| 基于一类SVM的贝叶斯分类算法 |
| |
| 引用本文： | 闭乐鹏,徐伟,宋瀚涛.基于一类SVM的贝叶斯分类算法[J].北京理工大学学报,2006,26(2):143-146. |
| |
| 作者姓名： | 闭乐鹏 徐伟 宋瀚涛 |
| |
| 作者单位： | 北京理工大学,计算机科学技术学院,北京,100081 |
| |
| 基金项目： | 国家重点基础研究发展计划(973计划) |
| |
| 摘 要： | 提出一种基于一类支持向量机(one-class SVM)的贝叶斯分类算法,该算法用一类SVM对类条件概率密度进行估计以构造贝叶斯分类器. 证明采用高斯核的一类SVM,其解可以归一化为密度函数,并把该密度函数看作类条件概率密度的平滑估计,构造贝叶斯分类器. 实际数据集上的实验结果表明,提出的分类算法测试准确率高于简单贝叶斯分类器与贝叶斯网络分类器,不低于传统二类SVM;比传统二类SVM需要计算的核矩阵规模更小,训练时间更短.
|
| 关 键 词： | 贝叶斯分类 支持向量机 概率密度估计 简单贝叶斯 分类算法 Classification Algorithm 训练时间 规模 核矩阵 计算 网络分类器 准确率 算法测试 结果 实验 数据集 平滑估计 密度函数 归一化 高斯核 构造 条件概率密度 一类支持向量机 |
| 文章编号： | 1001-0645(2006)02-0143-04 |
| 收稿时间： | 07 1 2005 12:00AM |
| 修稿时间： | 2005年7月1日 |
A Bayesian Classification Algorithm Based-on One-Class SVM |
| |
| BI Le-peng,XU Wei and SONG Han-tao.A Bayesian Classification Algorithm Based-on One-Class SVM[J].Journal of Beijing Institute of Technology(Natural Science Edition),2006,26(2):143-146. |
| |
| Authors: | BI Le-peng XU Wei and SONG Han-tao |
| |
| Institution: | Sehool of Computer Seienee and Teehnology, Beijing Institute of Teehnology, Beijing 100081, China |
| |
| Abstract: | A Bayesian classification algorithm based on one-class SVM is presented.It constructs the Bayesian classifier using the classes' conditional density estimated by one-class SVM.It is proven that the solution of one-class SVM using the Gaussian kernel can be normalized as an estimate of probability density,and can be used to obtain the Bayesian classifier.Experimental results showed that the proposed classifier outperformed NaiveBayes and BayesNet in terms of prediction accuracy,comparable to traditional two-class SVM.The size of kernel matrix of the new algorithm is less than that of the traditional two-class SVM,which lead to less training time for the new classifier. |
| |
| Keywords: | Bayesian classification support vector machine probability density estimate |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《北京理工大学学报》浏览原始摘要信息 |
| 点击此处可从《北京理工大学学报》下载免费的PDF全文 |
