AN ARCHITECTURE OF DEEP LEARNING METHOD TO PREDICT TRAFFIC FLOW IN BIG DATA

Abstract

The invent of IEEE 802.11p as a communication standard, specific network protocol called vehicular adhoc network (VANET) based on mobile adhoc network ( MANET) along with sensor technology has put a strong foundation to visualize as well as make a reality of various intelligent transport applications & systems (ITAS) for safety and comfort. The success of such conceptualized applications depends upon how precisely as well reliability (in term of timeliness) the “traffic flow prediction” is done. The constitute of traffic data is characterized as Big Data type, therefore existing traffic prediction models are not in a capacity to provide the accurate result for various ITAS as the existing models consider low traffic data which lacks the insight of Big Data . In order to overcome these limitations, the synopsis aims to solve the “traffic flow prediction problem” by a novel mechanism of rigorous-learning based prediction model (RLBPM) using big traffic data. The RLBPM will exploit the spatial-temporal correlation statistics and for the purpose of learning algorithm “stacked auto encoder (SAE) model” will be used. The outcome of the RLBPM is expected to perform more superior as compared to the existing traffic flow prediction model. The implementation strategy involved mathematical modeling and simulation using Matlab.