稀疏链式多标记分类器
DOI:
作者:
作者单位:

作者简介:

通讯作者:

基金项目:


arse Classifier Chains for MultiLabel Classification.
Author:
Affiliation:

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
    摘要:

    高阶多标记学习算法能够挖掘所有类别标记之间的关系或标记子集的关系,但在处理错误传播和冗余或错误的类别依赖关系这两个问题上存在弊端。针对此类问题,在链式分类器的基础上,提出稀疏链式多标记学习算法(Sparse Classifier Chains,SCC);为了验证所提出算法的有效性,将其与5种多标记学习算法进行对比,选取8个评价指标来评估算法的性能,在12个标准数据集上进行了实验验证,并利用秩和检验方法来分析所有对比算法之间的相对性能;实验结果表明:稀疏链式多标记学习算法优于所有对比算法,显著优于部分算法,并具有较强的泛化性能。

    Abstract:

    Higherorder multilabel learning algorithm can mine the relationships or subsets of all class labels, however, it has some drawbacks in dealing with the problems of error propagation and redundant or erroneous class dependencies. For such problems, a new multilabel classifier SCC, i.e., Sparse Classifier Chains, was proposed based on classier chains by introducing sparse learning. In order to verify the effectiveness of the proposed algorithm, we compared this with other 5 kinds of multilabel learning algorithms and selected 8 evaluation indexes to evaluate the performance of them. The experimental verification which was carried out on 12 standard data set lastly analyzed by using the rank sum test method to compare the relative performance . The experimental results showed that SCC was superior to all the contrast algorithms, significantly superior to some algorithms; furthermore, it had a strong generalization performance.

    参考文献
    相似文献
    引证文献
引用本文

王灿, 黄俊, 秦锋.稀疏链式多标记分类器[J].重庆工商大学学报(自然科学版),2018,35(5):7-16
WANG Can, HUANG Jun, QIN Feng. arse Classifier Chains for MultiLabel Classification.[J]. Journal of Chongqing Technology and Business University(Natural Science Edition),2018,35(5):7-16

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
历史
  • 收稿日期:
  • 最后修改日期:
  • 录用日期:
  • 在线发布日期: 2018-09-19
×
2023年《重庆工商大学学报(自然科学版)》影响因子稳步提升