short-paper

Bike-Share Demand Prediction using Attention based Sequence to Sequence and Conditional Variational AutoEncoder

Authors:

Tomohiro Mimura,

Shin Ishiguro,

Satoshi Kawasaki,

Yusuke FukazawaAuthors Info & Claims

PredictGIS'19: Proceedings of the 3rd ACM SIGSPATIAL International Workshop on Prediction of Human Mobility

Pages 41 - 44

https://doi.org/10.1145/3356995.3364543

Published: 05 November 2019 Publication History

Get Access

Abstract

In recent years, bicycle sharing services (bike-shares) have been established worldwide. One important aspect of bike-share management is to periodically rebalance the positions of the available bikes. Because the bike demand varies by and over time, the number of bikes at each bike-port tends to become unbalanced. To efficiently rebalance a bike-share system, it is essential to predicting the number of bikes in each bike-port. In this paper, we propose a method to predicting bike demand and the number of bike pickups and drop offs at each bike-port every hour, up to 24 hours in advance. To predict demand, we used a time series generation model based on the Variational Autoencoders model and the Attention based Sequence to Sequence learning model. We named this method "Conditional Variational Autoencoders considering Partial Future data" (CVAE-PF). In the experiment, our proposed method showed higher prediction accuracy in root mean square error (RMSE) compared to conventional methods.

References

[1]

Pierre Hulot, Daniel Aloise, and Sanjay Dominik Jena. Towards station-level demand prediction for effective rebalancing in bike-sharing systems. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 378--386. ACM, 2018.

Digital Library

Google Scholar

[2]

Yu chun Yin, Chi-Shuen Lee, and Yu-Po Wong. Demand prediction of bicycle sharing systems. 2014.

Google Scholar

[3]

Po-Chuan Chen, He-Yen Hsieh, Xanno Kharis Sigalingging, Yan-Ru Chen, and Jenq-Shiou Leu. Prediction of station level demand in a bike sharing system using recurrent neural networks. 2017 IEEE 85th Vehicular Technology Conference (VTC Spring), pp. 1--5, 2017.

Crossref

Google Scholar

[4]

Yexin Li, Yu Zheng, and Qiang Yang. Dynamic bike reposition: A spatiotemporal reinforcement learning approach. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 1724--1733. ACM, 2018.

Digital Library

Google Scholar

[5]

Shuai Wang, Tian He, Desheng Zhang, Yuanchao Shu, Yunhuai Liu, Yu Gu, Cong Liu, Haengju Lee, and Sang H Son. Bravo: Improving the rebalancing operation in bike sharing with rebalancing range prediction. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, Vol. 2, No. 1, p. 44, 2018.

Google Scholar

[6]

Petar Mrazovic, Josep-Lluís Larriba-Pey, and Mihhail Matskin. A deep learning approach for estimating inventory rebalancing demand in bicycle sharing systems. 2018 IEEE 42nd Annual Computer Software and Applications Conference (COMPSAC), Vol. 02, pp. 110--115, 2018.

Crossref

Google Scholar

[7]

Biao Zhang, Deyi Xiong, Jinsong Su, Hong Duan, and Min Zhang. Variational neural machine translation. arXiv preprint arXiv:1605.07869, 2016.

Google Scholar

[8]

Diederik P Kingma and Max Welling. Auto-encoding variational bayes. 12 2014.

Google Scholar

[9]

Shin Ishiguro, Satoshi Kawasaki, and Yusuke Fukazawa. Taxi demand forecast using real-time population generated from cellular networks. In Proceedings of the 2018 ACM International Joint Conference and 2018 International Symposium on Pervasive and Ubiquitous Computing and Wearable Computers, pp. 1024--1032. ACM, 2018.

Digital Library

Google Scholar

[10]

Makita Naoki, Kimura Masakazu, Terada Masayuki, Motonari Kobayashi, and Oyabu Yuki. Can mobile phone network data be used to estimate small area population? Statistical Journal of the IAOS, Vol. 29(3), pp. 223--232, Oct 2013.

