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：
为进一步提高支持向量分类器的分类精度和运行速度，提出了基于自适应核函数的支持向量数据描述分类算法。该算法的核心思想为：根据信息几何中保角映射的方法构造数据驱动的核函数修正算法，然后再利用修正的核函数训练支持向量数据描述分类算法。试验结果表明，该方法具有较好的分类精度和较快的运行速度。
英文摘要：
A support vector data description classification algorithm based on an adaptive kernel function is proposed in order to further improve the classification accuracy and running speed of a support vector classifier. The essential features of the algorithm are as follows： A kernel modification algorithm is constructed according to the conformal mapping of information geometry and the modified kernel function is subsequently used to train the classification algorithm in support vector data description. The experimental results show that the proposed algorithm possesses higher classification accuracy and faster running speed.
同期刊论文项目
同项目期刊论文
期刊信息
位置：