Swallow monitoring through apnea detection in breathing signal

This paper presents the concepts, design, and algorithms for a wearable swallow monitoring system. Swallow monitoring can be used for assessing a person´s overall food and drink intake habits as well as other swallow related disorders. The system works based on the key observation that a person´s otherwise continuous breathing process is interrupted by a short apnea when she or he swallows as a part of food intake process. Using a wearable chest-belt, we detect swallows by detecting apneas extracted from breathing signal captured by the chest-belt. A matched filter based template matching framework is developed for swallow detection. A number of matched filter template design, both static and iterative, are developed for high-accuracy swallow detection.