images |
title_full |
Active Learning Algorithms for the Classification of Hyperspectral Sea Ice Images |
title_fullStr |
Active Learning Algorithms for the Classification of Hyperspectral Sea Ice Images |
title_full_unstemmed |
Active Learning Algorithms for the Classification of Hyperspectral Sea Ice Images |
title_sort |
active learning algorithms for the classification of hyperspectral sea ice images |
publisher |
Hindawi Limited |
publishDate |
2015 |
url |
https://doi.org/10.1155/2015/124601 https://doaj.org/article/745d6bda0c8d4ab9b1dda85d63f8a21b |
geographic |
Baffin Bay Greenland |
geographic_facet |
Baffin Bay Greenland |
genre |
Baffin Bay Baffin Bay Baffin Greenland Sea ice |
genre_facet |
Baffin Bay Baffin Bay Baffin Greenland Sea ice |
op_source |
Mathematical Problems in Engineering, Vol 2015 (2015) |
op_relation |
http://dx.doi.org/10.1155/2015/124601 https://doaj.org/toc/1024-123X https://doaj.org/toc/1563-5147 1024-123X 1563-5147 doi:10.1155/2015/124601 https://doaj.org/article/745d6bda0c8d4ab9b1dda85d63f8a21b |
op_doi |
https://doi.org/10.1155/2015/124601 |
container_title |
Mathematical Problems in Engineering |
container_volume |
2015 |
container_start_page |
1 |
op_container_end_page |
10 |
_version_ |
1766365371770601472 |