Smart City Gnosys

Smart city article details

Title	Markov Chain Long Run Probabilities For Estimation Of Traffic Flow
ID_Doc	36435
Authors	Sujatha R.; Kuppuswami G.; Nagarajan D.
Year	2020
Published	AIP Conference Proceedings, 2282
DOI	http://dx.doi.org/10.1063/5.0028464
Abstract	Traffic congestion is an important social problem in a past few decades. Prediction of traffic conditions study has recently become increased and gained attention of researchers and significant number of different forecasting method exist in this field because of its vital role played to control the traffic and decision making process. Traffic control is vital in smart cities. This work attempts to find the equilibrium state for traffic volume detection using Markov chain. The proposed approach is demonstrated through a case study. A Markov chain is a stochastic model comprising of a set of states and the conditional probabilities of transition between them. The equilibrium state of a Markov chain denotes the probability of being in each state in the long run. The new proposed approach very useful to know the change of traffic flow in any junction. This method also helpful to the transportation department to know the variation of the traffic in any congested place. © 2020 Author(s).
Author Keywords	equilibrium state; Markov chain; Traffic congestion; traffic prediction; traffic states; transition probability

Id	Similarity	Authors	Title	Published
11709	0.876	Pop M.-D.; Prostean O.	Bayesian Reasoning For Od Volumes Estimation In Absorbing Markov Traffic Process Modeling	2019 4th MEC International Conference on Big Data and Smart City, ICBDSC 2019 (2019)
25580	0.868	Mehta V.; Mapp G.; Gandhi V.	Exploring New Traffic Prediction Models To Build An Intelligent Transport System For Smart Cities	Proceedings of the IEEE/IFIP Network Operations and Management Symposium 2022: Network and Service Management in the Era of Cloudification, Softwarization and Artificial Intelligence, NOMS 2022 (2022)