Non-divergent traffic management scheme using classification learning for smart transportation systems

Abstract

Smart transportation is an autonomous arrangement that embodies technologically enabled intelligent vehicles and traffic systems to assist diverse real-time roadside applications and navigation. Intelligent Pervasive computing techniques with a common shared platform, such as the cloud, are employed to ease operations. This article introduces a Non-Divergent Traffic Management Scheme (NDTMS) to improve roadside driving for users and vehicles. This scheme recognizes and classifies traffic, neighbors, and environmental navigation data. Combining two inputs into the ecological data, the Pervasive computing systems assist in non-deviating seamless application support. The input data gives information regarding the traffic on roads and traffic density. The extracted data from the neighbors help in matching the data with features and reduces traffic. The problem of data mishandling for traffic management is addressed by classifier learning links to the application-specific requirements. This Pervasive computing technique operates on combinational data for precise traffic management through navigation/ alerts/ communications.