[B-19] Healthcare and Medical Information Communication Technology

10:45 AM - 11:00 AM JST(1:45 AM - 2:00 AM UTC)Candidate for Academic Incentive AwardCareer Explorer

[B-19-05] Non-contact Heart Rate Estimation Using Transformer-Based Deep Learning under Low SNR Conditions in a Low-Power 60 GHz MIMO-FMCW Sensor

◎△YUTO IMADA¹, Takeshi Toda² (1. Graduate School of Science & Technology, NIHON UNIVERSITY, 2. College of Science and Technology, NIHON UNIVERSITY)

Keywords:

Healthcare,Heart Rate,Sensor,Deep Learning,Millimeter-Wave Sensor

In our previous work, we performed heart rate estimation using a CNN-based 1D ResNet with a low-power 60 GHz-band FMCW sensor; however, the estimation accuracy was limited. In this paper, we report on our investigation into contactless heart rate estimation using Transformer-based deep learning with a Masked Autoencoder (MAE) that incorporates time-series information.