Rotas Veiculares Cientes de Contexto: Arcabouço e Aná lise Usando Dados Oficiais e Sensoriados por Usuários sobre Crimes

  • Frances A. Santos
  • Diego O. Rodrigues
  • Thiago H. Silva
  • Antonio A. F. Loureiro
  • Leandro A. Villas

Resumo


An increasing number of users have been adopting route recommendation systems, many of them motivated by the convenience that these systems bring to their traffic experiences. These systems observe the current traffic conditions in order to evaluate the fastest path. However, contextual information, such as pollution levels, weather conditions and security of the route, might not be taken into account in the recommendation process. With this in mind, we propose a framework to support contextaware route recommendation systems. Furthermore, we present possible approaches for development of two key components of this framework: (1) identification of contextual areas based on different urban data sources; and (2) identification of typical routes. The proposed framework might improve existing recommendation algorithms, or also enable the proposal of new ones. To validate this hypothesis, we used a set of routes suggested by Google Maps in the city of Curitiba to identify frequent patterns on these routes. Afterwards, some insecure zones were identified in Curitiba using data provided by the government of the city and also data generated by the citizens via their mobile devices. The obtained results showed the existence of an opportunity for route planners to provide differential services to users who desire it, which is an important step towards the development of context-aware vehicular networks.
Publicado
19/05/2017
SANTOS, Frances A.; RODRIGUES, Diego O.; SILVA, Thiago H.; LOUREIRO, Antonio A. F.; VILLAS, Leandro A.. Rotas Veiculares Cientes de Contexto: Arcabouço e Aná lise Usando Dados Oficiais e Sensoriados por Usuários sobre Crimes. In: WORKSHOP DE GERÊNCIA E OPERAÇÃO DE REDES E SERVIÇOS (WGRS), 22. , 2017, Belém. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2017 . ISSN 2595-2722.