Abstract | ||
---|---|---|
In this paper, a novel dynamic neighborhood topology based on small world network (SWLPSO) is introduced. The strategy of the learning exemplar choice of the particle is based upon the clustering coefficient and the average shortest distance. This strategy enables the diversity of the swarm to be preserved to discourage premature convergence. Experiments were conducted on a set of classical benchmark functions. The results demonstrate good performance in solving multimodal problems used in this paper when compared with the other PSO variants. |
Year | DOI | Venue |
---|---|---|
2009 | 10.1007/978-3-642-04020-7_85 | ICIC (2) |
Keywords | Field | DocType |
classical benchmark function,premature convergence,multimodal problem,small world network,novel dynamic neighborhood topology,exemplar choice,good performance,pso variant,clustering coefficient,average shortest distance,particle swarm optimizer | Mathematical optimization,Premature convergence,Swarm behaviour,Computer science,Small-world network,Neighbourhood (mathematics),Artificial intelligence,Clustering coefficient,Machine learning,Particle swarm optimizer | Conference |
Volume | ISSN | ISBN |
5755 | 0302-9743 | 3-642-04019-5 |
Citations | PageRank | References |
4 | 0.54 | 12 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yanmin Liu | 1 | 9 | 4.00 |
Qingzhen Zhao | 2 | 14 | 1.76 |
Zengzhen Shao | 3 | 5 | 3.28 |
Zhaoxia Shang | 4 | 4 | 0.54 |
Changling Sui | 5 | 5 | 1.22 |