Graph Convolutional Neural Networks for Human Activity Purpose Imputation from GPS-based Trajectory Data

Abstract

Automatic location tracking of people has recently become a viable source for \nmobility and movement data. Such data are used in a wide range of applications, \nfrom city and transport planning to individual recommendations and schedule \noptimization. For many of these uses, it is of high interest to know why a person \nvisited at a given location at a certain point in time. We use multiple personalized \ngraphs to model human mobility behavior and to embed a large variety of spatiotemporal information and structure in the graphs’ weights and connections. Taking \nthese graphs as input for graph convolutional neural networks (GCNs) allows us to \nbuild models that can exploit the structural information inherent in human mobility. \nWe use GPS travel survey data to build person specific mobility graphs and use \nGCNs to predict the purpose of a user’s visit at a certain location. Our results show \nthat GCNs are suitable to exploit the structure embedded in the mobility graphs.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 9 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.