Discrete particle swarm network community detection method with particle diversity and mutation strategies
A discrete particle swarm and detection method technology, applied in the field of discrete particle swarm network community detection, can solve problems such as unsatisfactory, and achieve the effect of stabilizing the quality of community division and global convergence
Inactive Publication Date: 2020-03-24
NANCHANG UNIV
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] The traditional particle swarm optimization algorithm tends to produce local optima during the optimization process, which cannot satisfy the research of deeper problems.
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0027] The technical solutions of the present invention will be further described below in conjunction with the accompanying drawings and through specific implementation methods.
[0028] Such as figure 1 As shown, the integer corresponding to each dimension of the particle is the community to which the node belongs. The particle position is defined as follows:
[0029]
[0030] For a single particle i, its velocity vector is expressed as:
[0031]
[0032] when When , the position vector value corresponding to dimension j change otherwise constant.
[0033] For the position vector P of two particles 1 and P 2 ,and Then the subtraction operation Ξ of the two position vectors represents the variation ΔP of the particle position, that is, the velocity V.
[0034] P 1 ΞP 2 =V={v 1 ,v 2 ,...,v n} (3)
[0035] where v i The calculation rules conform to:
[0036]
[0037] The multiplication operation of the learning factor and the speed is the same as t...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a discrete particle swarm network community detection method with particle diversity and mutation strategies. The discrete particle swarm network community detection method comprises the following steps: (1) redefining particle codes, particle speeds, particle positions and evolutionary operations thereof in a discrete manner; (2) adjusting a strategy based on a hybrid inertia weight; and (3) based on a self-adaptive variation strategy. The invention provides a discrete particle swarm network community detection method with particle diversity and mutation strategies. Particle coding, particle speed, particle position and evolutionary operation thereof are redefined in a discrete manner, the convergence speed of the method is increased based on a hybrid inertia weight adjustment strategy and an adaptive mutation strategy, and the method is prevented from falling into local optimum. Experiments are carried out on a manual reference data set and a real data set, and the effectiveness of the method is verified through experimental results.
Description
technical field [0001] The invention relates to the field of data mining, in particular to a discrete particle swarm network community detection method with particle diversity and variation strategies. Background technique [0002] Community detection in complex networks is a representative hot issue in the field of complex network research. Many systems in reality are abstracted into complex networks for research. The nodes of the network correspond to entities in the system, and the edges of the network correspond to certain relationships between entities. Many researchers have studied networks in various fields, such as social networks, information networks, biological networks, and metabolic regulation networks. After years of research, researchers have found that complex networks have some common characteristics, such as small-world, high aggregation, power-law distribution, and scale-free, etc., and the above characteristics are mainly related to the network topology....
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06N3/00G06Q50/00
CPCG06N3/006G06Q50/01
Inventor 李向军刘凌锋刘伯成王科选周顺吴晓亮卿松
Owner NANCHANG UNIV