A dynamic, interpretable, and robust hybrid data analytics system for train movements in large-scale railway networks

Oneto, Luca; Buselli, Irene; Lulli, Alessandro; Canepa, Renzo; Petralli, Simone; Anguita, Davide

doi:10.1007/s41060-018-00171-z

Cited by 21 publications

(12 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…End If (12) End if (13) End for (14) End if (15) End for (16) If equations (14)-(16) cannot be satisfied then (17) A � Null; (18) Break; (19) End if (20) End for (21) Return Z 2 � Equation (13); ALGORITHM 1 Table 2: Proportion of passengers' departure time intention in each time period.…”

Section: Results Andmentioning

confidence: 99%

“…For the adjustment method of the train operation, the problem of the train movement is important. Lulli et al [17] and Oneto et al [18] studied four important aspects of the train movements in the larger-scale railway network: the travel time, the dwell time, the train delay, and the penalty costs.…”

Section: Adjustment Methods Of the Train Operationmentioning

confidence: 99%

“…is strategy should ensure that the running time of the adjusted train in the section does not exceed the minimum running time. erefore, the section acceleration scheme can be selected based on equation (18), which indicates that the arrival headway between the adjusted train i and the front train i − 1 should not be less than the minimum arrival headway at station s.…”

Section: Section Accelerationmentioning

confidence: 99%

See 2 more Smart Citations

An Adjustment Method for the Customized Trains of the Railway

Shi

et al. 2020

Journal of Advanced Transportation

View full text Add to dashboard Cite

The “customized train” is a train operated by the customized service of the passengers. The departure time, total travel time, and the travel classes are decided by passengers’ wishes. Successful operation of customized trains (CT) has a great significance to the future development in the relationship between the railway enterprise and the passenger service. In order to establish a comprehensive method for the CT operation plan, the paper proposes an intention survey method to obtain the passenger travel wishes data. Then, according to the existing timetable, the alternative set of CTs is built. The CT should satisfy the constraints of the passenger demand, the stop, and the train travel time. Based on the alternative set, a bilevel programming model for the maximum operation revenue of the CTs and minimum adjustment cost of existing timetable is established according to the passengers’ travel demands. The model also considers the constraints of actual travel time, arrival headway, departure headway, maximal adjustment time and capacity, and so on. The adjustment strategies for the train operation confliction are established. Finally, the method is proven through the analysis of actual cases, which can provide decision-making basis for future railway enterprises when operating the customized trains.

show abstract

Section: Results Andmentioning

confidence: 99%

Section: Adjustment Methods Of the Train Operationmentioning

confidence: 99%

Section: Section Accelerationmentioning

confidence: 99%

See 1 more Smart Citation

An Adjustment Method for the Customized Trains of the Railway

Shi

et al. 2020

Journal of Advanced Transportation

View full text Add to dashboard Cite

show abstract

“…In Europe the increasing volume of people and freight transported on railways is congesting the network. The only viable solution to increase capacity, in the short/medium term, is then to improve the efficiency in order to be able to control a larger number of running trains without requiring massive public investments in new physical assets 1 . For this reason, in the last years, all the major players of the European railways grouped together 2 and started extensive modernisation programs that leverage on advanced ICT solutions, Artificial Intelligence (AI)-based especially, to improve system safety and service reliability, to enhance passenger experience, to provide higher transit capacity, and to reduce operational costs.…”

Section: Introductionmentioning

confidence: 99%

“…The study of train movements has a long history and, in the last 10 years, it has attracted the interest of both researchers and industry because of the ability of the new generation of AI-based systems to positively impact on the efficiency of the railway. In particular, a significant effort has been spent in predicting inter-station trains movements to support railway stakeholders decisions [1,2]: infrastructure managers and train operators can better plan the use and the exploitation of the railway infrastructure, while travellers can be informed timely of congestion and delays. Much less effort has been spent in studying the in-station movements because of the complexity in retrieving the related fine-grained data.…”

Section: Introductionmentioning

confidence: 99%

In-Station Train Movements Prediction: from Shallow to Deep Multi Scale Models

Boleto¹,

Oneto²,

Cardellini³

et al. 2021

ESANN 2021 Proceedings

Self Cite

View full text Add to dashboard Cite

Public railway transport systems play a crucial role in servicing the global society and are the transport backbone of a sustainable economy. While a significant effort has been devoted to predict inter-station trains movements to support stakeholders (i.e., infrastructure managers, train operators, and travellers) decisions, the problem of predicting instation movements, while being crucial to improve train dispatching (i.e., empowering human or automatic dispatchers), has been far more less investigated. In fact, stations are the most critical points in a railway network: even small improvements in the estimation of the duration of trains movements can remarkably enhance the dispatching efficiency in coping with the increase in capacity demand and with delays. In this work we will first leverage on state of the art shallow models, fed by domain experts with domain specific features, to improve the current predictive systems. Then, we will leverage on a customised deep multi scale model able to automatically learn the representation and improve the accuracy of the shallow models. Results on real-world data coming from the Italian railway network will support our proposal. * This work has been partially funded by Hitachi Rail STS through the RAIDLab (Railway Artificial Intelligence and Data Analysis Laboratory), a joint laboratory between Hitachi Rail STS and University of Genoa.1 https://ec.europa.eu/transport/themes/infrastructure en 2 https://shift2rail.org/ 475

show abstract

Data Analytics Framework Based on Cloud Environment

Kanagaraj¹,

Geetha²

2021

Integration of Cloud Computing With Internet of Things

View full text Add to dashboard Cite

A dynamic, interpretable, and robust hybrid data analytics system for train movements in large-scale railway networks

Cited by 21 publications

References 31 publications

An Adjustment Method for the Customized Trains of the Railway

An Adjustment Method for the Customized Trains of the Railway

In-Station Train Movements Prediction: from Shallow to Deep Multi Scale Models

Data Analytics Framework Based on Cloud Environment

Contact Info

Product

Resources

About