Capturing and explaining trajectory singularities using composite signal neural networks

Dubois, Hippolyte, Le Callet, Patrick, Hornberger, Michael ORCID: https://orcid.org/0000-0002-2214-3788, Spiers, Hugo J. and Coutrot, Antoine (2021) Capturing and explaining trajectory singularities using composite signal neural networks. In: 28th European Signal Processing Conference, EUSIPCO 2020 - Proceedings. European Signal Processing Conference . European Signal Processing Conference, EUSIPCO, NLD, pp. 1422-1426. ISBN 9789082797053

[thumbnail of Capturing_and_Explaining_Trajectory_Singularities_using_Composite_Signal_Neural_Networks]
Preview
PDF (Capturing_and_Explaining_Trajectory_Singularities_using_Composite_Signal_Neural_Networks) - Accepted Version
Download (3MB) | Preview

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.

Item Type: Book Section
Additional Information: Funding Information: ACKNOWLEDGMENT This project was partially funded by the RFI Atlantic 2020 and RFI Ouest Industrie Creative programs of the French region Pays de la Loire
Uncontrolled Keywords: cnn,explainability,gcnn,graph signal processing,neural network,pattern analysis,trajectory,signal processing,electrical and electronic engineering ,/dk/atira/pure/subjectarea/asjc/1700/1711
Faculty \ School: Faculty of Medicine and Health Sciences > Norwich Medical School
Related URLs:
Depositing User: LivePure Connector
Date Deposited: 20 Jul 2022 09:30
Last Modified: 01 Oct 2022 19:30
URI: https://ueaeprints.uea.ac.uk/id/eprint/86703
DOI: 10.23919/Eusipco47968.2020.9287403

Actions (login required)

View Item View Item