loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Paper Unlock

Authors: Chih-Jung Hsu and Hung-Hsuan Chen

Affiliation: Computer Science and Information Engineering, National Central University, Taoyuan, Taiwan

Keyword(s): LSTM, Multi-head Attention, Deep Learning, Residual Connection, Taxi Demand.

Abstract: This paper presents a simple yet effective framework to accurately predict the taxi demands of different regions in a city in the near future. This framework is based on a deep-learning structure with residual connections in the LSTM layers and the attention mechanism. We found that adding residuals accelerates optimization and that adding the attention mechanism makes the model better predict the taxi demands, especially when the demand fluctuates greatly in the peak hours and off-peak hours. We conducted extensive experiments by comparing the proposed models to the time-series model (ARIMA), traditional supervised learning model (ridge regression), strong machine learning model that won many Kaggle competitions (Gradient Boosted Decision Tree implemented in the XGBoost library), and deep learning models (LSTM and DMVST-Net) on two real and open-source datasets. Experimental results show that the proposed models outperform the baselines for most cases. We believe the greatest improv ement comes from the attention mechanism, which helps distinguish the demands in the peak hours and off-peak hours. Additionally, the proposed model runs 10% to 40%-times faster than the other deep-learning-based models. We applied the models to participate in a taxi demand prediction challenge and won second place out of hundreds of teams. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 3.145.163.58

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Hsu, C. and Chen, H. (2020). Taxi Demand Prediction based on LSTM with Residuals and Multi-head Attention. In Proceedings of the 6th International Conference on Vehicle Technology and Intelligent Transport Systems - VEHITS; ISBN 978-989-758-419-0; ISSN 2184-495X, SciTePress, pages 268-275. DOI: 10.5220/0009562002680275

@conference{vehits20,
author={Chih{-}Jung Hsu. and Hung{-}Hsuan Chen.},
title={Taxi Demand Prediction based on LSTM with Residuals and Multi-head Attention},
booktitle={Proceedings of the 6th International Conference on Vehicle Technology and Intelligent Transport Systems - VEHITS},
year={2020},
pages={268-275},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0009562002680275},
isbn={978-989-758-419-0},
issn={2184-495X},
}

TY - CONF

JO - Proceedings of the 6th International Conference on Vehicle Technology and Intelligent Transport Systems - VEHITS
TI - Taxi Demand Prediction based on LSTM with Residuals and Multi-head Attention
SN - 978-989-758-419-0
IS - 2184-495X
AU - Hsu, C.
AU - Chen, H.
PY - 2020
SP - 268
EP - 275
DO - 10.5220/0009562002680275
PB - SciTePress

- Science and Technology Publications, Lda.
RESOURCES

Proceedings

Papers

Authors

Ontology

CONTACTS

Science and Technology Publications, Lda
Avenida de S. Francisco Xavier, Lote 7 Cv. C,
2900-616 Setúbal, Portugal.

Phone: +351 265 520 185 (National fixed network call)
Fax: +351 265 520 186
Email: info@scitepress.org

EXTERNAL LINKS

PRIMORIS

INSTICC

SCITEVENTS

CROSSREF

PROCEEDINGS SUBMITTED FOR INDEXATION BY:

dblp

Ei Compendex

SCOPUS

Semantic Scholar

Google Scholar

Microsoft Academic