Proceedings on Automation in Medical Engineering
Vol 1 No 1 (2020): Proc AUTOMED
Model-based sensor fusion of multimodal cardiorespiratory signals using an unscented Kalman filter
Main Article Content
Copyright (c) 2020 Proceedings on Automation in Medical Engineering
This work is licensed under a Creative Commons Attribution 4.0 International License.
Based on a model of three coupled oscillators describing the influence of respiration, namely respiratory sinus arrhythmia (RSA), and so-called Mayer waves on the heart rate, an unscented Kalman filter (UKF) is designed to perform sensor fusion of multimodal cardiorespiratory sensor signals. The aim is to implicitly use redundancy between the sensor signals to improve the estimated heart rate while utilizing model knowledge. The effectiveness of the approach is shown by estimations of heart rate variability on synthesized data as well as multimodal patient data, which provide different numbers of sensor channels.