Identifying Elevated and Shallow Respiratory Rate using mmWave Radar leveraging Machine Learning Algorithms

This paper presents remote monitoring of patients using non-invasive RF sensing to detect normal respiratory rates and abnormal breathing rates such as elevated patterns where person experiences heavy breathing and shallow rates where minimal air is inhaled and exhaled. In this context, a millimeter wave, frequency modulated continuous wave radar operating at 60 GHz is used to acquire data. A total of 10 volunteers participated in the experimental campaign and 300 observations were obtained represented in terms of micro-Doppler signatures. Time domain statistical features were obtained from features such as bandwidth and centroid of the corresponding signatures. Support vector machine (SVM), k-nearest neighbor (KNN) and decision tree algorithms were used to evaluate overall performance of the proposed model. It was observed that the SVM classifier provided best classification accuracy (96%).