Improvement on Least Squares Twin Support Vector Machine for Pattern Classification

CHU Mao-xiang; WANG An-na; GONG Rong-fen

doi:10.3969/j.issn.0372-2112.2014.05.026

您当前的位置：

首页 >

文章列表页 >

Improvement on Least Squares Twin Support Vector Machine for Pattern Classification

更新时间：2025-07-16

- Improvement on Least Squares Twin Support Vector Machine for Pattern Classification
- Acta Electronica Sinica Vol. 42, Issue 5, Pages: 998-1003(2014)
- 作者机构：
  
  1. 东北大学信息科学与工程学院,辽宁,沈阳,110819
  2. 辽宁科技大学电子与信息工程学院,辽宁,鞍山,114051
  3. 东北大学信息科学与工程学院,辽宁,沈阳,110819
  4. 辽宁科技大学电子与信息工程学院,辽宁,鞍山,114051
- 作者简介：
- 基金信息：
  
  National Natural Science Foundation of China (No.61050006)
- DOI：10.3969/j.issn.0372-2112.2014.05.026
  CLC： TP18
- Published：2014
- 稿件说明：
移动端阅览
CHU Mao-xiang, WANG An-na, GONG Rong-fen. Improvement on Least Squares Twin Support Vector Machine for Pattern Classification[J]. Acta Electronica Sinica, 2014, 42(5): 998-1003.
DOI：

CHU Mao-xiang, WANG An-na, GONG Rong-fen. Improvement on Least Squares Twin Support Vector Machine for Pattern Classification[J]. Acta Electronica Sinica, 2014, 42(5): 998-1003. DOI： 10.3969/j.issn.0372-2112.2014.05.026.

摘要

提出了一种新的模式分类器，即广泛权重的最小二乘孪生支持向量机.该支持向量机在正、负两类样本上广泛地增加权重，很好地抑制了交叉噪声样本对数据分类的影响.其次，根据间隔最大化原理，该支持向量机在目标函数上增加了一个正规化项，实现结构风险最小化和避免在求解该目标函数时可能对病态矩阵求逆的处理.同时，提出了利用一种指数函数计算训练样本的密度来获得样本权重值的算法.该算法能够有效缩减计算权重的时间，且具有较强的鲁棒性.实验证明本文提出的广泛权重的最小二乘孪生支持向量机能够实现高精度和高效率的分类效果，而且特别适合于含有交叉噪声样本的数据集分类.

Abstract

Widely weighted least squares twin support vector machine (WWLSTSVM) is proposed for pattern classification.In WWLSTSVM

weights are widely added on error variables of data samples both in one class and the other.This widely weighted method is especially effective on eliminating the interference of intercrossing noise samples.Moreover

a regularization term is added with the theory of maximizing margin

in which the structural risk is minimized and the possible ill-conditioning is avoided for matrix inversion.Also

an effective weight algorithm with exponential function is proposed to reduce the time complexity of computing weight values and enhance its robustness for cross plane dataset.Comparative experiments show that WWLSTSVM obtains better results on eliminating the interference of noise samples and higher classification accuracy with less computing time in both linear and nonlinear cases compared with the other classifiers.

关键词

Keywords

references

Views

2293

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Hardware Implementation of Orthogonal Matching Pursuit Algorithm for Weighted QR Decomposition

Multi‑Fractal Detrended Fluctuation Analysis Method for Non‑Stationary Time Series Based on EMD‑LS

A Two-Norm Annular Margin Classifier

Multiscale Image Information from Multisensor Fusion Algorithm

Applications of Rough Approximate Operators in the Possibility and Necessity of Pattern Classification

Related Author

LI Miao

YU Bai-shan

ZHANG Lei

MOU Xiao-shuang

LIU Ting

ZHANG Hong-sheng

YANG Hong

LIANG Wen-kai

Related Institution

School of Optoelectronic Engineering， Chongqing University of Posts and Telecommunications

Jiangxi Province Key Laboratory of Precision Drive and Control, Institute of Technology

School of Mechanical and Electrical Engineering, Nanchang Institute of Technology

Institute of Graphic and ImageHangzhou Dianzi UniversityHangzhouZhejiang 310018China

School of Computer Science and TechnologyZhejiang University of TechnologyHangzhouZhejiang 310023China

⁰