Bagging and the Random Subspace Method for Redundant Feature Spaces
Bagging and the Random Subspace Method for Redundant Feature Spaces
复制标题
冗余特征空间的Bagging和随机子空间方法
DOI：
10.1007/3-540-48219-9_1
复制
发表时间：
2001
期刊：
影响因子：
--
通讯作者：
R. Duin
中科院分区：
文献类型：
--
作者：
M. Skurichina;R. Duin
通过将Bagging、Boosting和随机子空间方法相结合，可以提高单个弱分类器的性能。当将它们应用于线性判别分析时，它们似乎在不同的情况下都很有用。它们的性能受到基础分类器的选择和训练样本大小的强烈影响。同样，它们的有用性取决于数据分布。本文以伪Fisher线性分类器为例，研究了数据特征集的冗余性对随机子空间方法和Bagging方法性能的影响。
The performance of a single weak classifier can be improved by using combining techniques such as bagging, boosting and the random subspace method. When applying them to linear discriminant analysis, it appears that they are useful in different situations. Their performance is strongly affected by the choice of the base classifier and the training sample size. As well, their usefulness depends on the data distribution. In this paper, on the example of the pseudo Fisher linear classifier, we study the effect of the redundancy in the data feature set on the performance of the random subspace method and bagging.