mm-MuRe: mmWave-Based Multi-Subject Respiration Monitoring via End-to-End Deep Learning

Abstract

This study presents mm-MuRe, a novel method to perform multi-subject contactless respiration waveform monitoring by processing raw multiple-input-multiple-output mmWave radar data with an end-to-end deep neural network. The traditional vital signs monitoring signal processing scheme for mmWave radar involves analog or digital beamforming, human subject localization, phase variation extraction, filtering, and rate or biomarker analysis. This traditional method has many downsides, including sensitivity to selected beamforming weights and over-reliance on phase variation. To avoid these drawbacks, mm-MuRe (for MM-wave based MUlti-subject REspiration monitoring) is developed to improve reconstruction accuracy and reliability by taking in unprocessed 60 GHz MIMO FMCW radar data and outputting respiratory waveforms of interest, effectively mimicking an adaptive beamformer and bypassing the need for traditional localization and vital signs extraction techniques. Extensive testing across scenarios differing in range, angle, environment, and subject count demonstrates the network's robust performance, with an average cosine similarity exceeding 0.95. Results are compared to two baseline methods and show more than a 10% average improvement in waveform reconstruction accuracy across single and multi-subject scenarios. Coupled with a rapid inference time of 8.57 ms on a 10 s window of data, mm-MuRe shows promise for potential deployment to efficient and accurate near-real-time contactless respiration monitoring systems.