欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
球形支持向量机是一种学习算法,它通过在高维特征空间中,对每一个模式类别构造一个覆盖其所有训练样本的具有最小体积的超球体,来实现对训练样本空间的划分。在此基础上,提出了一种基于新的决策规则的球形支持向量机算法,并在七个UCI数据集上进行了实验,实验结果表明提出的算法可以取得比标准的支持向量机算法更好的分类效果。
英文摘要：
The sphere-structured support vector machines algorithm is one of the learning methods. It can partition the training samples space by means of constructing the hyperspheres. These hyperspheres have the minimum volume and cover all training samples of each pattern classe. According to this approach, a sphere-structured support vector machines classification algorithm based on the new decision rule was proposed. To investigate the effectiveness of the presented approach, it was applied to seven UCI datasets. Experimental results show the better classification performance than the standard support vector machines algorithm.
同期刊论文项目
同项目期刊论文
期刊信息
位置：