TRAFFIC CONGESTION DETECTION USING DATA MINING IN VANET

Abstract

Information Technology, in the past few years has progressed to a level where it is impossible for an aspect of life to not be touched by it. It is being used to the advantage of humanity in solving difficult engineering problems and improving the quality of life. Vehicular traffic is one such area where modern technology has advanced to a phase where the ideas of interconnecting the vehicles on the road are being experimented with in different countries. These networks of interconnected vehicles are commonly known as Vehicular Ad-hoc Networks or VANETs for short. VANETs provide a platform for the implementation of road safety procedures and access to various features of internet like multimedia, emails, etc. VANETs make use of the on-board communication abilities of a vehicle and pre-installed roadside Units to achieve this goal. One of the most interesting areas of research is the analysis of road traffic. This includes vehicle path tracking, path prediction, intelligent vehicles, congestion detection and many more. Most of the research that has been done to detect traffic congestion used vehicular adhoc network (VANET) but of late data mining approach has been applied. Though most of the proposed work has successfully detected traffic congestion, it is complex to come up with an effective mechanism that incorporates detection, control and prediction of recurrent and nonrecurrent traffic congestions all in one system.