Presentation | 2021-12-10 Prediction of Train Delays at Stations Using Multiple Convolutional Neural Networks with Actual Operation Data Tsukasa Takahashi, Takumi Fukuda, Sei Takahashi, Hideo Nakamura, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | In the metropolitan area, railroads are frequently delayed due to high congestion rates during rush hours, and many measures are being taken to mitigate delays. A train operation simulator has been developed as a means of evaluating the effects of countermeasures, but this simulator evaluates the effects before and after countermeasures by applying known delays. The simulator evaluates the effect before and after the countermeasure by giving a known delay. However, the delay generated by the countermeasure changes according to the change of running conditions, so the generation of station generated delay is essential for the evaluation. In this study, we aimed to improve the prediction accuracy by using a large amount of train operation data to predict the station generated delay. As a result, the highest prediction accuracy of 75.9% was obtained. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Delay resolution / Delay improvement / Train delay / Operation management / Machine learning / Convolutional neural network |
Paper # | DC2021-61 |
Date of Issue | 2021-12-03 (DC) |
Conference Information | |
Committee | DC |
---|---|
Conference Date | 2021/12/10(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | Hiroshi Takahashi(Ehime Univ.) |
Vice Chair | Tatsuhiro Tsuchiya(Osaka Univ.) |
Secretary | Tatsuhiro Tsuchiya(Nihon Univ.) |
Assistant |
Paper Information | |
Registration To | Technical Committee on Dependable Computing |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Prediction of Train Delays at Stations Using Multiple Convolutional Neural Networks with Actual Operation Data |
Sub Title (in English) | |
Keyword(1) | Delay resolution |
Keyword(2) | Delay improvement |
Keyword(3) | Train delay |
Keyword(4) | Operation management |
Keyword(5) | Machine learning |
Keyword(6) | Convolutional neural network |
1st Author's Name | Tsukasa Takahashi |
1st Author's Affiliation | Nihon University(Nihon Univ.) |
2nd Author's Name | Takumi Fukuda |
2nd Author's Affiliation | Nihon University(Nihon Univ.) |
3rd Author's Name | Sei Takahashi |
3rd Author's Affiliation | Nihon University(Nihon Univ.) |
4th Author's Name | Hideo Nakamura |
4th Author's Affiliation | The University of Tokyo(UTokyo) |
Date | 2021-12-10 |
Paper # | DC2021-61 |
Volume (vol) | vol.121 |
Number (no) | DC-293 |
Page | pp.pp.34-37(DC), |
#Pages | 4 |
Date of Issue | 2021-12-03 (DC) |