Based on some traditional algorithms, this thesis provides a weighted star cluster algorithm to learn user profile.

对已有算法进行改进，提出了一种加权的星型聚类算法以学习用户的兴趣特征。

youdao

A kind of traditional data cluster algorithm based on grid used the method of the fixed network division, with its faster processing but low accuracy.

传统的基于网格的数据流聚类算法采用固定划分网格的方法，虽然算法的处理速度较快，但是聚类准确性较低。

youdao

In this paper, we propose a new clustering algorithm based on cluster validity indices, which obviates the needs for cluster parameters.

本文提出了一种新的基于有效性指数的聚类算法，无需提供聚类的参数。

youdao