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

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.

[1]  Dit-Yan Yeung,et al.  Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting , 2015, NIPS.

[2]  Rob M.P. Goverde,et al.  Recent applications of big data analytics in railway transportation systems: A survey , 2018 .

[3]  Davide Anguita,et al.  Dynamic Delay Predictions for Large-Scale Railway Networks: Deep and Shallow Extreme Learning Machines Tuned via Thresholdout , 2017, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[4]  David M Levinson,et al.  Developing a Comprehensive U.S. Transit Accessibility Database , 2015 .

[5]  Andrew Guthrie,et al.  Accessibility Scenario Analysis of a Hypothetical Future Transit Network: Social Equity Implications of a General Transit Feed Specification–Based Sketch Planning Tool , 2017 .

[6]  M. Walton,et al.  Artificial Intelligence in Transportation Information for Application , 2007 .

[7]  Masoud Yaghini,et al.  Railway Passenger Train Delay Prediction via Neural Network Model , 2013 .

[8]  Jürgen Schmidhuber,et al.  LSTM: A Search Space Odyssey , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[9]  Nate Wessel,et al.  Discovering the space–time dimensions of schedule padding and delay from GTFS and real-time transit data , 2017, J. Geogr. Syst..

[10]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[11]  Jürgen Schmidhuber,et al.  Applying LSTM to Time Series Predictable through Time-Window Approaches , 2000, ICANN.

[12]  Paul Schonfeld,et al.  Real-time energy-saving metro train rescheduling with primary delay identification , 2018, PloS one.

[13]  Kornchawal Chaipah,et al.  Improving arrival time prediction of Thailand's passenger trains using historical travel times , 2014, 2014 11th International Joint Conference on Computer Science and Software Engineering (JCSSE).

[14]  David M Levinson,et al.  Modeling the commute mode share of transit using continuous accessibility to jobs , 2015 .

[15]  Lovekesh Vig,et al.  Long Short Term Memory Networks for Anomaly Detection in Time Series , 2015, ESANN.

[16]  Yann Dauphin,et al.  Convolutional Sequence to Sequence Learning , 2017, ICML.

[17]  Norio Tomii,et al.  Identification of causes of delays in urban railways , 2012 .

[18]  James Wong,et al.  Leveraging the General Transit Feed Specification for Efficient Transit Analysis , 2013 .

[19]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[20]  Davide Anguita,et al.  Train Delay Prediction Systems: A Big Data Analytics Perspective , 2017, Big Data Res..

[21]  Davide Anguita,et al.  Delay Prediction System for Large-Scale Railway Networks Based on Big Data Analytics , 2016, INNS Conference on Big Data.