A feasibility study on developing an intelligence ensemble system for predicting and preventing train delays
University of East Anglia
With support from Greater Anglia
Projects
In October 2017, RSSB launched a £500,000 call for research to identify novel data-driven solutions to key network performance challenges.
The five projects that were awarded funding show how machine learning, graph theory and data analytics can be used to make accurate predictions about the impact of reactionary delays and dwell time variations. The findings were presented at a one-day 'Enabling Better Performance' conference on 4 April 2019 (see article).
Find out more about the projects by clicking on the project cards below, or find information about the initiative on SPARK.
For any questions, please email: researchcompetitions@rssb.co.uk
Providing data analysis insights into real to-the-second timing patterns of passenger rail services using Machine Learning techniques
Middlesex University and University of Brighton
With support from Southeastern
Predicting and mitigating small fluctuations in station dwell times
University of Southampton
With support from South Western Railway
Anticipating and mitigating reactionary delays
Liverpool John Moores University
With support from Merseyrail
Agent based modelling and visualisation of the causes and consequences of knock-on delays
City, University London and Risk Solutions
With support from Great Western Railway
Join the conversation on Twitter
Other R&I Competitions
Click here to find out more about other RSSB R&I Competitions.