对反求工程中的点云数据处理，给出一种基于特征的区域分割法来划分点云，为后续曲面拟合提供有利条件。
For dealing with the cloud data in reverse engineering, one region-division method which based on character is presented to divide up cloud data, this provides advantage to the later surface fitting.
实现的算法可以直接应用于数据挖掘、数字网格划分与评估、数据分割、数值地形曲面的简化等问题。
The algorithm can be directly applied to data mining, digital grid partitioning and estimation, data partitioning, digital terrain surface simplification, etc.
起源于并行学习算法对数据划分的要求，在对一种现行等分割聚类算法进行改进的基础上，本文提出自己的等分聚类算法。
Rooted in the requirement of data partitioning in parallel learning, we proposed our cluster method by improving a current clustering equally method.
首先给出了属性分割的有效性测试算法，它能检测基于当前分割的交互学习算法是否优越于传统的不划分属性的单一数据集的学习算法；
A feature split algorithm is presented which can test whether this algorithm will outperform the traditional algorithms without using a feature split with a just single view.
首先给出了属性分割的有效性测试算法，它能检测基于当前分割的交互学习算法是否优越于传统的不划分属性的单一数据集的学习算法；
A feature split algorithm is presented which can test whether this algorithm will outperform the traditional algorithms without using a feature split with a just single view.
应用推荐