Apnea Detection based on Respiratory Signal Classification

Obstructive sleep apnea (OSA) is the most common form of different types of sleep-related breathing disorders. It is characterized by repetitive cessations of respiratory flow during sleep, which occurs due to a collapse of the upper respiratory airway. OSA is majorly undiagnosed due to the inconvenient Polysomnography (PSG) testing procedure at sleep labs. This paper introduces an automated approach towards identifying the presence of sleep apnea based on the acoustic signal of respiration. The characterization of breathing sound was carried by Voice Activity Detection (VAD) algorithm, which is used to measure the energy of the acoustic respiratory signal during breath and breath hold. The performance of our classification algorithm is tested on real respiratory signals and the experimental results show that the VAD is useful as a predictive tool for the segmentation of breath into sound and silence segments. Moreover, the system we developed can be used as a basis for future development of a tool for OSA screening.