摘要
提出一种适用于网络热点事件识别与跟踪的算法,该算法将新事件识别与事件跟踪很好地结合,同时实现快速聚类。
This paper proposes an algorithm that is suitable for the network hot spot event detection and event tracking,this algorithm is very good to union the new event recognition and the event tracking,simultaneously realizes the fast clustering.
出处
《计算机与现代化》
2009年第12期122-124,共3页
Computer and Modernization
基金
湖南省教育厅科研项目(08C458)
关键词
特征提取
权重
种子
时间窗口
feature extraction
weight
seed
time window
