Abstract
Remote and continuous biometric signal monitoring has become increasingly crucial for the prompt diagnosis of physiological disorders. However, traditional contact sensors might pose the risk of virus spread and cause discomfort, thereby impeding the continuous monitoring process. Furthermore, the enhancement of diagnostic performance using deep neural networks necessitates the use of large models, which could be a burden when developing embedded edge devices. Thus, we propose a multitask learning model to estimate the remote photoplethysmogram (PPG) and respiratory rate simultaneously based on facial videos using complex-valued neural networks. The RGB channel images are obtained from a region of interest of the facial video streams and a complex-numbered dataset is constructed. The multitask learning model designed for the complex domain can yield a small network architecture by reducing the number of parameters, which is advantageous for small embedded devices. Using a public dataset of face video streams from multiple participants, the proposed multitask learning model could simultaneously learn the remote PPG and respiratory rate with higher performance and a smaller structure compared with conventional real-valued neural networks. These results validate the potential of the proposed model for the accurate and efficient remote monitoring of physiological disorders.