Neuromorphic approach for breathing rate monitoring using data produced by FMCW radar

The paper introduces a neuromorphic computational approach for breathing rate monitoring of a single person observed using a Frequency-Modulated Continuous Wave radar. The architecture, aimed at implementation in analog hardware to ensure high energy efficiency and to provide system operation longevity, comprises two main functional modules. The first one is a data preprocessing unit aimed at the extraction of information relevant to the analysis objective, whereas the second one is a pre-trained recurrent neural regressor, which analyzes sequences of incoming samples and estimates the breathing rate. To ensure compatibility with neural processing and to achieve simplicity of underlying resources, several solutions were proposed for the data preprocessing module, which provides range-wise space segmentation, selection of a bin of interest (comprising the dominant motion activity), and delivery of data to regressor inputs. To implement these functions, we introduce an appropriate chirp frequency modulation scheme, apply a neuromorphic filtering procedure and use a Winner-Takes-All network for extracting information from the bin of interest. The architecture has been experimentally verified using a dataset of indoor recordings supplied with reference data from a Zephyr BioHarness device. We show that the proposed architecture is capable of making correct breathing rate estimates while being feasible for analog implementation. The mean squared regression error with respect to the Zephyr-produced reference values is approximately 3.3 breaths per minute (with a deviation of ±0:27 in the 95% confidence interval) and the estimates are produced by a recurrent, GRU-based neural regressor, with a total of only 147 parameters.