Title :

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

Author(s) :

Wu, Yujin [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189
Daoudi, Mohamed [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189
Amad, Ali [Auteur]
Lille Neurosciences & Cognition (LilNCog) - U 1172
Sparrow, Laurent [Auteur]
Sciences Cognitives et Sciences Affectives (SCALab) - UMR 9193
D'Hondt, Fabien [Auteur]
Lille Neurosciences & Cognition (LilNCog) - U 1172

Conference title :

IEEE International Conference on Systems, Man, and Cybernetics (SMC)

City :

Prague

Country :

République tchèque

Start date of the conference :

2022-10-09

English keyword(s) :

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

HAL domain(s) :

Sciences cognitives

English abstract : [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 ...
Show more >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.Show less >

Language :

Anglais

Audience :

Internationale

Popular science :

Non

Administrative institution(s) :

Université de Lille
CNRS
CHU Lille

Collections :

• Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189
• Lille Neurosciences & Cognition (LilNCog) - U 1172
• Sciences Cognitives et Sciences Affectives (SCALab) - UMR 9193

Research team(s) :

Équipe Langage

Submission date :

2024-01-17T15:08:43Z
2024-02-13T10:00:32Z
2024-02-13T10:42:15Z