Research on Multi-class Classification Based on SVM and Huffman Tree

胡俊; 滕少华; 张巍; 刘冬宁

doi:10.3969/j.issn.1007-7162.2014.02.007

English Version Journal Login

您当前的位置：

首页 >

文章列表页 >

Research on Multi-class Classification Based on SVM and Huffman Tree

更新时间：2026-05-27

- Research on Multi-class Classification Based on SVM and Huffman Tree
- Vol. 31, Issue 2, Pages: 36-42(2014)
- 作者机构：
- 作者简介：
- 基金信息：
- DOI：10.3969/j.issn.1007-7162.2014.02.007
  CLC： TP274
- Online First：06 June 2014，
  
  Published：2014
- 稿件说明：
移动端阅览
胡俊, 滕少华, 张巍, 刘冬宁. 支持向量机与哈夫曼树实现多分类的研究[J]. 广东工业大学学报, 2014, 31(2): 36-42.

胡俊, 滕少华, 张巍, et al. Research on Multi-class Classification Based on SVM and Huffman Tree[J]. 2014, 31(2): 36-42.
胡俊, 滕少华, 张巍, 刘冬宁. 支持向量机与哈夫曼树实现多分类的研究[J]. 广东工业大学学报, 2014, 31(2): 36-42. DOI： 10.3969/j.issn.1007-7162.2014.02.007.

胡俊, 滕少华, 张巍, et al. Research on Multi-class Classification Based on SVM and Huffman Tree[J]. 2014, 31(2): 36-42. DOI： 10.3969/j.issn.1007-7162.2014.02.007.

摘要

基于支持向量机和决策树的多分类方法存在错误累积问题，累积的错误往往使分类准确率下降，分类效果变差.在仔细分析了其产生错误累积原因的基础上，提出了基于哈夫曼树的支持向量机多分类方法.该方法首先将一个多分类问题分解为多个二分类问题，针对每个二分类问题使用支持向量机二分类方法解决；然后根据相异度来决策分类的优先顺序，构建基于哈夫曼树的支持向量机多分类模型；最后使用勒卡斯开源数据集进行验证，并将它与传统的支持向量机多分类方法进行实验比较.实验结果表明，新的方法在分类速度和分类精度上较传统的支持向量机多分类方法优越.

Abstract

There exists error accumulation in the multi-classification method

based on support vector machines and decision trees. It tends to decrease classification accuracy and results in a bad classification. With a careful analysis of error accumulation

it proposes a new multi-classification method

based on Huffman Tree and SVM. It divided a multi-classification problem into multiple binary classification problems

and gave classification priority

depending on the dissimilarity. At last

through an experiment with Lecast open source data sets

it verified the effectiveness. The experimental results show that the new method is superior to the traditional multi-classification method in classification speed and classification accuracy.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Extension Classification Method for Label Variability

Research on Sentiment Classification of Texts Based on SVM

Research on the Extension Transformation Strategy for Customer Retention

Efficient Temporal Modeling for RGB-T Tracking

Research on Foreign Object Detection in Power Transmission Lines Based on the AAGV-YOLOX Model

Related Author

Tian Yingjie

Liu Dalian

Li Xingsen

CHEN Pei-Wen

Fu Xiu-fen

Li Xing-sen

Zhu Zheng-xiang

Liu Yan-bin

Related Institution

Research Center on Fictitious Economy and Data Science, Chinese Academy of Sciences

Institute of Mathematics and Physics, Beijing Union University

Institute of Fundamental and Interdisciplinary Sciences, Beijing Union University

Research Institute of Extenics and Innovation Methods, Guangdong University of Technology

AI问答

⁰