A Multi-class Semi-Supervised Classification Algorithm Based on Evidence Theory

SHENG Kai; LIU Zhong; ZHOU De-chao; WEI Qi-hang; FENG Cheng-xu

doi:10.3969/j.issn.0372-2112.2018.11.011

您当前的位置：

首页 >

文章列表页 >

A Multi-class Semi-Supervised Classification Algorithm Based on Evidence Theory

更新时间：2025-07-16

- A Multi-class Semi-Supervised Classification Algorithm Based on Evidence Theory
- Acta Electronica Sinica Vol. 46, Issue 11, Pages: 2642-2649(2018)
- 作者机构：
  
  1. 海军工程大学兵器工程学院,湖北,武汉,430033
  2. 66029部队, 内蒙古锡林郭勒盟,011216
  3. 海军工程大学兵器工程学院,湖北,武汉,430033
  4. 66029部队内蒙古锡林郭勒盟,011216
- 作者简介：
- 基金信息：
- DOI：10.3969/j.issn.0372-2112.2018.11.011
  CLC： TP391
- Published Online：25 November 2018，
  
  Published：2018
- 稿件说明：
移动端阅览
SHENG Kai, LIU Zhong, ZHOU De-chao, et al. A Multi-class Semi-Supervised Classification Algorithm Based on Evidence Theory[J]. Acta Electronica Sinica, 2018, 46(11): 2642-2649.
DOI：

SHENG Kai, LIU Zhong, ZHOU De-chao, et al. A Multi-class Semi-Supervised Classification Algorithm Based on Evidence Theory[J]. Acta Electronica Sinica, 2018, 46(11): 2642-2649. DOI： 10.3969/j.issn.0372-2112.2018.11.011.

摘要

为了提高多类半监督分类的性能，提出了一种基于证据理论的多类协同森林算法（DSM-Co-Forest）.首先，通过多对多模式将有标记的多类数据随机拆分为多个二类数据集，并以此训练二类基分类器；然后，利用多个基分类器同时对未标记样本进行预测，并利用证据组合算法挑选出可信度较高的未标记样本；最后，将高可信度的未标记样本加入到原训练样本中，以迭代更新其他的基分类器，从而提高分类器的整体性能.通过在一些公共数据集上进行实验，并与其他半监督分类算法进行对比，验证了所提算法的可行性和有效性.

Abstract

In order to improve the performance of multi-class semi-supervised classification

a new multi-class Co-Forest algorithm named DSM-Co-Forest is proposed on the basis of D-S evidence theory. First

through MVM mode

the multi-labeled data set is randomly split into multiple binary-class data set to train the base classifiers; then

these base classifiers are used to pick out the high reliability samples from the unlabeled data set by using the evidence combination algorithm; finally

adds these selected samples to the original training set to iteratively update the base classifiers so as to improve the overall performance of the multi-class classifier. Through comparing with other semi-supervised classification algorithms on several public data sets

the feasibility and validity of the proposed algorithm are verified.

关键词

Keywords

references

Views

274

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Semi-Supervised Medical Image Segmentation Based on Suspicious Pixel Mutual Correction

An Active Semi-Supervised Short Text Classification Method Based on Federated Learning

Advances of Hyperspectral Image Classification Based on Graph Neural Networks

Semi-Supervised Feature Selection with Adaptive Graph Learning

Related Author

YANG Zi-yao

LEI Tao

DU Xiao-gang

WANG Meng-xi

SUN Fei-man

GONG Mao-guo

KONG De-yan

JI Zhen-yan

Related Institution

Key Laboratory of Collaborative Intelligent Systems, Ministry of Education, Xidian University

School of Mathematics, Southwest Jiaotong University

Shaanxi Joint Laboratory of Artificial Intelligence, Shaanxi University of Science and Technology

School of Electronic Information and Artificial Intelligence, Shaanxi University of Science and Technology

Beijing Key Laboratory of Security and Privacy in Intelligent Transportation, School of Cyberspace Science and Techonology, Beijing Jiaotong University

⁰