基于约束投影的支持向量机选择性集成  

Constraint Projection-based Support Vector Machines Selective Ensemble Algorithms

作　　者：王磊[1,2] 

机构地区：[1]西南财经大学经济信息工程学院,成都610074 [2]西南财经大学中国支付体系研究中心,成都610074

出　　处：《计算机科学》2009年第10期234-236,243,共4页Computer Science

基　　金：国家自然科学基金青年项目(69732010);西南财经大学科学研究基金(QN0806)资助

摘　　要：提出两种基于约束投影的支持向量机选择性集成算法。首先利用随机选取的must-link和cannot-link成对约束集确定投影矩阵,将原始训练样本投影到不同的低维空间训练一组基分类器;然后,分别采用遗传优化和最小化偏离度误差两种选择性集成技术对基分类器进行组合。基于UCI数据的实验表明,提出的两种集成算法均能有效提高支持向量机的泛化性能,显著优于Bagging,Boosting,特征Bagging及LoBag等集成算法。This paper proposed two constraint project-based selective ensemble algorithms of support vector machines. Firstly,projective matrices were determined upon randomly selected must-link and cannot-link constraint sets, with which original training samples were transformed into different representation spaces to learn a group of base classifiers. Then, two selective ensemble techniques of genetic optimization and minimizing deviation errors were utilized to combine base classifiers. Experiments on UCI datasets show that both proposed algorithms improve the generalization performance of support vector machines significantly, which are much better than classical ensemble algorithms, such as Bagging, Boosting, feature Bagging and LoBag.

关 键 词：约束投影 选择性集成 支持向量机 分类器 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]