Density classification based on agents under majority rule: Connectivity influence on performance

item.page.type
Artigo de evento
Date
2020
item.page.ispartof
Advances in Intelligent Systems and Computing
item.page.citationsscopus
3
Authors
Abilhoa W.D.
de Oliveira P.P.B.
publication.page.advisor
Journal Title
Journal ISSN
Volume Title
publication.page.board
publication.page.program
Abstract
© Springer Nature Switzerland AG 2020.The density classification task is a prototypical consensus problem of distributed solution, usually addressed in the field of cellular automata. In short, this problem consists of finding the most frequent state in a binary sequence, necessarily through a non-global process on which the automaton reaches uniform consensus about such state. In this regard, we formulate the task as an agent-based model, in which agents set up a connectivity pattern, here corresponding to a circulant graph, and update their internal states according to the majority rule. The performance of the model corresponds to the number of correctly classified densities, given a set of binary sequences. Therefore, our goal is to analyze the sensibility of the model’s performance in terms of the connectivity pattern associated with it, configured as a circulant graph, under different orders, average degrees and connectivity arrangements.
Description
Keywords
item.page.scopussubject
Agent-based model , Circulant graphs , Density classifications , Distributed problem solving , Emergent computation , Majority rule
Citation
Collections