基于样本关联度权重的增量支持向量机算法  

Incremental Support Vector Machine Algorithm Based on Weight of Sample Correlation Degree

作　　者：张烨[1] 

机构地区：[1]兰州交通大学电子与信息工程学院,甘肃兰州730070

出　　处：《电子科技》2017年第3期41-44,48,共5页Electronic Science and Technology

基　　金：甘肃省自然科学基金资助项目(1308RJZA111)

摘　　要：当处理数据规模较大、属性较多、且存在噪声数据干扰的医疗数据时,传统的支持向量机会出现训练速度变慢、参数敏感且难以保证其准确率等问题。为解决此问题,文中提出了一种基于样本关联度权重的增量支持向量机算法。通过引入关联度对样本进行加权处理,同时利用KKT条件对训练样本进行筛选,不仅节省了大量的内存存储空间,且减少了训练时间,进一步提高了分类学习的准确度。When processing data on a larger scale, more properties and noise data of medical data, the traditional support vector machine has the problem of slow training speed, sensitive parameters and difficult to ensure its accuracy. In order to solve this problem, this paper proposes an incremental support vector machine algorithm based on the weight of sample correlation degree. By introducing the correlation degree of the sample weighted, at the same time, the KKT conditions for screening of training samples, improved incremental weighted support vector machine algorithm, and it not only to save the large memory storage space, but also reduces the training time, to further improve the accuracy of classification learning.

关 键 词：支持向量机 样本加权 增量支持向量机 KKT条件 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]