基于复合核支持向量回归机的多类分类算法
第15卷 第6期太赫兹科学与电子信息学报Vo1.15，No.6 2017年12月 Journal of Terahertz Science and Electronic Information Technology Dec.，2017 文章编号：2095-4980(2017)06-1039-06
基于复合核支持向量回归机的多类分类算法
陈 垚a，宋召青b
(海军航空工程学院 a.控制科学与工程系；b.七系，山东烟台 264001)
摘 要：针对传统支持向量机(SVM)在解决多类分类问题时需要训练多个分类器、存在不可分区域等问题，研究了基于支持向量回归机的多类分类算法。利用回归思想求解多类分类问题，
将分类样本作为回归输入，样本的类别标识作为回归输出，通过支持向量回归机训练拟合出各样
本与其类别标识之间的函数关系。将待分类样本代入回归函数，对其输出取整后即可得到样本类
别。该算法仅使用1个分类器，明显简化了分类过程。另外，引入复合核函数来提高支持向量回
归机的性能。采用加州大学欧文分校(UCI)例题库中的多类分类问题进行仿真验证，并将改进算法
与传统算法作对比，结果表明改进算法在分类速度和准确率上都有显著提高。
关键词：支持向量机；多类分类；支持向量回归机；复合核函数
中图分类号：TN850.6；TP181文献标志码：A doi：10.11805/TKYDA201706.1039
Multi-class classification method based on support vector regression machine
with composite kernel function
CHEN Yao a，SONG Zhaoqing b
(a.Department of Control Science and Engineering；
b.The 7th Department，Naval Aeronautical and Astronautical University，Yantai Shandong 264001，China)
Abstract：Aiming at the problem that there is inseparable region and more than one traditional Support Vector Machine(SVM) classifiers need to be trained in the multi-class classification problem, the
support vector regression machine based multi-class classification method is researched. This method
utilizes regression theory to solve multi-class classification problems, in which the classification samples
are served as regression input, and their class labels are served as regression output, then the relationship
between samples and their class labels are fitted by support vector regression machine method. The
samples are classified into the regression function, and the class labels are obtained by adding a rounding
operation to the regression output. This method uses only one classifier, which significantly simplifies the
classification process. In addition, the composite kernel function is introduced to improve the performance
of the support vector regression machine. The datasets of multi-class classification problems selected from
University of California Irvine(UCI) database are used for simulation. Compared with traditional multi-
class support vector machine, both classification speed and accuracy of the proposed method have been
significantly improved.
Keywords：Support Vector Machine；multi-class classification；support vector regression machine；
composite kernel function
支持向量机(SVM)是近年来诞生的一种机器学习算法，由Vapnik等[1]提出。该算法以统计学习理论为基础，主要在小样本、高维数和非线性等实际中经常遇到的问题上有很好的表现，相比神经网络等其他机器学习方法，避免了局部最优解、过学习及“维数灾难”等问题，受到了广泛的关注，产生了许多研究成果。SVM设计用来解决两类分类问题，但实际中面对的一般为多类分类问题(如人脸识别、语音识别、故障诊断等)，需要将SVM算法进行推广。目前的多类分类SVM算法主要有两大类，第一类是将多类分类拆分为一系列的两类分
收稿日期：2016-05-16；修回日期：2016-06-28
基金项目：国家自然科学基金重点资助项目(61433011)
万方数据