Capturing and explaining trajectory singularities using composite signal neural networks

Hippolyte Dubois, Patrick Le Callet, Michael Hornberger, Hugo J. Spiers, Antoine Coutrot

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

1 Citation (Scopus)

Abstract

Spatial trajectories are ubiquitous and complex signals. Their analysis is crucial in many research fields, from urban planning to neuroscience. Several approaches have been proposed to cluster trajectories. They rely on hand-crafted features, which struggle to capture the spatio-temporal complexity of the signal, or on Artificial Neural Networks (ANNs) which can be more efficient but less interpretable. In this paper we present a novel ANN architecture designed to capture the spatio-temporal patterns characteristic of a set of trajectories, while taking into account the demographics of the navigators. Hence, our model extracts markers linked to both behaviour and demographics. We propose a composite signal analyser (CompSNN) combining three simple ANN modules. Each of these modules uses different signal representations of the trajectory while remaining interpretable. Our CompSNN performs significantly better than its modules taken in isolation and allows to visualise which parts of the signal were most useful to discriminate the trajectories.

Original languageEnglish
Title of host publication28th European Signal Processing Conference, EUSIPCO 2020 - Proceedings
PublisherEuropean Signal Processing Conference, EUSIPCO
Pages1422-1426
Number of pages5
ISBN (Electronic)9789082797053
DOIs
Publication statusPublished - 24 Jan 2021
Event28th European Signal Processing Conference, EUSIPCO 2020 - Amsterdam, Netherlands
Duration: 24 Aug 202028 Aug 2020

Publication series

NameEuropean Signal Processing Conference
Volume2021-January
ISSN (Print)2219-5491

Conference

Conference28th European Signal Processing Conference, EUSIPCO 2020
Country/TerritoryNetherlands
CityAmsterdam
Period24/08/2028/08/20

Keywords

  • Cnn
  • Explainability
  • Gcnn
  • Graph signal processing
  • Neural network
  • Pattern analysis
  • Trajectory

Cite this