返回
On rough set based fuzzy clustering for graph data
DOI:10.1007/s13042-022-01607-6.png)
摘要
En 中文
Data clustering refers to partition the original data set into some subsets such that every vertex belongs to one or more subsets at the same time. For graph data that composed by attribute information of vertices as well as structural information between vertices, how to make an efficient clustering is not an easy thing. In this paper, we propose a novel method of how to partition graph data into some overlapping subgraph data in aspect of rough set theory. At first, we introduce a detailed description about the global similarity measurement of vertices. After that, an objective-function oriented optimization model is constructed in terms of updating fuzzy membership degree and cluster center that based on the theory of rough set. Obviously, the determined cluster is no longer a fuzzy set, but a rough set, that is to say, the cluster is expressed by the upper approximation set and lower approximation set. Finally, eleven real-world graph data and four synthetic graph data are applied to verify the validity of the proposed fuzzy clustering algorithm. The experimental results show that our algorithm is better than existing clustering approach to some extent.
Keyword:
Fuzzy clustering
Global similarity measurement
Graph data
Rough set
期刊
IF:
2.7
论文数:
3.2K
被引数:
5.6K
机构
引用论文
Hydroxyapatite deposition disease of the wrist with intraosseous migration to the lunate bone腕关节羟基磷灰石沉积病伴向月骨的骨内迁移
A Multiobjective Evolutionary Algorithm Based on Structural and Attribute Similarities for Community Detection in Attributed Networks基于结构和属性相似性的多目标进化算法在属性网络社区发现中的应用
Cooled radiofrequency ablation of genicular nerves provides 24‐Month durability in the management of osteoarthritic knee pain: Outcomes from a prospective, multicenter, randomized trial股骨神经冷却射频消融在治疗骨关节炎膝关节疼痛方面提供了24‐Month的持久效果:来自一项前瞻性、多中心、随机试验的结果

