Fusion of Physiological and Behavioural Signals on SPD Manifolds with Application to Stress and Pain Detection
| Autor: | Yujin Wu, Mohamed Daoudi, Ali Amad, Laurent Sparrow, Fabien D'Hondt |
|---|---|
| Přispěvatelé: | Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 (CRIStAL), Centrale Lille-Université de Lille-Centre National de la Recherche Scientifique (CNRS), Ecole nationale supérieure Mines-Télécom Lille Douai (IMT Nord Europe), Institut Mines-Télécom [Paris] (IMT), Lille Neurosciences & Cognition - U 1172 (LilNCog), Institut National de la Santé et de la Recherche Médicale (INSERM)-Université de Lille-Centre Hospitalier Régional Universitaire [Lille] (CHRU Lille), Laboratoire Sciences Cognitives et Sciences Affectives - UMR 9193 (SCALab), Université de Lille-Centre National de la Recherche Scientifique (CNRS), DAOUDI, Mohamed, Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL], Ecole nationale supérieure Mines-Télécom Lille Douai [IMT Nord Europe], Lille Neurosciences & Cognition - U 1172 [LilNCog], Laboratoire Sciences Cognitives et Sciences Affectives - UMR 9193 [SCALab] |
| Jazyk: | angličtina |
| Rok vydání: | 2022 |
| Předmět: |
FOS: Computer and information sciences
covariance matrix Computer Science - Machine Learning Computer Science - Artificial Intelligence multimodal fusion stress detection pain detection symmetric positive definite manifold [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV] [SCCO] Cognitive science Machine Learning (cs.LG) [SCCO]Cognitive science [INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV] Artificial Intelligence (cs.AI) |
| Zdroj: | International Conference on Systems, Man, and Cybernetics International Conference on Systems, Man, and Cybernetics, Oct 2022, Prague, Czech Republic |
| Popis: | 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-of-the-art results for stress and pain detection tasks. International Conference on Systems, Man, and Cybernetics, IEEE SMC 2022, October 9-12, 2022 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|