Fusion of Physiological and Behavioural Signals on SPD Manifolds with Application to Stress and Pain Detection
This work addresses stress and pain detection for healthcare applications, representing an incremental improvement by integrating existing methods in a novel way.
The paper tackled the problem of multimodal stress and pain detection by proposing a geometric framework using Symmetric Positive Definite matrices to incorporate cross-modality correlations, achieving state-of-the-art results on two public datasets.
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.