Proposal and Evaluation of Prediction of Pavement Rutting Depth by Recurrent Neural Network

Tomoyuki Okuda, Kouyu Suzuki, Naohiko Kohtake

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper describes a method of predicting the rutting depth by introducing Adam and dropout into MLP of neural network and GRU of recurrent neural net that can handle time series data. We built a model to predict the current rutting depth from the past rutting 3 years ago. We compared RMSE with the multiple regression model (MLR), which is most frequently used as a regression problem for the time variation of rutting depth. As a result, RMSE decreased in the order of MLR, MLP, GRU. The difference between GRU and RMSE of MLR was about 10%.

Original languageEnglish
Title of host publicationProceedings - 2017 6th IIAI International Congress on Advanced Applied Informatics, IIAI-AAI 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1053-1054
Number of pages2
ISBN (Electronic)9781538606216
DOIs
Publication statusPublished - 2017 Nov 15
Event6th IIAI International Congress on Advanced Applied Informatics, IIAI-AAI 2017 - Hamamatsu, Shizuoka, Japan
Duration: 2017 Jul 9 → …

Other

Other6th IIAI International Congress on Advanced Applied Informatics, IIAI-AAI 2017
CountryJapan
CityHamamatsu, Shizuoka
Period17/7/9 → …

Fingerprint

Recurrent neural networks
Pavements
Neural networks
Time series
Regression model
Evaluation
Pavement
Multiple regression
Prediction

Keywords

  • Machine learning
  • Pavement condition survey
  • Recurrent neural network
  • Road management

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Computer Science Applications
  • Information Systems
  • Information Systems and Management

Cite this

Okuda, T., Suzuki, K., & Kohtake, N. (2017). Proposal and Evaluation of Prediction of Pavement Rutting Depth by Recurrent Neural Network. In Proceedings - 2017 6th IIAI International Congress on Advanced Applied Informatics, IIAI-AAI 2017 (pp. 1053-1054). [8113413] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IIAI-AAI.2017.177

Proposal and Evaluation of Prediction of Pavement Rutting Depth by Recurrent Neural Network. / Okuda, Tomoyuki; Suzuki, Kouyu; Kohtake, Naohiko.

Proceedings - 2017 6th IIAI International Congress on Advanced Applied Informatics, IIAI-AAI 2017. Institute of Electrical and Electronics Engineers Inc., 2017. p. 1053-1054 8113413.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Okuda, T, Suzuki, K & Kohtake, N 2017, Proposal and Evaluation of Prediction of Pavement Rutting Depth by Recurrent Neural Network. in Proceedings - 2017 6th IIAI International Congress on Advanced Applied Informatics, IIAI-AAI 2017., 8113413, Institute of Electrical and Electronics Engineers Inc., pp. 1053-1054, 6th IIAI International Congress on Advanced Applied Informatics, IIAI-AAI 2017, Hamamatsu, Shizuoka, Japan, 17/7/9. https://doi.org/10.1109/IIAI-AAI.2017.177
Okuda T, Suzuki K, Kohtake N. Proposal and Evaluation of Prediction of Pavement Rutting Depth by Recurrent Neural Network. In Proceedings - 2017 6th IIAI International Congress on Advanced Applied Informatics, IIAI-AAI 2017. Institute of Electrical and Electronics Engineers Inc. 2017. p. 1053-1054. 8113413 https://doi.org/10.1109/IIAI-AAI.2017.177
Okuda, Tomoyuki ; Suzuki, Kouyu ; Kohtake, Naohiko. / Proposal and Evaluation of Prediction of Pavement Rutting Depth by Recurrent Neural Network. Proceedings - 2017 6th IIAI International Congress on Advanced Applied Informatics, IIAI-AAI 2017. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 1053-1054
@inproceedings{ac91b0c472db450f9acff862df5fdda4,
title = "Proposal and Evaluation of Prediction of Pavement Rutting Depth by Recurrent Neural Network",
abstract = "This paper describes a method of predicting the rutting depth by introducing Adam and dropout into MLP of neural network and GRU of recurrent neural net that can handle time series data. We built a model to predict the current rutting depth from the past rutting 3 years ago. We compared RMSE with the multiple regression model (MLR), which is most frequently used as a regression problem for the time variation of rutting depth. As a result, RMSE decreased in the order of MLR, MLP, GRU. The difference between GRU and RMSE of MLR was about 10{\%}.",
keywords = "Machine learning, Pavement condition survey, Recurrent neural network, Road management",
author = "Tomoyuki Okuda and Kouyu Suzuki and Naohiko Kohtake",
year = "2017",
month = "11",
day = "15",
doi = "10.1109/IIAI-AAI.2017.177",
language = "English",
pages = "1053--1054",
booktitle = "Proceedings - 2017 6th IIAI International Congress on Advanced Applied Informatics, IIAI-AAI 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Proposal and Evaluation of Prediction of Pavement Rutting Depth by Recurrent Neural Network

AU - Okuda, Tomoyuki

AU - Suzuki, Kouyu

AU - Kohtake, Naohiko

PY - 2017/11/15

Y1 - 2017/11/15

N2 - This paper describes a method of predicting the rutting depth by introducing Adam and dropout into MLP of neural network and GRU of recurrent neural net that can handle time series data. We built a model to predict the current rutting depth from the past rutting 3 years ago. We compared RMSE with the multiple regression model (MLR), which is most frequently used as a regression problem for the time variation of rutting depth. As a result, RMSE decreased in the order of MLR, MLP, GRU. The difference between GRU and RMSE of MLR was about 10%.

AB - This paper describes a method of predicting the rutting depth by introducing Adam and dropout into MLP of neural network and GRU of recurrent neural net that can handle time series data. We built a model to predict the current rutting depth from the past rutting 3 years ago. We compared RMSE with the multiple regression model (MLR), which is most frequently used as a regression problem for the time variation of rutting depth. As a result, RMSE decreased in the order of MLR, MLP, GRU. The difference between GRU and RMSE of MLR was about 10%.

KW - Machine learning

KW - Pavement condition survey

KW - Recurrent neural network

KW - Road management

UR - http://www.scopus.com/inward/record.url?scp=85040550726&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85040550726&partnerID=8YFLogxK

U2 - 10.1109/IIAI-AAI.2017.177

DO - 10.1109/IIAI-AAI.2017.177

M3 - Conference contribution

SP - 1053

EP - 1054

BT - Proceedings - 2017 6th IIAI International Congress on Advanced Applied Informatics, IIAI-AAI 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -