Non-Contact Breath Rate Classification Using SVM Model and mmWave Radar Sensor Data
This work addresses breath rate monitoring for healthcare applications, but it is incremental as it applies existing SVM methods to new radar data.
The paper tackled the problem of classifying normal and abnormal breath rates using a non-contact system based on FMCW radar and SVM models, achieving a best accuracy of 95% with a quadratic polynomial kernel.
This work presents the use of frequency modulated continuous wave (FMCW) radar technology combined with a machine learning model to differentiate between normal and abnormal breath rates. The proposed system non-contactly collects data using FMCW radar, which depends on breath rates. Various support vector machine kernels are used to classify the observed data into normal and abnormal states. Prolonged experiments show good accuracy in breath rate classification, confirming the model's efficacy. The best accuracy is 95 percent with the smallest number of support vectors in the case of the quadratic polynomial kernel.