Pattern Ensembling for Spatial Trajectory Reconstruction

TL;DR

This paper introduces a pattern ensembling method that leverages similar local trajectory patterns to robustly reconstruct missing or unreliable geolocation data, improving the accuracy of mobility analysis.

Contribution

It presents a novel probabilistic ensembling approach for trajectory reconstruction that outperforms traditional interpolation methods, especially for complex and extended missing segments.

Findings

Effective reconstruction of missing trajectory segments

Improved accuracy over traditional interpolation methods

Applicable to complex and extended trajectory gaps

Abstract

Digital sensing provides an unprecedented opportunity to assess and understand mobility. However, incompleteness, missing information, possible inaccuracies, and temporal heterogeneity in the geolocation data can undermine its applicability. As mobility patterns are often repeated, we propose a method to use similar trajectory patterns from the local vicinity and probabilistically ensemble them to robustly reconstruct missing or unreliable observations. We evaluate the proposed approach in comparison with traditional functional trajectory interpolation using a case of sea vessel trajectory data provided by The Automatic Identification System (AIS). By effectively leveraging the similarities in real-world trajectories, our pattern ensembling method helps to reconstruct missing trajectory segments of extended length and complex geometry. It can be used for locating mobile objects when temporary unobserved as well as for creating an evenly sampled trajectory interpolation useful for further trajectory mining.