Efficient frequency-based classification of respiratory movements

Lung diseases are mainly associated with respiration. Detecting the breath and classifying breathing movements such as inhale and exhale has settled importance in many biomedical research areas. To this end, monitoring the breathing movements for lung cancer patients tends to remain one of the breath detection applications which has received much attention. A novel method is proposed in this paper that detects and classifies breathing movements. In our technique, we employ the Mel-Frequency Cepstral Coefficients (MFCCs) to the acoustic signal of respiration captured using a microphone. We classify the movements using the 6^th MFCC order which carries important classification information. Experimental results on a number of individuals verify our proposed classification methodology. This work is intended to indirectly assist lung cancer patients regulate their breath through virtual therapy.