A framework for predicting trajectories using global and local information

William Groves, Ernesto Nunes, Maria L Gini

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Scopus citations

Abstract

We propose a novel framework for predicting the paths of vehicles that move on a road network. The framework leverages global and local patterns in spatio-temporal data. From a large corpus of GPS trajectories, we predict the subsequent path of an in-progress vehicle trajectory using only spatio-temporal features from the data. Our framework consists of three components: (1) a component that abstracts GPS location data into a graph at the neighborhood or street level, (2) a component that generates policies obtained from the graph data, and (3) a component that predicts the subsequent path of an in-progress trajectory. Hierarchical clustering is used to construct the city graph, where the clusters facilitate a compact representation of the trajectory data to make processing large data sets tractable and efficient. We propose four alternative policy generation algorithms: a frequency-based algorithm (FreqCount), a correlation-based algorithm (EigenStrat), a spectral clusteringbased algorithm (LapStrat), and a Markov Chain-based algorithm (MCStrat). The algorithms explore either global patterns (Freq-Count and EigenStrat) or local patterns (MCStrat) in the data, with the exception of LapStrat which explores both. We present an analysis of the performance of the alternative prediction algorithms using a large real-world taxi data set.

Original languageEnglish (US)
Title of host publicationProceedings of the 11th ACM Conference on Computing Frontiers, CF 2014
PublisherAssociation for Computing Machinery
ISBN (Print)9781450328708
DOIs
StatePublished - 2014
Event11th ACM International Conference on Computing Frontiers, CF 2014 - Cagliari, Italy
Duration: May 20 2014May 22 2014

Publication series

NameProceedings of the 11th ACM Conference on Computing Frontiers, CF 2014

Other

Other11th ACM International Conference on Computing Frontiers, CF 2014
CountryItaly
CityCagliari
Period5/20/145/22/14

Keywords

  • Big data
  • GPS
  • Large-scale data
  • Route prediction
  • Smart cities
  • Spatio-temporal analysis
  • Urban mobility

Fingerprint Dive into the research topics of 'A framework for predicting trajectories using global and local information'. Together they form a unique fingerprint.

Cite this