混合策略超球支持向量机算法  

An Hyper-sphere Support Vector Machine with Hybrid Decision Strategy

作　　者：刘爽[1,2] 陈鹏[3] 李克秋[1] 

机构地区：[1]大连理工大学计算机科学与技术学院,辽宁大连116024 [2]大连民族学院计算机科学与工程学院,辽宁大连116605 [3]大连东软信息学院计算机科学与技术系,辽宁大连116023

出　　处：《微电子学与计算机》2014年第7期1-5,9,共6页Microelectronics & Computer

基　　金：国家自然科学基金项目(71303031)

摘　　要：针对多类别分类超球支持向量机算法的重叠区域数据分类问题,提出了一种混合策略决策算法.首先对超球相交区域的数据分布情况分析得到数据分布的特点,然后根据数据分布特点采用不同的决策策略.如果用两球相交面直接可以把两类数据分开,则直接用相交面作为分类平面.如果两类数据近似线性可分,构造最优二分超平面作为分类平面.如果两类数据非线性可分,则引入核函数构造最优二分超平面为分类球面.如果相交区域只包含一个类别的数据,则采用排它法作为测试样本的决策规则.实验结果表明所提出的算法性能优于单一决策策略的超球支持向量机算法,在提高分类精度的同时,降低了决策规则求解的复杂度.In order to solve classification problem of the intersections for multi-class classification based on hyper-sphere support vector machines ,a hybrid decision strategy is put forward in this paper .First ,characteristics of data distribution in the intersections are analyzed and then decision class is decided by different strategies .If training samples of two classes in the intersection can be classified by intersection hyper-plane for two hyper-spheres ,then new test samples can be decided by this plane . If training samples of two classes in the intersection can be approximately linearly classified ,new test samples can be classified by standard optimal binary-SVM hyper-plane .If training samples of two classes in the intersection can not be linearly classified ,new test samples can be decided by introducing kernel function to get optimal classification hyper-plane .If training examples belong to only one class , then new test samples can be classified by exclusion method . Experimental results show performance of our algorithm is more optimal than hyper-sphere support vector machines with only one decision strategy .And this algorithm improves the performance and decreases computation complexity .

关 键 词：超球支持向量机 重叠区域 混合策略 多类别分类 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]