Google Scholar

Cited By

View all

Suzuki MFuruta SFukazawa Y(2023)Personalized human mobility prediction for HuMob challengeProceedings of the 1st International Workshop on the Human Mobility Prediction Challenge10.1145/3615894.3628501(22-25)Online publication date: 13-Nov-2023
https://dl.acm.org/doi/10.1145/3615894.3628501
Akatsuka HTerada M(2023)Application of Kalman Filter to Large-scale Geospatial Data: Modeling Population DynamicsACM Transactions on Spatial Algorithms and Systems10.1145/35636929:1(1-29)Online publication date: 12-Jan-2023
https://dl.acm.org/doi/10.1145/3563692
Ghaffar AHyland MSaphores J(2023)Meta-analysis of shared micromobility ridership determinantsTransportation Research Part D: Transport and Environment10.1016/j.trd.2023.103847121(103847)Online publication date: Aug-2023
https://doi.org/10.1016/j.trd.2023.103847
Show More Cited By

Index Terms

Bike-Share Demand Prediction using Attention based Sequence to Sequence and Conditional Variational AutoEncoder
1. Computing methodologies
  1. Machine learning
    1. Learning paradigms
      1. Supervised learning
        Supervised learning by regression
2. Theory of computation
  1. Theory and algorithms for application domains
    1. Machine learning theory
      1. Models of learning

Recommendations

Vehicle Trajectory Prediction Using Intention-based Conditional Variational Autoencoder
2019 IEEE Intelligent Transportation Systems Conference (ITSC)
Vehicle trajectory prediction has been an active research area in autonomous driving. In a real traffic scene, autonomous vehicle needs to predict future motion of surrounding vehicles before motion planning to improve driving safety and efficiency. In ...
Autonomous Vehicle Path Prediction Using Conditional Variational Autoencoder Networks
Advances in Knowledge Discovery and Data Mining
Abstract
Path prediction of autonomous vehicles is an essential requirement under any given traffic scenario. Trajectory of several agent vehicles in the vicinity of ego vehicle, at least for a short future, is needed to be predicted in order to decide ...
SeqVAE: Sequence variational autoencoder with policy gradient
Abstract
In the paper, we propose a variant of Variational Autoencoder (VAE) for sequence generation task, called SeqVAE, which is a combination of recurrent VAE and policy gradient in reinforcement learning. The goal of SeqVAE is to reduce the deviation ...

Comments

Information & Contributors

Information

Published In

PredictGIS'19: Proceedings of the 3rd ACM SIGSPATIAL International Workshop on Prediction of Human Mobility

November 2019

81 pages

ISBN:9781450369640

DOI:10.1145/3356995

Editors:
Satish V. Ukkusuri
Purdue University, IN, USA
,
Kaoru Sezaki
University of Tokyo, Japan
,
Takahiro Yabe
Purdue University, IN, USA
,
Kota Tsubouchi
Yahoo Japan Corporation, Tokyo, Japan

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 05 November 2019

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Short-paper
Research
Refereed limited

Conference

SIGSPATIAL '19

Sponsor:

