2019 IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting | 2019
Mapping Lung Water Signal Distribution on Human Chest and Predition of Lung Water Content
Abstract
Measuring lung water change is invaluable for monitoring patients with heart failure and pulmonary diseases and assessing their responses to the treatment. Sensors for such measurement have been developed in Hawaii Advanced Wireless Technologies Institute (HAWTI) and clinical trials have been carried out. In this paper, we use numerical simulations to obtain the signals received by the sensors as a function of lung water content and sensor locations on the human torso. The data are interpolated to obtain a finer distribution of signals on the chest. The higher resolution data are used to train the support vector regression (SVR) machine to establish a prediction model for lung water content as a function of received signal and location of the sensors. The interpolation and SVR methods can save significant simulation time and will be used for building a database for lung water prediction for various human torsos.