Smart Recommendations Based on Urban Spaces

Abstract

Smart Urban Planning is the need of this era. A lot of research is going on in this area. We’re predicting traffic intensities at varying times and weather conditions to provide support for Smart Urban Planning. Google provides us the visualized data of traffic at a time. Google also provides the alternative routes at a time but it can’t predict the traffic and alternative routes for the future. The services of the Google are free to a limited number of requests after which it starts charging the user. In our country, during the times of crisis mostly roads are blocked and this not only affect the economy but also causes death of patients due to unreachability of ambulances and it also affects the running local businesses. Our aim is to predict the Optimized Ambulance Routes, Smart Urban Planning and Business Enhancement for Real Estates. The main challenge of our project was the data because data wasn’t available and we had to find a way to make and collect data. We’re collecting data from the Google Map images by making them usable for our project. We’re making a closed source an open source by using the Google images. We will be providing services like ambulance route optimization, better positioning of police staff in times of crisis as well as commercial applications such as identifying optimal locations for real estate and advertisement placement. Improving and analyzing the collected data with the help image processing techniques to predict the traffic intensities. Based on the traffic intensities, system is trained on huge data. The application then predicts the smart recommendations. The front end is designed in Rshiny (a framework of R).