SIGSPATIAL

SIGSPATIAL '19: 27th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems

November 5, 2019

IL, Chicago, USA

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

9
Total Citations
View Citations
336
Total Downloads

Downloads (Last 12 months)30
Downloads (Last 6 weeks)2

Reflects downloads up to 10 Nov 2024

Other Metrics

View Author Metrics

Citations

Cited By

View all

Suzuki MFuruta SFukazawa Y(2023)Personalized human mobility prediction for HuMob challengeProceedings of the 1st International Workshop on the Human Mobility Prediction Challenge10.1145/3615894.3628501(22-25)Online publication date: 13-Nov-2023
https://dl.acm.org/doi/10.1145/3615894.3628501
Akatsuka HTerada M(2023)Application of Kalman Filter to Large-scale Geospatial Data: Modeling Population DynamicsACM Transactions on Spatial Algorithms and Systems10.1145/35636929:1(1-29)Online publication date: 12-Jan-2023
https://dl.acm.org/doi/10.1145/3563692
Ghaffar AHyland MSaphores J(2023)Meta-analysis of shared micromobility ridership determinantsTransportation Research Part D: Transport and Environment10.1016/j.trd.2023.103847121(103847)Online publication date: Aug-2023
https://doi.org/10.1016/j.trd.2023.103847
Tsushima HSviridova NIkeguchi T(2022)Tabu search for solving multiple-vehicle bike sharing system routing problem with real port distribution2022 International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME)10.1109/ICECCME55909.2022.9988144(1-6)Online publication date: 16-Nov-2022
https://doi.org/10.1109/ICECCME55909.2022.9988144
Shinoda KYamada MTakanashi MTsuboi THasegawa DFukazawa YKimoto M(2021)Prediction of Restaurant Sales during High Demand States Using Population Statistical Data2021 Thirteenth International Conference on Mobile Computing and Ubiquitous Network (ICMU)10.23919/ICMU50196.2021.9638955(1-6)Online publication date: 17-Nov-2021
https://doi.org/10.23919/ICMU50196.2021.9638955
Chen JLi KLi KYu PZeng Z(2021)Dynamic Bicycle Dispatching of Dockless Public Bicycle-sharing Systems Using Multi-objective Reinforcement LearningACM Transactions on Cyber-Physical Systems10.1145/34476235:4(1-24)Online publication date: 22-Sep-2021
https://dl.acm.org/doi/10.1145/3447623
Akatsuka HTerada M(2020)Application of Kalman Filter to Large-Scale Geospatial DataProceedings of the 28th International Conference on Advances in Geographic Information Systems10.1145/3397536.3422223(530-539)Online publication date: 3-Nov-2020
https://dl.acm.org/doi/10.1145/3397536.3422223
Ukkusuri SSezaki KYabe TTsubouchi K(2020)PredictGIS 2019 workshop report: Held in conjunction with ACM SIGSPATIAL 2019SIGSPATIAL Special10.1145/3383653.338366611:3(34-37)Online publication date: 13-Feb-2020
https://dl.acm.org/doi/10.1145/3383653.3383666
Wang YWang CLing YYokoyama KWu HFang Y(2020)Leveraging an Efficient and Semantic Location Embedding to Seek New Ports of Bike Share Services2020 IEEE International Conference on Big Data (Big Data)10.1109/BigData50022.2020.9378326(1273-1282)Online publication date: 10-Dec-2020
https://doi.org/10.1109/BigData50022.2020.9378326

View Options

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Cited By

Index Terms

Recommendations

Vehicle Trajectory Prediction Using Intention-based Conditional Variational Autoencoder

Autonomous Vehicle Path Prediction Using Conditional Variational Autoencoder Networks

SeqVAE: Sequence variational autoencoder with policy gradient

Comments

Published In

Sponsors

Publisher

Publication History

Permissions

Check for updates

Author Tags

Qualifiers

Conference

Other Metrics

Article Metrics

Other Metrics

Cited By

Login options

Full Access

PDF

eReader

Abstract

References

Cited By

Index Terms

Recommendations

Vehicle Trajectory Prediction Using Intention-based Conditional Variational Autoencoder

Autonomous Vehicle Path Prediction Using Conditional Variational Autoencoder Networks

SeqVAE: Sequence variational autoencoder with policy gradient

Comments

Information

Published In

Sponsors

Publisher

Publication History

Permissions

Check for updates

Author Tags

Qualifiers

Conference

Contributors

Other Metrics

Bibliometrics

Article Metrics

Other Metrics

Citations

Cited By

Get Access

Login options

Full Access

View options

PDF

eReader

Figures

Other

Share

Share this Publication link

Share on social media

Affiliations