Carrots and cookies not only taste different. They make distinct sounds when you chew them.
This may seem trivial, but it is helping create a library that catalogs the unique sounds that foods make as we bite, grind, and swallow them.
The library will be part of a software package supporting AutoDietary, a food-tracking necklace similar to Fitbit and other wearable devices. Only instead of tracking burned calories, it will monitor caloric intake—or what we eat.
“There is no shortage of wearable devices that tell us how many calories we burn, but creating a device that reliably measures caloric intake isn’t so easy,” says Wenyao Xu, assistant professor of computer science at the University at Buffalo’s School of Engineering and Applied Sciences.
The device wraps around the back of the neck like a choker necklace. A tiny high-fidelity microphone—about the size of a zipper pull—records the sounds made during chewing and as the food is swallowed. The data is then sent to a smartphone via Bluetooth, where food types are recognized.
For the small study, 12 test subjects, male and female, ages 13 to 49, were given water and six types of food: apples, carrots, potato chips, cookies, peanuts, and walnuts. AutoDietary was able to accurately identify the correct food and drink 85 percent of the time.
“Each food, as it’s chewed, has its own voice,” says Xu, who notes that the device could someday help people suffering from diabetes, obesity, bowel disorders, and other ailments by helping them to better monitor their food intake and, improve how they manage their conditions.
Xu plans future studies to build upon his library by testing different foods and recording the sounds they make. He also plans to refine the algorithms used to differentiate the foods to improve AutoDietary’s ability to recognize what’s being eaten.
While promising, a wearable necklace that measures sound has limitations when used alone. For example, it cannot differentiate similar foods such as frosted corn flakes and regular corn flakes. It also can’t distinguish the ingredients of complex foods such as soup or chili.
To address these limitations, Xu is planning a biomonitoring device that would complement AutoDietary. The device is underdevelopment but it would be activated once the necklace recognizes that the user is eating a general category of food.
The biomonitor would then determine the nutritional value of the food via blood sugar levels and other measurements. The system then gathers and presents this information on a smartphone, while providing suggestions on healthier eating.
The beauty of the system, Xu says, is that the user isn’t overwhelmed by a continuous stream of information. The system is only active as food is consumed and immediately after.
Researchers at Northeastern University in China are coauthors of the study that is published in IEEE Sensors Journal.