Avaliação de técnicas de estimação da matriz origem-destino do tráfego de veículos em cidades

• Ano de defesa: 2018
• Autor(a) principal: Pando, Luciano Urgal
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Universidade Tecnológica Federal do Paraná; Curitiba; Brasil; Mestrado em Engenharia Elétrica e Informática Industrial; UTFPR
• Palavras-chave em Português: Engenharia de tráfego; Programação heurística; Mínimos quadrados; Programação linear; Algorítmos genéticos; Partículas (Física nuclear); Inteligência artificial; Trânsito - Fluxo; Transporte Urbano - Porto (Portugal); Transporte Urbano - Curitiba (PR); Sistemas inteligentes de veículos rodoviários; Planejamento urbano - Inovações tecnológicas; Engenharia elétrica; Traffic engineering; Heuristic programming; Least squares; Linear programming; Genetic algorithms; Particles (Nuclear physics); Artificial intelligence; Traffic flow; Urban transportation - Porto (Portugal); Urban transportation - Curitiba (PR); Intelligent transportation systems; City planningTechnological innovations; Electric engineering; CNPQ::CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO; Engenharia Elétrica
• Link de acesso: http://repositorio.utfpr.edu.br/jspui/handle/1/3299

The knowledge of urban mobility patterns is important to maintain good public services as well as for city planning. These mobility patterns can be characterized by using expensive fieldwork or through the huge amount of data available from services and environmental monitoring in smart cities. The origin-destination matrix estimation aims to estimate the traffic of vehicles between two particular origin and destination areas in the city from traffic observed by sensors installed on roads or from probe vehicles. This work evaluates and compares four origin-destination matrix estimation techniques: least squares, mixed-integer linear programming (MILP), genetic algorithm and particle swarm optimization (PSO). Two cities are considered as case studies: OPorto and Curitiba. The city of OPorto in Portugal has data from taxi trips used as probe vehicles. Curitiba in Brazil has road traffic sensors. In addition, due to georeferenced spatial data, algorithms for clustering and map matching are considered to characterize areas of origin-destination and routes, respectively. The case studies show better results for MILP and PSO estimates. However, they strongly depend on the amount and position of sensors.