Fusion of Physiological and Behavioural Signals on SPD Manifolds with Application to Stress and Pain Detection. Wu, Y., Daoudi, M., Amad, A., Sparrow, L., & D'Hondt, F. Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics, 2022-October:2949-2955, Institute of Electrical and Electronics Engineers Inc., 2022.
Paper doi abstract bibtex 1 download 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.
@article{Wu2022,
abstract = {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.},
author = {Yujin Wu and Mohamed Daoudi and Ali Amad and Laurent Sparrow and Fabien D'Hondt},
doi = {10.1109/SMC53654.2022.9945260},
isbn = {9781665452588},
issn = {1062922X},
journal = {Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics},
keywords = {covariance matrix,multimodal fusion,pain detection,stress detection,symmetric positive definite manifold.},
pages = {2949-2955},
publisher = {Institute of Electrical and Electronics Engineers Inc.},
title = {Fusion of Physiological and Behavioural Signals on SPD Manifolds with Application to Stress and Pain Detection},
volume = {2022-October},
url = {https://ieeexplore.ieee.org/document/9945260},
year = {2022}
}
Downloads: 1
{"_id":"GwcDRZfgXHH58KXMx","bibbaseid":"wu-daoudi-amad-sparrow-dhondt-fusionofphysiologicalandbehaviouralsignalsonspdmanifoldswithapplicationtostressandpaindetection-2022","author_short":["Wu, Y.","Daoudi, M.","Amad, A.","Sparrow, L.","D'Hondt, F."],"bibdata":{"bibtype":"article","type":"article","abstract":"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.","author":[{"firstnames":["Yujin"],"propositions":[],"lastnames":["Wu"],"suffixes":[]},{"firstnames":["Mohamed"],"propositions":[],"lastnames":["Daoudi"],"suffixes":[]},{"firstnames":["Ali"],"propositions":[],"lastnames":["Amad"],"suffixes":[]},{"firstnames":["Laurent"],"propositions":[],"lastnames":["Sparrow"],"suffixes":[]},{"firstnames":["Fabien"],"propositions":[],"lastnames":["D'Hondt"],"suffixes":[]}],"doi":"10.1109/SMC53654.2022.9945260","isbn":"9781665452588","issn":"1062922X","journal":"Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics","keywords":"covariance matrix,multimodal fusion,pain detection,stress detection,symmetric positive definite manifold.","pages":"2949-2955","publisher":"Institute of Electrical and Electronics Engineers Inc.","title":"Fusion of Physiological and Behavioural Signals on SPD Manifolds with Application to Stress and Pain Detection","volume":"2022-October","url":"https://ieeexplore.ieee.org/document/9945260","year":"2022","bibtex":"@article{Wu2022,\n abstract = {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.},\n author = {Yujin Wu and Mohamed Daoudi and Ali Amad and Laurent Sparrow and Fabien D'Hondt},\n doi = {10.1109/SMC53654.2022.9945260},\n isbn = {9781665452588},\n issn = {1062922X},\n journal = {Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics},\n keywords = {covariance matrix,multimodal fusion,pain detection,stress detection,symmetric positive definite manifold.},\n pages = {2949-2955},\n publisher = {Institute of Electrical and Electronics Engineers Inc.},\n title = {Fusion of Physiological and Behavioural Signals on SPD Manifolds with Application to Stress and Pain Detection},\n volume = {2022-October},\n url = {https://ieeexplore.ieee.org/document/9945260},\n year = {2022}\n}\n","author_short":["Wu, Y.","Daoudi, M.","Amad, A.","Sparrow, L.","D'Hondt, F."],"key":"Wu2022","id":"Wu2022","bibbaseid":"wu-daoudi-amad-sparrow-dhondt-fusionofphysiologicalandbehaviouralsignalsonspdmanifoldswithapplicationtostressandpaindetection-2022","role":"author","urls":{"Paper":"https://ieeexplore.ieee.org/document/9945260"},"keyword":["covariance matrix","multimodal fusion","pain detection","stress detection","symmetric positive definite manifold."],"metadata":{"authorlinks":{}},"downloads":1},"bibtype":"article","biburl":"https://nextcloud.univ-lille.fr/index.php/s/pPGQfg4JXoHoBE6/download/BIB_FDH.bib","dataSources":["F636tzkHrc3ThLeTQ","ATRkM2TLoR6tFHedP","Th2hJq5hckp8eADcs","3GW57JhuLNkW5xJr9","rhSPLqkAQ2ghKGndw","GsDYmPYw6fNzpugKw","Qu7EfK3RCh2QokW4g","eootQuRYbh8hH74Mu"],"keywords":["covariance matrix","multimodal fusion","pain detection","stress detection","symmetric positive definite manifold."],"search_terms":["fusion","physiological","behavioural","signals","spd","manifolds","application","stress","pain","detection","wu","daoudi","amad","sparrow","d'hondt"],"title":"Fusion of Physiological and Behavioural Signals on SPD Manifolds with Application to Stress and Pain Detection","year":2022,"downloads":1}