Smart Traffic Analysis using Machine Learning
Aditya Krishna K.V.S1, Abhishek K2, Allam Swaraj3, Shantala Devi Patil4, Gopala Krishna Shyam5
1Aditya Krishna K.V.S, Department of C&IT, REVA University, Bangalore (Karnataka), India.
2Abhishek K, Department of C&IT,.REVA University, Bangalore (Karnataka), India.
3Allam Swaraj, Department of C&IT, REVA University, Bangalore (Karnataka), India.
4Dr. Shantala Devi Patil, Department of C&IT, REVA University, Bangalore (Karnataka), India.
5Dr. Gopala Krishna Shyam, Department of C&IT, REVA University, Bangalore (Karnataka), India.
Manuscript received on 05 June 2019 | Revised Manuscript received on 14 June 2019 | Manuscript Published on 29 June 2019 | PP: 199-202 | Volume-8 Issue-5S, May 2019 | Retrieval Number: E10410585S19/19©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: Congestion is costly as well as annoying. India is the second largest road network in the world. Out of the total stretch of 5.4 million km of road network, almost 97,991 km is covered by national highways.The major cause leading to traffic congestion is the high number of vehicle which was caused by the population and the development of economy[1].Typical urban residents spend more than ten hours a week driving of which (one to three hours) occurs in congested situation. In smart city roads would be equipped with the sensors for analyzing the trafficflow and also there are few traffic analysis / prediction methods use neural network and other prediction models which are not so efficient and suitable for many real world application [1]. So, here in this paper solution for traffic analysis using random forest algorithm is being proposed which would select only part of data for analyze like two third of entire data and predict the traffic congestion of specific path and notifying well in advance the vehicles intending to move to move on that specific path. Thus accurate traffic flow information help road users for fast and safe transporting.
Keywords: Machine Learning, Traffic analysis, Styling, Random Forest.
Scope of the Article: Machine Learning