Optimal subclasses with dichotomous variables for feature selection and discrimination
Optimal subclasses with dichotomous variables for feature selection and discrimination
复制标题
用于特征选择和区分的具有二分变量的最佳子类
DOI：
10.1109/21.44035
复制
发表时间：
1989
期刊：
影响因子：
--
通讯作者：
M. Shimbo
中科院分区：
文献类型：
--
作者：
Mineichi Kudo;M. Shimbo
作者提出了一个有效的算法，寻找最佳子类的类的成员表示的几个二分功能0或1。每个子类都由一个逻辑公式表示，该公式具有其成员之间的共同特征。它表明，一些典型的子类，其中包含大量的样本从一个类，由少数功能。因此，在特征选择问题中，可以将这些特征作为所有特征的一个小子集来选择。最好的子类的选择，当发现的算法是一个中等大小的子类，进行了讨论。>
The authors present an efficient algorithm for finding optimal subclasses of a class whose members are represented by several dichotomous features with 0 or 1. Each subclass is expressed by a logical formula with common features among its members. It is shown that some typical subclasses, which contain a large number of samples from a class, consist of a few features. Thus one can select these features as a small subset of all features in problems of feature selection. The selection of best subclasses, when subclasses found by the algorithm is a moderate size, is discussed. >