- author = "Tao Wang3 and Xingguang Peng and Yapei Wu and Jian Gao",
- title = "A {GP} Based Two-Layer Framework for Data-Driven Modeling of Swarm Self-Organizing Rules",
- booktitle = "2019 IEEE Congress on Evolutionary Computation, CEC 2019",
- year = "2019",
- editor = "Carlos A. Coello Coello",
- pages = "174--181",
- address = "Wellington, New Zealand",
- month = "10-13 " # jun,
- organization = "IEEE Computational Intelligence Society",
- publisher = "IEEE Press",
- keywords = "genetic algorithms, genetic programming, swarm intelligence, selforganizing rules",
- isbn13 = "978-1-7281-2152-6",
-
DOI = "
doi:10.1109/CEC.2019.8790126",
- size = "8 pages",
- abstract = "There are many swarms of creatures in nature, which lead to a lot of highly ordered and beautiful emergence behaviours. For the modelling of self-organising rules, most of the existing literature focuses on modeling according to special knowledge of physics or biology. Some self-organizing models are proposed in the literature which has been validated by the reproduction of certain emergence motion pattern, such as torus, or flocking. However, there are few studies about data driven modelling of self-organizing rules of swarms. In this paper, we propose a prior knowledge free (i.e., data-driven) approach to learn the self-organizing rules of moving swarms. We use a Genetic Programming (GP) based two-layer framework to optimise the self-organizing model which is consist of neighbour selection rules and corresponding reaction rules. The proposed data-driven modeling method is validated by modeling of three typical collective behaviours (highly parallel group, dynamic parallel group and torus swarm behavior) only according to the simulation data generated from Vicsek and Couzin models. An analysis is conducted with expression tree simplification, swarm behaviour reproduction and global metric evaluation. Results show that the proposed method can learn classic self-organising rules effectively.",
-
notes = "Also known as \cite{8790126}
IEEE Catalog Number: CFP19ICE-ART",
