[1]FANG Liandi,ZHANG Yanping,CHEN Jie,et al.Three-way decision based on non-overlapping community division[J].CAAI Transactions on Intelligent Systems,2017,12(3):293-300.[doi:10.11992/tis.201705013]
Copy
CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume:
12
Number of periods:
2017 3
Page number:
293-300
Column:
学术论文—智能系统
Public date:
2017-06-25
- Title:
-
Three-way decision based on non-overlapping community division
- Author(s):
-
FANG Liandi1; 2; ZHANG Yanping1; 2; CHEN Jie1; 2; WANG Qianqian3; LIU Feng1; 2; WANG Gang1; 2
-
1. School of Computer Science and Technology, Anhui University, Hefei 230601, China;
2. Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education, Anhui University, Hefei 230601, China;
3. School of Business, Anhui University, Hefei 230601, China
-
- Keywords:
-
complex network; community division; overlapping node; three-way decision; granulation coefficient; hierarchical clustering; community structure; node belonging degree
- CLC:
-
TP301
- DOI:
-
10.11992/tis.201705013
- Abstract:
-
This paper proposes an algorithm called N-TWD based on the theory of three-way decision, which can further divide overlapping communities formed by the initial clustering into non-overlapping communities. First, it utilizes a hierarchical clustering algorithm to get an overlapping community structure. The nodes in the non-overlapping parts of the community of the left side between two communities with overlapping parts were defined as positive regions. Then, the nodes on its right are denoted as the negative region, and nodes in the overlapping parts are denoted as the boundary region. The degree of belonging (BP,BN) between the positive and negative regions was calculated using the nodes in the boundary region. Moreover, a further division was done based on the degree of belonging. After division, the belonging of the rest nodes in the boundary region would be determined by voting to ultimately get a non-overlapping community structure. The experimental results for four classical social networks and one real-world data-set indicate that the proposed algorithm has a lower time complexity and gets a higher modularity value than other community division algorithms (GN, NFA, LPA, CACDA).