TRAFFIC CONTROL THROUGH FUZZY LOGIC AND NEURAL NETWORKS / CONTROLE DE SEMÁFOROS POR LÓGICA FUZZY E REDES NEURAIS
AUTOR(ES)
ALEXANDRE ROBERTO RENTERIA
DATA DE PUBLICAÇÃO
2002
RESUMO
This work presents the use of fuzzy logic and neural networks in the development of a traffic signal controller - FUNNCON. The work consists of four main sections: study of traffic engineering fundamentals; definition of a methodology for evaluation of traffic controls; definition of the proposed controller model; and implementation on a case study using real data.The study of traffic engineering fundamentals considers definitions of terms,parameters used for traffic flow description, types of intersections and their traffic signals,commonly used traffic control systems and performance measures.In order to analyse the results provided by FUNNCON, a methodology for the evaluation of controllers is defined. The existing traffic simulators are investigated, in order to select the best one for the present study.The definition of the FUNNCON model includes a brief description of its modules.Thereafter each module is studied separately: the use of neural networks for future traffic prediction; the setup of a best scenario database using an optimizer; and the extraction of fuzzy rules from this database.In the case study, FUNNCON is implemented with real data supplied by CET-Rio from an intersection in Rio de Janeiro; its performance is compared with that of the existing controller.It can be observed that neural networks can present good results in the prediction of future traffic and that the fuzzy rules created from the best scenario database lead to an effective traffic control at the considered intersection. When compared with the system in operation, FUNNCON reveals itself much superior.
ASSUNTO(S)
fuzzy rules neural networks traffic control fuzzy logic regras fuzzy controle de trafego redes neurais logica fuzzy
ACESSO AO ARTIGO
Documentos Relacionados
- ARTIFICIAL NEURAL NETWORKS, FUZZY LOGIC AND NEURO-FUZZY SYSTEM IN THE ROLE OF SHORT TERM LOAD FORECAST
- MODELO DE PREVISÃO DE CARGA DE CURTO PRAZO UTILIZANDO REDES NEURAIS E LÓGICA FUZZY
- Modeling and predictive hybrid control by fuzzy logic for polymerization processes
- Desenvolvimento e análise de controle híbrido preditivo por lógica fuzzy de processos de polimerização
- AUXÍLIO À ANÁLISE DE SÉRIES TEMPORAIS NÃO SAZONAIS USANDO REDES NEURAIS NEBULOSAS