Using doppler radar classify respiration by MFCC

Abstract

Respiration rate is an important parameter to indicate whether the respiratory system is normal or abnormal. In general, respiration rate can be calculated and counted the number of inhale and exhale when a person is in resting condition in 1 minute. There are many methods that can evaluate respiratory data from a various biomedical signal such as Electrocardiogram (ECG) Signals, Blood Pressure (BP) and Photo-plethysmography (PPG). But it can not be used in all condition like sleeping all night comfortably. According to all of the previous methods, they are all contact devices. Therefore, this paper studies non-contact respiration measured by using doppler radar to receive the signal data, then use MFCC to extract the feature of the signal and feed the feature to DCNN. In the result, we got 85% of accuracy.