Abstract | ||
---|---|---|
This paper proposed an improved adaptive-velocity self-organizing model as a prospective candidate in order to enhance high-speed convergence and accelerate convergence. Moreover, weights are assigned to reinforce convergence under super high-speed circumstances. Convergence performance is assessed via group polarization, convergence ratio and convergent time. As verified by numerical experiments, superior high-speed performance and fast convergence are achieved simultaneously in the improved adaptive-velocity model. The weighted adaptive model prominently improved super high-speed performance with short convergent time and low energy consumption. Then, the parameter space of the weighted adaptive flocking model is investigated. |
Year | DOI | Venue |
---|---|---|
2016 | 10.1016/j.neucom.2016.08.008 | Neurocomputing |
Keywords | Field | DocType |
Self-organization,Collective behavior,Adaptive velocity,Weight,High speed,Quick convergence,Energy efficiency | Convergence (routing),Flocking (texture),Collective behavior,Search engine,Computer science,Efficient energy use,Self-organization,Artificial intelligence,Parameter space,Machine learning,Imagination | Journal |
Volume | Issue | ISSN |
216 | C | 0925-2312 |
Citations | PageRank | References |
2 | 0.38 | 9 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Miaomiao Zhao | 1 | 15 | 0.99 |
Housheng Su | 2 | 1360 | 83.94 |
Miaomiao Wang | 3 | 214 | 24.07 |
Lei Wang | 4 | 35 | 6.07 |
Michael Z. Q. Chen | 5 | 282 | 22.00 |