0


下坡时使用稳定性探针进行时空聚类

Space-Time Clustering with Stability Probe while Riding Downhill
课程网址: https://videolectures.net/videos/kdd2016_huang_riding_downhill  
主讲教师: Xin Huang
开课单位: KDD 2016研讨会
开课时间: 2025-02-04
课程语种: 英语
中文简介:
我们提出了一种新的数据驱动程序,用于使用稳定性探测的概念在动态聚类算法中优化选择调整参数。由于稳定性探针动力学的形状,我们将新的聚类稳定性过程称为下坡骑行(DR)。我们结合DBSCAN和TRUST研究了DR的最终样本性能,并将其应用于对德国中部的合成时间序列和年度温度记录进行聚类。
课程简介: We propose a new data-driven procedure for optimal selection of tuning parameters in dynamic clustering algorithms, using the notion of stability probe. Due to the shape of the stability probe dynamics, we refer to the new clustering stability procedure as Downhill Riding (DR). We study final sample performance of DR in conjunction with DBSCAN and TRUST in application to clustering synthetic times series and yearly temperature records in Central Germany.
关 键 词: 稳定性; 时空聚类; 数据驱动程序
课程来源: 视频讲座网
数据采集: 2025-03-31:liyq
最后编审: 2025-03-31:liyq
阅读次数: 2