There are a number of gadgets that can give you a count of calories that you’ve burnt, however what if you want to know how many you’ve taken in? That’s where a computer scientist from the University at Buffalo, New York comes in. He has come up with a unique way of tracking the intake of calories; a necklace that determines the calorie intake based upon the sounds that you make while chewing.
The gadget is known as AutoDietary and has been created by Wenyao Xu. It works on the basic principle that different kind of food makes different sound when chewed. The genius behind the gadget is currently working on developing a library that features the biting, grinding and swallowing sounds of various kinds of food. The library shall be incorporated into the app that supports the necklace being developed by Xu in collaboration with researchers at China’s Northeastern University.
Xu says, “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. People either forget or they tend to forget or they want to forget what they eat. You can set up a threshold. For example, I want to eat 2,000 calories a day. Once you have reached that, the threshold will send you a reminder.”
AutoDietary has been shaped like a necklace that fits around the neck snugly and enables a small high-fidelity microphone to record sounds that are made while eating food. These acquired sounds are then sent to the app via Bluetooth where they are checked against the database and respective food is identified. Xu conducted a study along with his team where the gadget was able to identify the food and drink with an accuracy of 85%.
The gadget does have its limitations as of now. For example, it can’t ascertain the difference between foods that are alike in texture and cause similar sounds. It is also not able to cater for dishes that contain more than one ingredient. However, Xu is working on these shortcomings and plans on incorporating a biomonitoring device that would take in blood sugar levels and other measurements for determining the kind of food being eaten. Pretty cool, huh?