Abstract | ||
---|---|---|
Despite the many features that the behaviour of the standard particle swarm algorithm shares with grouping behaviour in animals (e.g. social attraction and communication between individuals), this biologically inspired technique has been mainly used in classical optimisation problems (i.e. finding the optimal value in a fitness landscape). We present here a novel application for particle swarms: the simulation of group-foraging in animals. Animals looking for food sources are modelled as particles in a swarm moving over an abstract food landscape. The particles are guided to the food by a smell (or aura), which surrounds it and whose intensity is proportional to the amount of food available. The results show that this new extended version of the algorithm produces qualitatively realistic behaviour. For example, the simulation shows the emergence of group-foraging behaviour among particles. |
Year | DOI | Venue |
---|---|---|
2006 | 10.1007/11844297_67 | PPSN |
Keywords | Field | DocType |
qualitatively realistic behaviour,group-foraging behaviour,grouping behaviour,particle swarm,new extended version,standard particle swarm algorithm,food source,fitness landscape,abstract food landscape,classical optimisation problem | Mathematical optimization,Fitness landscape,Swarm behaviour,Evolutionary algorithm,Computer science,Parallel algorithm,Swarm intelligence,Artificial neural network,Foraging,Particle | Conference |
Volume | ISSN | ISBN |
4193 | 0302-9743 | 3-540-38990-3 |
Citations | PageRank | References |
4 | 0.88 | 2 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Cecilia Di Chio | 1 | 251 | 21.24 |
Riccardo Poli | 2 | 2589 | 308.79 |
Paolo Di Chio | 3 | 22 | 5.36 |