OBJECTIVE COUGH-SOUND RECOGNITION AS A BIOMARKER FOR AERIAL FACTORS

Abstract

The relation between air quality and respiratory health and comfort in humans and animals has been widelyshown. In general, a state of respiratory discomfort in everyday indoor and outdoor life results in an increase in audibleacoustic symptoms. The general concept of sound analysis as an objective, contactless, and non-invasive biomarker for aerialstressors was studied on free-field registered cough sounds of 12 Belgian Landrace piglets. A citric acid-induced coughsound-recognition algorithm with a recognition percentage of 95% was applied to cough sounds registered in the presenceof distinct types of aerial factors: irritating gas (ammonia), respirable particles (dust), and climate (temperature). Therecognition percentage for all aerial factors exceeded 90% and averaged 94%. Therefore, it was concluded that soundanalysis could provide an effective biomarker for all three types of aerial factors. The generality of the biomarker is speculatedto arise from the common mechanism involved in protective cough, which will stand as long as no physical changes (e.g.,growth, disease) to the state of the respiratory system occur. The results suggest that sound analysis as a biomarker of therespiratory state may be integrated into room or personalized air ventilation control to improve respiratory comfort ofanimals.