Abstract
Railroads have been experiencing traffic demand growth and increasing capacity constraints. Effective capacity management is thus crucial to the successful operation of railroads. The initial step in capacity management is to measure and monitor capacity and congestion. This research established a process for constructing parametric capacity models for single- and double-track railroads with simulation results using both regression and neural network (NN) techniques. Experimental results show that the NN models outperform the regression models in terms of predicting both single- and double-track capacity. Aside from traffic volume, average train speed and siding/crossover spacing were identified as the most sensitive factors relative to rail capacity. The use of this capacity evaluation tool can determine efficiency of current operations and can provide an objective basis to assess the need for capital expansion projects.
Similar content being viewed by others
References
American Association of State Highway, Transportation Officials (AASHTO) (2007) Transportation—invest in our future: America’s freight challenge. AASHTO, Washington
Cambridge Systematics (2007) National rail freight infrastructure capacity and investment study. Association of American Railroads, Washington
Abril M, Barber F, Ingolotti L, Salido MA, Tormos P, Lova A (2008) An assessment of railway capacity. Transp Res E 44:774–806
Hansen IA, Pachl J (2008) Railway timetable & traffic: analysis, modelling, simulation. Eurailpress, Hamburg
Martland CD, Hutt G (2005) Analysis of potential approaches to interline capacity flow management. Railinc, Cary
Lai YC, Barkan CPL (2011) Comprehensive decision support framework for strategic railway capacity planning. ASCE J Transp Eng 137(10):738–749
Landex A (2009) Evaluation of railway networks with single track operation using the UIC 406 capacity method. Netw Spat Econ 9(1):7–23
Dicembre A, Ricci S (2011) Railway traffic on high density urban corridors: capacity, signalling and timetable. J Rail Transp Plan Manag 1(2):59–68
Medeossi G, Longo G, de Fabris S (2011) A method for using stochastic blocking times to improve timetable planning. J Rail Transp Plan Manag 1(1):1–13
Lindner T (2011) Applicability of the analytical UIC code 406 compression method for evaluating line and station capacity. J Rail Transp Plan Manag 1(1):49–57
Goverde RMP, Corman F, D’Ariano A (2013) Railway line capacity consumption of different railway signalling systems under scheduled and disturbed conditions. J Rail Transp Plan Manag. doi:10.1016/j.jrtpm.2013.12.001
Lai YC, Barkan CPL (2009) Enhanced parametric railway capacity evaluation tool. Transp Res Rec J Transp Res Board 2117:33–40
Krueger H (1999) Parametric modeling in railway planning. In: Proceedings of winter simulation conference, Phoenix, AZ
Prokopy JC, Rubin RB (1975) Parametric analysis of railway line capacity. Publication DOT-FR-5014-2. FRA, US Department of Transportation
Harrod S (2009) Capacity factors of a mixed speed railway network. Transp Res E 45:830–841
Sogin S, Lai YC, Dick CT, Barkan CPL (2013) Comparison of capacity of single- and double-track rail lines using simulation analyses. Transp Res Rec J Transp Res Board 2374:111–118
Gorman MH (2009) Statistical estimation of railroad congestion delay. Transp Res E 45:446–456
Abril M, Barber F, Ingolotti L, Salido MA, Tormos P, Lova A (2007) An assessment of railway capacity. Transp Res E. doi:10.1016/j.tre.2007.04.001
Pachl J, White T (2004) Transportation Research Board. 83rd annual meeting on 11-15 Jan 2004. Compendium of papers CD-ROM
Bronzini MS, Clarke DB (1985) Estimating rail line capacity and delay by computer simulation. Transp Forum 2–1:5–11
Fransoo C, Bertranda J (2000) Aggregate capacity estimation model for the evaluation of railroad passing constructions. Transp Res A 34(1):35–49
Vromans MJCM, Dekker R, Kroon LG (2006) Reliability and heterogeneity of railway services. Eur J Oper Res 172:647–655
Tu JV (1996) Advantages and disadvantages of using artificial neural networks versus logistic regression for predicting medical outcomes. J Clin Epidemiol 49(11):1225–1231
Kerh T, Ting SB (2005) Neural network estimation of ground peak acceleration at stations along taiwan high-speed rail system. Eng Appl ArtifIntell 18:857–866
