Time–frequency fusion learning for photoplethysmography biometric recognition

Photoplethysmography (PPG) signal is a novel biometric trait related to the identity of people; many time‐ and frequency‐domain methods for PPG biometric recognition have been proposed. However, the existing domain methods for PPG biometric recognition only consider a single domain or the feature‐level fusion of time and frequency domains, without considering the exploration of the fusion correlations of the time and frequency domains. The authors propose a time–frequency fusion for a PPG biometric recognition method with collective matrix factorisation (TFCMF) that leverages collective matrix factorisation to learn a shared latent semantic space by exploring the fusion correlations of the time and frequency domains. In addition, the authors utilise the ℓ2,1 norm to constrain the reconstruction error and shared matrix, which can alleviate the influence of noise and intra‐class variation, and ensure the robustness of learnt semantic space. Experiments demonstrate that TFCMF has better recognition performance than current state‐of‐the‐art methods for PPG biometric recognition.