基于k均值聚类的直推式支持向量机学习算法  

k means clustering based transductive support vector machine algorithm

作　　者：王立梅[1] 李金凤[1] 岳琪[2] 

机构地区：[1]牡丹江师范学院工学院,黑龙江牡丹江157011 [2]东北林业大学信息与计算机工程学院,哈尔滨150040

出　　处：《计算机工程与应用》2013年第14期144-146,共3页Computer Engineering and Applications

基　　金：黑龙江省自然科学基金(No.F200919);牡丹江市科技局攻关项目(No.G2011a852);牡丹江师范学院基金项目(No.QZ201212)

摘　　要：针对直推式支持向量机(TSVM)学习模型求解难度大的问题,提出了一种基于k均值聚类的直推式支持向量机学习算法——TSVMKMC。该算法利用k均值聚类算法,将无标签样本分为若干簇,对每一簇样本赋予相同的类别标签,将无标签样本和有标签样本合并进行直推式学习。由于TSVMKMC算法有效地降低了状态空间的规模,因此运行速度较传统算法有了很大的提高。实验结果表明,TSVMSC算法能够以较快的速度达到较高的分类准确率。As transductive support vector machine runs slowly, this paper proposes a k means clustering based transductive sup- port vector machine algorithm. The algorithm utilizes k means clustering to divide the unlabeled samples into several clusters, labels them with the same class, makes transductive inference on the mixed data set composed by both labeled and unlabeled samples. As TSVMKMC algorithm reduces the size of the state space effectively, the running speed is improved largely. The experimental results show that the algorithm can achieve good classification accuracy with faster speed.

关 键 词：直推式学习 支持向量机 K均值聚类 无标签样本 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]