Analyzing passenger train arrival delays with support vector regression

Marković, Nikola; Milinković, Sanjin; Tikhonov, Konstantin S.; Schonfeld, Paul

doi:10.1016/j.trc.2015.04.004

Cited by 163 publications

(66 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Supervised learning methods, in contrast, attempt to predict results, based on assumed connections in the input. For these reasons, neural networks [28,30], Bayesian networks [29], and supporting vector regression methods [31] require initial assumptions on the factors that have direct effect on the desired output, which can be cumbersome to identify and could be hidden. The clustering method proposed here does not require initial assumptions, so any recurrent delay pattern can be identified.…”

Section: Discussionmentioning

confidence: 99%

“…In response, Marković et al [31] introduce Support Vector Regression (SVR) to establish a functional relationship between characteristics of the railway system and train delays. Train category, scheduled time, infrastructure, and share of journey completed are identified as most influencing factors to predict the train delay at one station.…”

Section: Literature Surveymentioning

confidence: 99%

“…The operation of filtering can be considered noise reduction and improves the quality of clustering, as the k-means procedure tends to generate spherical clusters of same radius [38]. According to Marković et al [31], large delays are influenced by different factors other than smaller delays, which further supports the filtering choice. However, in different contexts, the filtering threshold might be set equal to a different value or not be applied at all.…”

Section: Case Study: the Kystbanen Copenhagenmentioning

confidence: 99%

See 2 more Smart Citations

Application of Data Clustering to Railway Delay Pattern Recognition

Cerreto

Nielsen

et al. 2018

Journal of Advanced Transportation

View full text Add to dashboard Cite

K-means clustering is employed to identify recurrent delay patterns on a high traffic railway line north of Copenhagen, Denmark. The clusters identify behavioral patterns in the very large ("big data") datasets generated automatically and continuously by the railway signal system. The results reveal the conditions where corrective actions are necessary, showing the cases where recurrent delay patterns take place. Delay profiles and delay change profiles are generated from timestamps to compare different train runs and to partition the set of observations into groups of similar elements. K-means clustering can identify and discriminate different patterns affecting the same stations, which is otherwise difficult in previous approaches based on visual inspection. Classical methods of univariate analysis do not reveal these patterns. The demonstrated methodology is scalable and can be applied to any system of transport.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Literature Surveymentioning

confidence: 99%

Section: Case Study: the Kystbanen Copenhagenmentioning

confidence: 99%

See 1 more Smart Citation

Application of Data Clustering to Railway Delay Pattern Recognition

Cerreto

Nielsen

et al. 2018

Journal of Advanced Transportation

View full text Add to dashboard Cite

show abstract

“…The closer classified delays for different types of passenger trains (see Table 2) compared 2012 and 2013, passenger trains cover the largest ratio of numbers of delays cases but by comparing the years 2012 and 2013, it can be stated that the number of cases of delays fell by 1.7%, which represents a decrease in the percentage of minutes by 0.77% [7]. …”

Section: The Evaluation Process Of Information Processingmentioning

confidence: 99%

Factors Affecting the Delay of Passenger Trains

Lalinská

Gašparík

Šipuš

2017

LOGI – Scientific Journal on Transport and Logistics

View full text Add to dashboard Cite

Paper deals with the problematic about the information quality impact and the basic methods which can optimize the costs of low quality of using information. First of all, it is important to purify the input data from the inconsistencies and measure the quality of data.This process assures to minimize the reasons that are responsible of poor quality of processes.Targets area of this paper is to identify and minimize the main reasons of delaying the passenger train by comparing years 2012 and 2013. Target groups of passenger trains were divided in three parts responsibilities of delaying -type of train, code of delay, group responsible for the train delay.

show abstract

“…These include Guan et al, [5], Fan and Machemehl [3], Zhou et al [24], Li et al [11], Tsai et al [20], DiJoseph and Chien [2], Kim and Schonfeld [8], and Markovic et al [13]. Kim et al [7] optimized vertical alignments and speed profiles for rail transit lines.…”

Section: Introductionmentioning

confidence: 99%

A Method for Optimizing the Phased Development of Rail Transit Lines

Cheng¹,

Schonfeld

2015

Urban Rail Transit

Self Cite

View full text Add to dashboard Cite

This paper develops a method for optimizing the construction phases for rail transit line extension projects with the objective of maximizing the net present worth and examines the economic feasibility of such extension projects under various financial constraints (i.e., unconstrained, revenue-constrained, and budget-constrained cases). A Simulated Annealing algorithm is used for solving this problem. Rail transit projects may be divided into several phases due to budget limits or demand growth that justifies different sections at different times. A mathematical model is developed to optimize these phases for a simple, one-route rail transit system, running from a Central Business District (CBD) to a suburban area. Some interesting results indicate that the economic feasibility of links with low demand is affected by the completion time of those links and their demand growth rate after their implementation. Sensitivity analysis explores the effects of interest rates on optimized results (i.e., construction phases and objective value). With further development, such a method should be useful to transportation planners and decision-makers in optimizing construction phases for rail transit line extension projects.

show abstract

Analyzing passenger train arrival delays with support vector regression

Cited by 163 publications

References 29 publications

Application of Data Clustering to Railway Delay Pattern Recognition

Application of Data Clustering to Railway Delay Pattern Recognition

Factors Affecting the Delay of Passenger Trains

A Method for Optimizing the Phased Development of Rail Transit Lines

Contact Info

Product

Resources

About