计算机与现代化

• 人工智能 • 上一篇    下一篇

一种基于成对标签的Rakel算法改进

  

  1. (浙江师范大学数理与信息工程学院,浙江 金华 321004)
  • 收稿日期:2015-10-20 出版日期:2016-03-17 发布日期:2016-03-17
  • 作者简介:周恩波(1990-),男,浙江宁波人,浙江师范大学数理与信息工程学院硕士研究生,研究方向:机器学习,人工智能; 通信作者:叶荣华(1971-),男,浙江绍兴人,教授,博士,研究方向:语义Web服务,Agent技术; 张微微(1990-),女,安徽安庆人,硕士研究生,研究方向:人工智能,机器学习。
  • 基金资助:
    浙江省自然科学基金资助项目(y1100169)

An Improved Rakel Approach Based on Label Pairwise

  1. (College of Mathematics, Physics and Information Engineering, Zhejiang Normal University, Jinhua 321004, China)
  • Received:2015-10-20 Online:2016-03-17 Published:2016-03-17

摘要: Rakel(Random k-labelsets)算法从原始标签集中随机选择一部分标签子集,并且使用LP(Label Powerset)算法训练相应的多标签子分类器。由于随机选择标签的原因导致LP子分类器预测性能不好。本文基于标签的共现关系选择成对标签来训练LP分类器,提出PwRakel(Pairwise Random k-labelsets)算法。该算法通过挖掘标签相关性扩展训练集,有效提高分类性能。实验结果表明,所提出的算法与Rakel算法以及其他算法对比,分类准确度更高。

关键词: 多标签分类, 标签相关性, PwRakel

Abstract: Rakel (Random k-labelsets) randomly selects a number of label subsets from the original set of labels and uses the LP (Label Powerset) method to train the corresponding multi-label classifiers. But the models maybe have a poor performance because of randomization nature. Thus in this paper we firstly capture some pairwise relationships based on label co-occurrence between the labels to training LP classifier by PwRakel (Pairwise Random k-labelsets) algorithm. The method extends the training set by exploiting label correlations to improve classification performance effectively. The experimental results indicate that the proposed method improves multi-label classification accuracy compared with the Rakel algorithm and to other state-of-the-art algorithms.

Key words: multilabel classification, label correlation, PwRakel

中图分类号: