Computational Technology Resources - CCP

M. Milenkovic¹, N. Bojovic¹, N. Glišovic² and R. Nuhodzic³

¹Division for Management in Railway, Rolling stock and Traction, Faculty of Transport and Traffic Engineering, University of Belgrade, Serbia
²Department for Mathematical Sciences, State University of Novi Pazar, Serbia
³Railway Infrastructure of Montenegro, Podgorica, Montenegro

doi:10.4203/ccp.104.193

purchase the full-text of this paper

, "Comparison of Sarima-Ann and Sarima-Kalman Methods for Railway Passenger Flow Forecasting", in J. Pombo, (Editor), "Proceedings of the Second International Conference on Railway Technology: Research, Development and Maintenance", Civil-Comp Press, Stirlingshire, UK, Paper 193, 2014. doi:10.4203/ccp.104.193

Keywords: railways, passenger service, forecasting, SARIMA, artificial neural networks, Kalman filtering.

Summary

For future planning purposes, every industry must have a flow of information concerning the expected demand for its product. In the case of railways, both the capacities to be used and the expected total revenue depend on the level of future rail passenger traffic, so that the railways have a crucial need for forecasts of their passenger traffic. Based on Time Series, Kalman Filter and Artificial Neural Networks, in this paper, two hybrid methods are proposed for railway passenger flow forecasting. In SARIMA-ANN model, the SARIMA model is used to decide the structure of an ANN model. In hybrid SARIMA-Kalman model, the SARIMA model is utilized to initialize the Kalman state and measurement equations for a Kalman model. Forecasting results of presented models are compared and they demonstrate the capability and effectiveness of the proposed models that can assist managers to better predict rail passenger demand.

purchase the full-text of this paper (price £20)

go to the previous paper
go to the next paper
return to the table of contents
return to the book description
purchase this book (price £65 +P&P)

	Computational & Technology Resources an online resource for computational, engineering & technology publications
	not logged in - login
Front Page Browse CCP CSETS CTR IJRT Other Authors Search Purchase Guide FAQ Contact us	Civil-Comp Proceedings ISSN 1759-3433 CCP: 104 PROCEEDINGS OF THE SECOND INTERNATIONAL CONFERENCE ON RAILWAY TECHNOLOGY: RESEARCH, DEVELOPMENT AND MAINTENANCE Edited by: J. Pombo Paper 193 Comparison of Sarima-Ann and Sarima-Kalman Methods for Railway Passenger Flow Forecasting M. Milenkovic¹, N. Bojovic¹, N. Glišovic² and R. Nuhodzic³ ¹Division for Management in Railway, Rolling stock and Traction, Faculty of Transport and Traffic Engineering, University of Belgrade, Serbia ²Department for Mathematical Sciences, State University of Novi Pazar, Serbia ³Railway Infrastructure of Montenegro, Podgorica, Montenegro doi:10.4203/ccp.104.193 purchase the full-text of this paper Full Bibliographic Reference for this paper , "Comparison of Sarima-Ann and Sarima-Kalman Methods for Railway Passenger Flow Forecasting", in J. Pombo, (Editor), "Proceedings of the Second International Conference on Railway Technology: Research, Development and Maintenance", Civil-Comp Press, Stirlingshire, UK, Paper 193, 2014. doi:10.4203/ccp.104.193 Keywords: railways, passenger service, forecasting, SARIMA, artificial neural networks, Kalman filtering. Summary For future planning purposes, every industry must have a flow of information concerning the expected demand for its product. In the case of railways, both the capacities to be used and the expected total revenue depend on the level of future rail passenger traffic, so that the railways have a crucial need for forecasts of their passenger traffic. Based on Time Series, Kalman Filter and Artificial Neural Networks, in this paper, two hybrid methods are proposed for railway passenger flow forecasting. In SARIMA-ANN model, the SARIMA model is used to decide the structure of an ANN model. In hybrid SARIMA-Kalman model, the SARIMA model is utilized to initialize the Kalman state and measurement equations for a Kalman model. Forecasting results of presented models are compared and they demonstrate the capability and effectiveness of the proposed models that can assist managers to better predict rail passenger demand. purchase the full-text of this paper (price £20) go to the previous paper go to the next paper return to the table of contents return to the book description purchase this book (price £65 +P&P)
Back to top	©Civil-Comp Limited 2023 - terms & conditions