Titre :

Fusion of Physiological and Behavioural Signals on SPD Manifolds with Application to Stress and Pain Detection

Auteur(s) :

Wu, Yujin [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Daoudi, Mohamed [Auteur]
Ecole nationale supérieure Mines-Télécom Lille Douai [IMT Nord Europe]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Amad, Ali [Auteur]
Lille Neurosciences & Cognition - U 1172 [LilNCog]
Sparrow, Laurent [Auteur]
Laboratoire Sciences Cognitives et Sciences Affectives - UMR 9193 [SCALab]
Fabien, D [Auteur]
Lille Neurosciences & Cognition - U 1172 [LilNCog]

Titre de la manifestation scientifique :

International Conference on Systems, Man, and Cybernetics

Ville :

Prague

Pays :

République tchèque

Date de début de la manifestation scientifique :

2022-10-09

Mot(s)-clé(s) en anglais :

stress detection
pain detection
multimodal fusion
covariance matrix
symmetric positive definite manifold

Discipline(s) HAL :

Informatique [cs]/Vision par ordinateur et reconnaissance de formes [cs.CV]
Sciences cognitives

Résumé en anglais : [en]

Existing multimodal stress/pain recognition approaches generally extract features from different modalities independently and thus ignore cross-modality correlations. This paper proposes a novel geometric framework for ...
Lire la suite >Existing multimodal stress/pain recognition approaches generally extract features from different modalities independently and thus ignore cross-modality correlations. This paper proposes a novel geometric framework for multimodal stress/pain detection utilizing Symmetric Positive Definite (SPD) matrices as a representation that incorporates the correlation relationship of physiological and behavioural signals from covariance and cross-covariance. Considering the non-linearity of the Riemannian manifold of SPD matrices, well-known machine learning techniques are not suited to classify these matrices. Therefore, a tangent space mapping method is adopted to map the derived SPD matrix sequences to the vector sequences in the tangent space where the LSTM-based network can be applied for classification. The proposed framework has been evaluated on two public multimodal datasets, achieving both the state-ofthe-art results for stress and pain detection tasks.Lire moins >

Langue :

Anglais

Comité de lecture :

Oui

Audience :

Internationale

Vulgarisation :

Non

Collections :

• Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189

Source :

Harvested from HAL