Continuous monitoring of eating habits could be useful in preventing lifestyle diseases such as metabolic syndrome. Conventional methods consist of self-reporting and calculating mastication frequency based on the myoelectric potential of the masseter muscle. Both these methods are significant burdens for the user. We developed a non-invasive, wearable sensing system that can record eating habits over a long period of time in daily life. Our sensing system is composed of two bone conduction microphones placed in the ears that send internal body sound data to a portable IC recorder. Applying frequency spectrum analysis on the collected sound data, we could not only count the number of mastications during eating, but also accurately differentiate between eating, drinking, and speaking activities. This information can be used to evaluate the regularity of meals. Moreover, we were able to analyze sound features to classify the types of foods eaten by food texture.

Continuous monitoring of eating habits could be useful in preventing lifestyle diseases such as the metabolic syndrome. Conventional methods consist in self-reporting and mastication frequency calculation from myoelectric potential of the masseter muscle, both resulting in a significant burden for the user. We developed a non-invasive wearable sensing system that can record eating habits over a long period of time in daily life. Our original sensing system is composed by a bone conduction microphone placed in the ears, from which sound data are collected to a portable IC recorder. Applying frequency spectrum analysis on collected sound data, we could not only count the mastication number during eating, but also accurately differentiate eating, drinking, and speaking activities, which can be used to evaluate the regularity of meals. Moreover, using clustering of sound spectra, we found it is possible to classify types of foods eaten regarding their texture.

No abstract

No abstract