A survey on deep learning-based techniques for cuffless blood pressure estimation-Part II: attention mechanisms and transfer learning

This paper constitutes the second part of the survey on deep learning-based techniques for, cuffless blood pressure (BP) estimation, focusing specifically on attention mechanisms and transfer learning. Attention mechanisms enhance model performance by adaptively focusing on the most informative physiological features, while transfer learning addresses the challenge of data scarcity by leveraging knowledge from related domains. Building upon the foundation established in the first-part survey, we provide a review of deep learning methodologies applied in this domain. Furthermore, based on an analysis of existing research, we outline promising future research directions to advance these technologies toward clinically viable and robust implementations.