Non-Contact Breath Rate Classification Using SVM Model and mmWave Radar Sensor Data

This work presents the use of frequency-modulated continuous wave (FMCW) radar technology combined with a machine learning (ML) model to differentiate between Normal and Abnormal Breath Rates (BR). The recommended system non-contactly collects data (or signals) using FMCW radar, which depends on BR. Various Support Vector Machine (SVM) kernels are used to classify the observed data into Normal and Abnormal states. Prolonged experiments show good accuracy in BR classification, confirming the model's efficacy. The best accuracy is 95% with the smallest number of support vectors in the case of the quadratic polynomial kernel.