Deep learning and big data for future smart cities: A survey

Big data analytics may be used in future smart cities to better understand how residents use the area. Transportation companies may be better able to assess the quality of their services if they have a greater grasp of consumers' travel habits. The triangulation of mobile phone data from millions of anonymous users has made it possible to forecast frequent drivers. Surveys conducted locally and nationally could show how useful the paradigm is it is possible to incorporate data from smart carts, metro and bus vehicle positions, and other sources to estimate how long it takes for passengers to board and deboard trains. In this paper, the Delphi method to compare modern metropolises to forthcoming smart cities. The estimate-talk-estimate approach (ETE), also referred to as the Delphi methodology, is a methodical and qualitative way of forecasting that involves asking a series of questions of experts to elicit their perspectives. The research methodology presents an evaluation and model performance by using deep learning algorithms.