Forecasting the Subway Passenger Flow Under Event Occurrences With Social Media
Subway passenger flow prediction is strategically important in metro transit system management. The prediction under event occurrences turns into a very challenging task. In this paper, the authors adopt a new kind of data source—social media—to tackle this challenge. They develop a systematic approach to examine social media activities and sense event occurrences. Their initial analysis demonstrates that there exists a moderate positive correlation between passenger flow and the rates of social media posts. This finding motivates us to develop a novel approach for improved flow forecast. The authors first develop a hashtag-based event detection algorithm. Furthermore, they propose a parametric and convex optimization-based approach, called optimization and prediction with hybrid loss function (OPL), to fuse the linear regression and the results of seasonal autoregressive integrated moving average (SARIMA) model jointly. The OPL hybrid model takes advantage of the unique strengths of linear correlation in social media features and SARIMA model in time series prediction. Experiments on events nearby a subway station show that OPL reports the best forecasting performance compared with other state-of-the-art techniques. In addition, an ensemble model is developed to leverage the weighted results from OPL and support vector machine regression together. As a result, the prediction accuracy and the robustness further increase.
- Record URL:
-
Availability:
- Find a library where document is available. Order URL: http://worldcat.org/oclc/41297384
-
Supplemental Notes:
- Copyright © 2017, IEEE.
-
Authors:
- Ni, Ming
- He, Qing
- Gao, Jing
- Publication Date: 2017-6
Language
- English
Media Info
- Media Type: Digital/other
- Features: Figures; References; Tables;
- Pagination: pp 1623-1632
-
Serial:
- IEEE Transactions on Intelligent Transportation Systems
- Volume: 18
- Issue Number: 6
- Publisher: Institute of Electrical and Electronics Engineers (IEEE)
- ISSN: 1524-9050
- Serial URL: http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=6979
Subject/Index Terms
- TRT Terms: Algorithms; Data mining; Mathematical prediction; Social media; Special events; Subways; Traffic flow; Traffic forecasting; Transit riders; Travel demand
- Subject Areas: Data and Information Technology; Passenger Transportation; Planning and Forecasting; Public Transportation;
Filing Info
- Accession Number: 01639426
- Record Type: Publication
- Files: TLIB, TRIS
- Created Date: Jun 1 2017 4:37PM