Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | 손승우 | - |
dc.date.accessioned | 2024-05-29T06:51:45Z | - |
dc.date.available | 2024-05-29T06:51:45Z | - |
dc.date.issued | 2024-05-22 | - |
dc.identifier.citation | CHAOS SOLITONS & FRACTALS, v. 184, article no. 115032, page. 1-8 | en_US |
dc.identifier.issn | 0960-0779 | en_US |
dc.identifier.uri | https://www.sciencedirect.com/science/article/pii/S0960077924005848 | en_US |
dc.identifier.uri | https://repository.hanyang.ac.kr/handle/20.500.11754/190429 | - |
dc.description.abstract | Predicting temporal patterns across various domains poses significant challenges due to their nuanced and often nonlinear trajectories. To address this challenge, prediction frameworks have been continuously refined, employing data-driven statistical methods, mathematical models, and machine learning. Recently, as one of the challenging systems, shared transport systems such as public bicycles have gained prominence due to urban constraints and environmental concerns. Predicting rental and return patterns at bicycle stations remains a formidable task due to the system’s openness and imbalanced usage patterns across stations. In this study, we propose a deep learning framework to predict rental and return patterns by leveraging cartogram approaches. The cartogram approach facilitates the prediction of demand for newly installed stations with no training data as well as long-period prediction, which has not been achieved before. We apply this method to public bicycle rental-and-return data in Seoul, South Korea, employing a spatial–temporal convolutional graph attention network. Our improved architecture incorporates batch attention and modified node feature updates for better prediction accuracy across different time scales. We demonstrate the effectiveness of our framework in predicting temporal patterns and its potential applications. | en_US |
dc.description.sponsorship | The authors acknowledge Beom Jun Kim for the fruitful discussion. This research was supported by the National Research Foundation (NRF) of Korea through the Grant Numbers. NRF-2023R1A2C1007523 (S.-W.S.), NRF-2021R1C1C1007918 (M.J.L.). This work was also partly supported by Institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government (MSIT) [No. RS-2022-00155885, Artificial Intelligence Convergence Innovation Human Resources Development (Hanyang University ERICA)] (S.-W.S.). We also acknowledge the hospitality at Asia Pacific Center for Theoretical Physics (APCTP). | en_US |
dc.language | en_US | en_US |
dc.publisher | PERGAMON-ELSEVIER SCIENCE LTD | en_US |
dc.relation.ispartofseries | v. 184, article no. 115032;1-8 | - |
dc.subject | Cartogram-enhanced deep learning | en_US |
dc.subject | Forecasting open systems | en_US |
dc.subject | Social dynamics | en_US |
dc.title | Improving demand forecasting in open systems with cartogram-enhanced deep learning | en_US |
dc.type | Article | en_US |
dc.relation.volume | 184 | - |
dc.identifier.doi | 10.1016/j.chaos.2024.115032 | en_US |
dc.relation.page | 115032-115032 | - |
dc.relation.journal | CHAOS SOLITONS & FRACTALS | - |
dc.contributor.googleauthor | Park, Sangjoon | - |
dc.contributor.googleauthor | Kwon, Yongsung | - |
dc.contributor.googleauthor | Soh, Hyungjoon | - |
dc.contributor.googleauthor | Lee, Mi Jin | - |
dc.contributor.googleauthor | Son, Seung-Woo | - |
dc.relation.code | 2024005410 | - |
dc.sector.campus | E | - |
dc.sector.daehak | COLLEGE OF SCIENCE AND CONVERGENCE TECHNOLOGY[E] | - |
dc.sector.department | DEPARTMENT OF APPLIED PHYSICS | - |
dc.identifier.pid | sonswoo | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.