A novel semisupervised support vector machine classifier based on active learning and context information

Fei Gao, Wenchao Lv, Yaotian Zhang, Jinping Sun, Jun Wang, Erfu Yang

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

This paper proposes a novel semisupervised support vector machine classifier (Formula presented.) based on active learning (AL) and context information to solve the problem where the number of labeled samples is insufficient. Firstly, a new semisupervised learning method is designed using AL to select unlabeled samples as the semilabled samples, then the context information is exploited to further expand the selected samples and relabel them, along with the labeled samples train (Formula presented.) classifier. Next, a new query function is designed to enhance the reliability of the classification results by using the Euclidean distance between the samples. Finally, in order to enhance the robustness of the proposed algorithm, a fusion method is designed. Several experiments on change detection are performed by considering some real remote sensing images. The results show that the proposed algorithm in comparison with other algorithms can significantly improve the detection accuracy and achieve a fast convergence in addition to verify the effectiveness of the fusion method developed in this paper.

LanguageEnglish
Number of pages20
JournalMultidimensional Systems and Signal Processing
Early online date2 Apr 2016
DOIs
Publication statusE-pub ahead of print - 2 Apr 2016

Fingerprint

Active Learning
Support vector machines
Support Vector Machine
Classifiers
Classifier
Fusion reactions
Remote sensing
Fusion
Semi-supervised Learning
Change Detection
Remote Sensing Image
Euclidean Distance
Expand
Context
Problem-Based Learning
Experiments
Query
Verify
Robustness
Experiment

Keywords

  • active learning
  • context information
  • remote sensing
  • semisupervised support vector machine

Cite this

@article{0bd9e476ca034c9e8801f465f84458f1,
title = "A novel semisupervised support vector machine classifier based on active learning and context information",
abstract = "This paper proposes a novel semisupervised support vector machine classifier (Formula presented.) based on active learning (AL) and context information to solve the problem where the number of labeled samples is insufficient. Firstly, a new semisupervised learning method is designed using AL to select unlabeled samples as the semilabled samples, then the context information is exploited to further expand the selected samples and relabel them, along with the labeled samples train (Formula presented.) classifier. Next, a new query function is designed to enhance the reliability of the classification results by using the Euclidean distance between the samples. Finally, in order to enhance the robustness of the proposed algorithm, a fusion method is designed. Several experiments on change detection are performed by considering some real remote sensing images. The results show that the proposed algorithm in comparison with other algorithms can significantly improve the detection accuracy and achieve a fast convergence in addition to verify the effectiveness of the fusion method developed in this paper.",
keywords = "active learning, context information, remote sensing, semisupervised support vector machine",
author = "Fei Gao and Wenchao Lv and Yaotian Zhang and Jinping Sun and Jun Wang and Erfu Yang",
note = "The final publication is available at Springer via http://dx.doi.org/10.1007/s11045-016-0396-1",
year = "2016",
month = "4",
day = "2",
doi = "10.1007/s11045-016-0396-1",
language = "English",
journal = "Multidimensional Systems and Signal Processing",
issn = "0923-6082",

}

A novel semisupervised support vector machine classifier based on active learning and context information. / Gao, Fei; Lv, Wenchao; Zhang, Yaotian; Sun, Jinping; Wang, Jun; Yang, Erfu.

In: Multidimensional Systems and Signal Processing, 02.04.2016.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A novel semisupervised support vector machine classifier based on active learning and context information

AU - Gao, Fei

AU - Lv, Wenchao

AU - Zhang, Yaotian

AU - Sun, Jinping

AU - Wang, Jun

AU - Yang, Erfu

N1 - The final publication is available at Springer via http://dx.doi.org/10.1007/s11045-016-0396-1

PY - 2016/4/2

Y1 - 2016/4/2

N2 - This paper proposes a novel semisupervised support vector machine classifier (Formula presented.) based on active learning (AL) and context information to solve the problem where the number of labeled samples is insufficient. Firstly, a new semisupervised learning method is designed using AL to select unlabeled samples as the semilabled samples, then the context information is exploited to further expand the selected samples and relabel them, along with the labeled samples train (Formula presented.) classifier. Next, a new query function is designed to enhance the reliability of the classification results by using the Euclidean distance between the samples. Finally, in order to enhance the robustness of the proposed algorithm, a fusion method is designed. Several experiments on change detection are performed by considering some real remote sensing images. The results show that the proposed algorithm in comparison with other algorithms can significantly improve the detection accuracy and achieve a fast convergence in addition to verify the effectiveness of the fusion method developed in this paper.

AB - This paper proposes a novel semisupervised support vector machine classifier (Formula presented.) based on active learning (AL) and context information to solve the problem where the number of labeled samples is insufficient. Firstly, a new semisupervised learning method is designed using AL to select unlabeled samples as the semilabled samples, then the context information is exploited to further expand the selected samples and relabel them, along with the labeled samples train (Formula presented.) classifier. Next, a new query function is designed to enhance the reliability of the classification results by using the Euclidean distance between the samples. Finally, in order to enhance the robustness of the proposed algorithm, a fusion method is designed. Several experiments on change detection are performed by considering some real remote sensing images. The results show that the proposed algorithm in comparison with other algorithms can significantly improve the detection accuracy and achieve a fast convergence in addition to verify the effectiveness of the fusion method developed in this paper.

KW - active learning

KW - context information

KW - remote sensing

KW - semisupervised support vector machine

UR - http://www.scopus.com/inward/record.url?scp=84962144487&partnerID=8YFLogxK

UR - http://link.springer.com/article/10.1007%2Fs11045-016-0396-1

U2 - 10.1007/s11045-016-0396-1

DO - 10.1007/s11045-016-0396-1

M3 - Article

JO - Multidimensional Systems and Signal Processing

T2 - Multidimensional Systems and Signal Processing

JF - Multidimensional Systems and Signal Processing

SN - 0923-6082

ER -