论文部分内容阅读
本文讨论的是一个能使客体自动分类的分类模型,所用的分类器是一多层的 Haffman 树。如果一组客体沿形如 Haffman 树状的给定装置从顶部到底部运动,那未它们将按其分类属性被分成不同的类别。关键问题是当一运动客体通过分岔结点时,如何决定其方向。文章提出了两种编码形式,一是关于树中分岔结点编码;一是关于叶子结点的编码。后一种编码反映了运动客体的分类属性和最终运动方向,这些编码形式使得决定客体在分岔结点方向问题变得容易了,只要做逻辑乘就可以了。最后文章给出了解上述问题的两组数据结构和算法。
This article discusses a classification model that enables objects to be automatically classified using a multi-layered Haffman tree. If a group of objects moves from top to bottom along a given device shaped like a Haffman tree, then they will be classified into different categories according to their classification properties. The key question is how to determine the direction of a moving object as it passes through the bifurcation node. The article proposed two kinds of coding forms, one is about the bifurcation node coding in the tree and the other is coding about the leaf nodes. The latter encoding reflects the classification properties and the final direction of motion of the moving object. These encoding forms make it easy to determine the direction of the object in the direction of the bifurcation node, as long as the logical multiplication is done. The last article gives two sets of data structures and algorithms to understand the above problems.