01764137

Component

https://annualmeeting.myt...nlineProgram/Details/15713

In metropolitan cities, train (e.g., subway) delays are among the most complained events by the public communities. Different from existing researches, the authors present a hybrid deep learning solution for predicting multi-step train delays in this paper. Firstly, the authors apply a real entropy to measure the time series regularity, and they find an approximate 80.5% potential predictability on train delays. The authors' solution uses Long Short-Term Memory (LSTM) and Critical Point Search (CPS) to generate the forecasts for train delays. The LSTM tackle the tasks for long-term predictions of running time and dwell time. The CPS utilizes the predicted values with a nominal timetable to identify the future primary and secondary delays based on the delay causes, run-time delay and dwell time delay. Finally, the authors demonstrate the performance of the standard LSTM and its variants applied in a novel architecture. The results show that the variants can improve upon the standard LSTM significantly when compared through predicting time steps of dwell time feature. The experiments also show historical trend volatility with a lot of irregularities, which prompts further studies needed to tackle them.

This paper was sponsored by TRB committee AED50 Standing Committee on Artificial Intelligence and Advanced Computing Applications.

TRBAM-21-01183

English

18p

2021

Transportation Research Board 100th Annual Meeting

Digital/other

Figures; References; Tables

Delays; Dwell time; Predictive models; Railroad traffic; Running time

Operations and Traffic Management; Planning and Forecasting; Railroads

Transportation Research Board Annual Meeting 2021 Paper #TRBAM-21-01183

TRIS, TRB, ATRI

Dec 23 2020 11:20AM