An IoT Solution for Monitoring and Prediction of Bus Stops on University Transportation Using Machine Learning Algorithms

Due to the growth of urbanization, cities have faced social, economic and environmental transformations. In addition, many vehicles currently have several sensors and actuators, capable of performing not only the sensing of the condition of vehicles, but also the environment around them, and this data can be used for various services. The environment of a large university may resemble urban environments, considering that these institutions compare to cities in various aspects, especially in relation to infrastructure problems. The objective of this work is to develop a solution for the monitoring and prediction of bus stops in university transportation. Tests were performed with six online and offline machine learning algorithms in order to analyze which algorithm is most efficient based on the fixed metrics. The best algorithm presented an absolute prediction error of 20 seconds, which shows the quality of the generated final model.