Schafer DH, Barkan CPL (2008) A hybrid logistic regression/neural network model for the prediction of broken rails. In: Proceedings of the 8th World Congress on Railway Research, Seoul, Korea, May 2008
Tsai TH, Lee CK, Wei CH (2009) Neural network based temporal feature models for short-term railway passenger demand forecasting. Expert Syst Appl 36:3728–3736
Karakasis K, Skarlatos D, Zakinthinos T (2005) A factorial analysis for the determination of an optimal train speed with a desired ride comfort. Appl Acoust 66:1121–1134
Ghosh S, Tian Y (2006) Optimum two level fractional plans for model identification and discrimination. J Multivar Anal 97:1437–1450
Murali P, Dessouky M, Ordonez F, Palmer K (2010) A delay estimation technique for single and double-track railroads. Transp Res E 46:483–495
Xu Y, Dong ZY, Zhang R, Meng K, Dai Y, Dai Y (2012) Extreme learning machine-based predictor for real-time frequency stability assessment of electric power systems. Neural Comput Appl. doi:10.1007/s00521-011-0803-3
Sheikhan M, Mohammadi N, Mohammadi N (2011) Neural-based electricity load forecasting using hybrid of GA and ACO for feature selection. Neural Comput Appl. doi:10.1007/s00521-011-0599-1
Abdi J, Moshiri B, Abdulhai B, Sedigh AK (2012) Short-term traffic flow forecasting: parametric and nonparametric approaches via emotional temporal difference learning. Neural Comput Appl. doi:10.1007/s00521-012-0977-3
Li CS, Chen MC (2012) Identifying important variables for predicting travel time of freeway with non-recurrent congestion with neural networks. Neural Comput Appl. doi:10.1007/s00521-012-1114-z
Lewis EB (1981) Control of body segment differentiation in Drosophila by the bithorax gene complex. Prog Clin Biol Res 85:269–288
Dogan E, Akgungor AP (2011) Forecasting highway casualties under the effect of railway development policy in Turkey using artificial neural networks. Neural Comput Appl. doi:10.1007/s00521-011-0778-0
Steel RGD, Torrie JH (1960) Principles and procedures of statistics. McGraw-Hill, New York, pp 187–287
Ozer DJ (1985) Correlation and the coefficient of determination. Psychol Bull 97(2):307–315
Hyndman RJ, Koehler AB (2006) Another look at measures of forecast accuracy. Int J Forecast 22(4):679–688
Vantuono WC (2005) Capacity is where you find it: how BNSF balances infrastructure and operations. Railw Age 206(2):17–23
Dingler MH, Lai YC, Barkan CPL (2013) Mitigating train type heterogeneity on a single track line. J Rail Rapid Transit 227(2):140–147
Dingler MH, Lai YC, Barkan CPL (2013) Effect of train type heterogeneity on single-track heavy haul railway line capacity. J Rail Rapid Transit. doi:10.1177/0954409713496762
Russell SJ, Norvig P (1995) Artificial intelligence—a modern approach. Prentice-Hall, Englewood Cliffs
Hoffmann AG (1998) Paradigms of artificial intelligence. Springer, Berlin
Munakata T (1998) Fundamentals of the new artificial intelligence. Springer, New York
Yeh YC (2002) Application of neural network. Scholar Books Co. Ltd, Taipei
Dreiseitl S, Ohno-Machado L (2002) Logistic regression and artificial neural network classification models: a methodology review. J Biomed Inform 35:352–359
Bejou D, Wray B, Ingram TN (1996) Determinants of relationship quality: an artificial neural network analysis. J Bus Res 36:137–143
Tu JV (1996) Advantages and disadvantages of using artificial neural networks versus logistic regression for predicting medical outcomes. J Clin Epidemiol 49:1225–1231
Ayer Turgay et al (2010) Comparison of logistic regression and artificial neural network models in breast cancer risk estimation. Radiographics 30(1):13–22
Vaughan MB (1998) The arc elasticity of demand: a note and comment. J Econ Educ 19(3):254–258
Beuthe M, Jourquin B, Geerts JF, Ha CKN (2001) Freight transportation demand elasticities: a geographic multimodal transportation network analysis. Transp Res E 37:253–266
Acknowledgments
The authors are grateful to Eric Wilson and Mark Dingler for their assistance in this research. This project was funded by National Science Council (NSC) of the Republic of China under Grant NSC 98-2221-E-002-114-MY3.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Lai, YC., Huang, YA. & Chu, HY. Estimation of rail capacity using regression and neural network. Neural Comput & Applic 25, 2067–2077 (2014). https://doi.org/10.1007/s00521-014-1694-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-014-1694-x