Improvement to the cooperative rules methodology by using the ant colony system algorithm

The cooperative rules (COR) methodology [2] is based on a combinatorial search of cooperative rules performed over a set of previously generated candidate rule consequents. It obtains accurate models preserving the highest interpretability of the linguistic fuzzy rule-based systems. Once the good be...

ver descrição completa

Detalhes bibliográficos
Autores: Alcalá Fernández, Rafael, Casillas Barranquero, Jorge, Cordón García, Oscar, Herrera Triguero, Francisco
Formato: artículo
Fecha de publicación:2001
País:España
Recursos:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2099/3613
Acesso em linha:https://hdl.handle.net/2099/3613
Access Level:acceso abierto
Palavra-chave:Linguistic fuzzy modeling
Learning
Cooperative rules
Ant colony system
COR methodology
Intel·ligència artificial
Aprenentatge automàtic -- Algorismes
Classificació AMS::68 Computer science::68T Artificial intelligence
Descrição
Resumo:The cooperative rules (COR) methodology [2] is based on a combinatorial search of cooperative rules performed over a set of previously generated candidate rule consequents. It obtains accurate models preserving the highest interpretability of the linguistic fuzzy rule-based systems. Once the good behavior of the COR methodology has been proven in previous works, this contribution focuses on developing the process with a novel kind of metaheuristic algorithm: the ant colony system one. Thanks to the capability of this algorithm to include heuristic information, the learning process is accelerated without model accuracy losses. Its behavior is successful compared with other processes based on genetic algorithms and simulated annealing when solving two modeling applications.