| Abstract |
Smart mobility is one of the major challenges of smart cities. The growth of cities’ population and the urban extensions lead to complex urban transport issues caused by congestion, accidents, rush hours, etc. In this chapter, a recommendation system based on machine learning is proposed to optimize monomodal trips according to users’ expectations and requirements. The main objective is to recommend and sort the best trips based on their rates that are related to combined criteria such as trip safety, comfort, price, mean of transport, and traffic fluidity. We used many machine learning algorithms to come up with the best accuracy. The model evaluation showed high performance for the artificial neural network. The use of the proposed recommendation system could provide users with the best recommendations to better plan and optimize their trips. © 2024 selection and editorial matter, Yassine Maleh, Justin Zhang, and Abderrahim Hansali; individual chapters, the contributors. |
