基于加权矢量场的轨迹层次聚类

陈琳; 王蒙

doi:10.13873/j.1000-9787(2017)06-0010-04

Chinese

您当前的位置：

首页 >

文章列表页 >

基于加权矢量场的轨迹层次聚类

研究与探讨 | 更新时间：2025-09-11

- 基于加权矢量场的轨迹层次聚类
- Trajectory hierarchical clustering based on weighted vector field
- 传感器与微系统 2017年36卷第6期页码：10-13
- 作者机构：
  
  昆明理工大学信息工程与自动化学院
- 作者简介：
- 基金信息：
  
  国家自然科学基金地区基金资助项目（61563025）;云南省教育厅科学研究基金资助项目（2015Z047）
- DOI：10.13873/j.1000-9787(2017)06-0010-04
  中图分类号： TP311.13
- 纸质出版：2017
- 稿件说明：
移动端阅览
[1]陈琳,王蒙.基于加权矢量场的轨迹层次聚类[J].传感器与微系统,2017,36(06):10-13.

CHEN Lin, WANG Meng. Trajectory hierarchical clustering based on weighted vector field[J]. 2017, 36(6): 10-13.
[1]陈琳,王蒙.基于加权矢量场的轨迹层次聚类[J].传感器与微系统,2017,36(06):10-13. DOI： 10.13873/j.1000-9787(2017)06-0010-04.

CHEN Lin, WANG Meng. Trajectory hierarchical clustering based on weighted vector field[J]. 2017, 36(6): 10-13. DOI： 10.13873/j.1000-9787(2017)06-0010-04.

摘要

传统的轨迹聚类方法存在定义轨迹相似度难度大

聚类过程中容易忽略轨迹细节等问题。基于矢量场的轨迹聚类（VFC）在保持轨迹原始运动特征的基础上

利用矢量场的几何结构可以很好地度量轨迹相似度。引入加权拟合方法

降低噪声对聚类的影响

以解决VFC鲁棒性较差问题。采用层次聚类动态地决定聚类类别数

以解决聚类类别数不能自适应的问题

提高聚类有效性。采用亚特兰大飓风数据作为实验原始轨迹数据

分别使用经典矢量场的轨迹聚类

k-means聚类

k-mediods聚类以及提出的方法进行实验

实验结果证明了加权拟合矢量场的层次聚类算法的有效性。

Abstract

It is hard to define similarity of trajectories and trends to ignore details of trajectories using a traditional trajectory clustering method. Vector field based clustering methods keep the inherent features of movements and measures similarities of trajectories with the geometric structure information derived from it. Weighted fitting scheme is introduced to weaken the effects of noises and increase the robustness of clustering. A hierarchical approach is employed to automatically determine the number of class solving the problem that traditional methods cannot be self-adaptive to clustering

thus improving the effectiveness of our method. Experiments of traditional vector field clustering

k-means clustering and k-mediods clustering as well as the proposed method are conducted on the Atlanta Hurricane dataset

and the result shows the effectiveness of the hierarchical clustering algorithm based on weighted vector field.

关键词

Keywords

references

基于K-means聚类点密度的WSNs加权质心定位算法 [J]. 张乙竹,周礼争,唐瑞,余敏. 传感器与微系统 . 2015(07)

基于改进混合蛙跳-K均值聚类算法的无功电压控制分区 [J]. 王联国,韩晓慧,宋磊. 传感器与微系统 . 2013(06)

一种利用统计中值的加权定位算法 [J]. 严筱永,钱焕延,施卫娟,杨万扣. 传感器与微系统 . 2011(08)

Vector Field k ‐Means: Clustering Trajectories by Fitting Multiple Vector Fields [J] . Nivan Ferreira,James T. Klosowski,Carlos E. Scheidegger,Cláudio T. Silva. Computer Graphics Forum . 2013 (3pt2)

An exploratory data analysis （EDA） of the paths of moving animals [J] . David R Brillinger,Haiganoush K Preisler,Alan A Ager,John G Kie. Journal of Statistical Planning and Inference . 2003 (1)

On Clustering Validation Techniques. [J] . Maria Halkidi,Yannis Batistakis,Michalis Vazirgiannis. J. Intell. Inf. Syst. . 2001 (2-3)

Robust regression methods for computer vision: A review [J] . Peter Meer,Doron Mintz,Azriel Rosenfeld,Dong Yoon Kim. International Journal of Computer Vision . 1991 (1)

Comparing partitions [J] . Lawrence Hubert,Phipps Arabie. Journal of Classification . 1985 (1)

A dendrite method for cluster analysis [J] . T. Calinski,J. Harabasz. Communications in Statistics - Theory and Methods . 1974 (1)

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

未知状况下光伏发电系统运行状态评估方法

基于传感器的室内测试轨迹系统