An anomaly detection-based dynamic OD prediction framework for urban networks

J. Liu, F. Zheng, H.J. van Zuylen, J. Li, J. Luo

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

Abstract

The dynamic origin-destination (OD) information is crucial for traffic operations and control. This paper presents a dynamic traffic demand prediction framework based on an anomaly detection algorithm. The Principal Component Analysis (PCA) method is applied to extract main demand patterns which are used to detect the abnormal conditions. The proposed approach can select prediction methods (parametric or nonparametric) automatically based on the pattern detection results. Both simulation and field observed Automatic Number Plate Recognition (ANPR) data are used to verify the proposed approach where the Kalman filter model and the K-nearest neighbor model are chosen as the basic prediction methods. The results show that the prediction framework can effectively reduce the noise of a single prediction model particularly in the abnormal conditions and provide more accurate and reliable prediction results.
Original languageEnglish
Title of host publication2020 Forum on Integrated and Sustainable Transportation Systems (FISTS)
Subtitle of host publicationNovember 3-5, 2020, Delft - The Netherlands
PublisherIEEE
Pages135-141
Number of pages7
ISBN (Electronic)978-1-7281-9503-2
DOIs
Publication statusPublished - 2020
Event2020 IEEE Forum on Integrated and Sustainable Transportation Systems - Delft , Netherlands
Duration: 3 Nov 20205 Nov 2020
https://forum-ists2020.org/about/

Conference

Conference2020 IEEE Forum on Integrated and Sustainable Transportation Systems
Abbreviated titleFISTS
CountryNetherlands
CityDelft
Period3/11/205/11/20
Internet address

Keywords

  • Gaussian kernel
  • OD prediction
  • anomaly detection
  • parametric and non-parametric methods

Fingerprint

Dive into the research topics of 'An anomaly detection-based dynamic OD prediction framework for urban networks'. Together they form a unique fingerprint.

Cite this