基于动态近邻的DBSCAN算法  

Improved DBSCAN clustering algorithm based on dynamic neighbor

作　　者：李阳[1] 马骊[1] 樊锁海[1] LI Yang;MA Li;FAN Suohai(School of Information Science and Technology, Jinan University, Guangzhou 510632, China)

机构地区：[1]暨南大学信息科学技术学院,广州510632

出　　处：《计算机工程与应用》2016年第20期80-85,共6页Computer Engineering and Applications

基　　金：国家自然科学基金(No.11071089);广东省自然科学基金(No.10151063201000005;No.2014A030313386);广东省教育厅科技创新项目(No.2013KJCX0018)

摘　　要：针对DBSCAN算法聚类参数敏感不易获取、参数固定无法适应密度不均匀数据等问题。提出了动态近邻的概念,即聚类参数随密度动态变化。设计了用于调整动态参数的近邻规模演化算法,即通过限制相对密度变化率,逐步调整近邻规模。最后根据动态的近邻规模,重新定义了DBSCAN算法核心对象的概念,并设计了基于动态近邻的DN-DBSCAN算法。仿真结果表明,DN-DBSCAN能够有效识别非凸及密度分布不均匀的数据样本,聚类效果优于传统DBSCAN算法和其他经典改进算法。DBSCAN is a classic density-based clustering algorithm. DBSCAN algorithm has many flaws, for example:difficult to obtain sensitive parameter, can’t adapt to uneven density data because of the fixed parameter. The concept ofdynamic neighbors is proposed, namely parameters changed with dynamic density. The neighbor scale evolution algorithmis designed to adjust the dynamic parameters, namely by limiting the relative density gradient, adjust the neighbor sizestep by step. Finally, according to the size of dynamic neighbors, it redefines the concept of core object, and designs theDN-DBSCAN algorithm. The simulation result shows that DN-DBSCAN can effectively identify the no convex and unevendistribution of density data samples, the clustering effect is better than the traditional DBSCAN algorithm and other classicalimproved algorithms.

关 键 词：动态近邻 DBSCAN算法 K近邻 近邻密度 相对密度变化率 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]