摘要
提出基于人工鱼群优化的直推式支持向量机分类算法。该算法使直推式学习思想的优势得到充分的展现,在部分UCI标准数据集和20-Newgroups文本实验数据集上的对比实验表明,该算法较经典支持向量机算法和基于蚁群算法的直推式支持向量机算法具有更高的分类性能。
In this paper,a transductive support vector machine classification algorithm based on artificial fish school optimisation is presented.This algorithm gives the advantage of transductive learning concept a full display.Contrasted experiments on part of UCI standard data sets and 20-Newgroups text experimental data set show that,compared with classical support vector machine algorithm and ant colony optimisation-based transductive support vector machine algorithm,the proposed algorithm has higher classification performance.
出处
《计算机应用与软件》
CSCD
北大核心
2013年第3期294-296,共3页
Computer Applications and Software
关键词
直推式学习
支持向量机
人工鱼群算法
Transductive learning Support vector machine Artificial fish school algorithm
