ABSTRACT
The expanding size of cities and the migration of people from rural to urban areas has resulted in a fast growth in the number of cars on the road, which poses several issues for road traffic management authorities in terms of traffic congestion, accidents, and air pollution. Researchers from industry and academia have been putting their efforts in recent years into leveraging advances in sensing, communication, and dynamic adaptive technologies to improve the efficiency of existing road traffic management systems in smart cities to deal with the aforementioned issues. This led to the concept of the intelligent traffic management system (ITMS). This chapter presents a framework in ITMS and discusses its different components. Also, it presents road segments classification techniques using different machine-learning approaches based on traffic density and average speed. Initially, it performs data pre-processing on the acquired traffic data to detect outliers, and it eliminates those outlier data. Density-based spatial clustering of applications with noise (DBSCAN) have been used to detect outliers. Then different machine-learning techniques have been used for the classification of road segments.
