Improving arrival time prediction of Thailand's passenger trains using historical travel times

Pongnumkul, Suporn; Pechprasarn, Thanakij; Kunaseth, Narin; Chaipah, Kornchawal

doi:10.1109/jcsse.2014.6841886

Cited by 21 publications

(14 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ANN, as a basic ML method, learn from historical data to make predictions about future [113]. Peters et al [114] applied ANN to process existing delays abstracted from known operation data to generate delay predictions for depending trains shortly; this method performs well when predicting future (secondary) delays based on existing (primary) delays, and it outperforms the traditional rule-based method.…”

Section: B: Gmmentioning

confidence: 99%

Train Dispatching Management With Data- Driven Approaches: A Comprehensive Review and Appraisal

Wen

Huang

et al. 2019

IEEE Access

View full text Add to dashboard Cite

Train dispatching (TD) is at the forefront of all rail operations that transport passengers or goods. Recent technological advances and the explosion of digital data have introduced data-driven methods (DDMs) in rail operations. In this study, DDMs on the TD problem are briefly explored, focusing on relevant studies on delay distribution, delay propagation, and timetable rescheduling. Data-driven TD methods, including statistical methods (SM), graphical models (GM), and machine learning (ML) methods are reviewed. Then, key issues in establishing different data-driven models for the TD problem are addressed. Subsequently, ML methods are considered to be among the most promising DDMs that lead to innovative TD methods, relying on rich data obtained from train operations. This study emphasizes the potentials for designing new alternatives in the three key fields of interest and provides directions for further research on TD. Future research, including the ML-driven TD and intelligent TD, were discussed in this study. INDEX TERMS Data-driven, delay distribution, delay propagation, timetable rescheduling, train dispatching, machine learning.

show abstract

Section: B: Gmmentioning

confidence: 99%

Train Dispatching Management With Data- Driven Approaches: A Comprehensive Review and Appraisal

Wen

Huang

et al. 2019

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The motivation to use the critical point search algorithm is to identify the primary delay and the flow-on delays [3] [4]. Our proposed algorithm is employed to the time series forecasting models to improve the prediction of the primary train delays, which are the causes of a lot of flow-on delays due to tracing causality.…”

Section: B Critical Point Search Algorithmmentioning

confidence: 99%

“…Pongnumkul et al proposed two algorithms to predict train arrival times at three train stations. The experiment was based on a moving average of historical travel times and the travel times of k-nearest neighbours (k-NN) of the last known arrival time [4]. Oneto et al implemented shallow and deep Extreme Learning Machines (ELM) for forecasting train delays of a large scale network with weather information on the Apache Spark [5].…”

Section: Introductionmentioning

confidence: 99%

Towards a General Prediction System for the Primary Delay in Urban Railways

Zhou

Dong

et al. 2019

2019 IEEE Intelligent Transportation Systems Conference (ITSC)

View full text Add to dashboard Cite

Nowadays a large amount of data is collected from sensor devices across the cyber-physical networks. Accurate and reliable primary delay predictions are essential for rail operations management and planning. However, very few existing 'big data' methods meet the specific needs in railways. We propose a comprehensive and general data-driven Primary Delay Prediction System (PDPS) framework, which combines General Transit Feed Specification (GTFS), Critical Point Search (CPS), and deep learning models to leverage the data fusion. Based on this framework, we have also developed an open source data collection and processing tool that reduces the barrier to the use of the different open data sources. Finally, we demonstrate an advanced deep learning model, the novel ConvLSTM Encoder-Decoder model with CPS for better primary delay predictions.

show abstract

“…Peters et al [4] propose a passenger train delay prediction with neural networks aiming to limit delay propagation with intelligent real-time timetable monitoring. Pongnumkul et al [5] estimate arrival time more accurately with moving average and k-nearest neighbors algorithms than with a simple translation of the current delay. Kecman and Goverde [6] apply linear regression, decision trees and random forests in order to predict running and dwelling times considering current train position and traffic information.…”

Section: Related Workmentioning

confidence: 99%

Estimating Long-Term Delay Risk with Generalized Linear Models

Faverges

Russolillo

Picouleau

et al. 2018

2018 21st International Conference on Intelligent Transportation Systems (ITSC)

View full text Add to dashboard Cite

This paper presents an original methodology to estimate delay risk a few days before operations with generalized linear models. These models represent a given variable with any distribution from the exponential family, allowing to compute for any subject its own probability distribution according to its features. This methodology is applied on small delays (less than 20 minutes) of high-speed trains arriving at a major french station. Several distributions are tested to fit delay data and three scenarios are evaluated: a single GLM with a negative binomial distribution and two two-part models using both a logistic regression as first part to compute the probability of arriving on time, and a second part using a negative binomial or a lognormal distribution to obtain the probabilities associated with positive delay values. This paper also proposes a validation methodology to assess the quality of these probabilistic predictions based on two aspects: calibration and discrimination.

show abstract

Improving arrival time prediction of Thailand's passenger trains using historical travel times

Cited by 21 publications

References 4 publications

Train Dispatching Management With Data- Driven Approaches: A Comprehensive Review and Appraisal

Train Dispatching Management With Data- Driven Approaches: A Comprehensive Review and Appraisal

Towards a General Prediction System for the Primary Delay in Urban Railways

Estimating Long-Term Delay Risk with Generalized Linear Models

Contact Info

Product

Resources

About