An accurate portable calorie counter
Engineers at Stanford University have developed a new calorie burn measurement system that is small, inexpensive, and accurate. Moreover, people can do it themselves. While smartwatches and smartphones tend to lag around 40 to 80 percent when it comes to counting calories burned during an activity, this system displays an average error of 13%.
Go to the website to watch the video.
“We built a compact system that we evaluated with a diverse group of participants to represent the American population and found that it works very well, with about a third of the error of smartwatches,” said Patrick Slade, graduate student in mechanical engineering at Stanford. who is the main author of an article on this work, published July 13 to Natural communications.
A crucial part of this research was understanding a fundamental flaw in other portable calorie counters: they rely on wrist movement or heart rate, although neither are particularly indicative of energy expenditure. (Consider how a cup of coffee can increase the heart rate.) The researchers hypothesized that the movement of the legs would be more revealing – and their experiments confirmed this idea.
There are laboratory systems that can accurately estimate the amount of energy a person burns during physical activity by measuring the rate of carbon dioxide and oxygen exchange in the respiratory air. Such setups are used to assess health and athletic performance, but they involve bulky, uncomfortable equipment, and can be expensive. This new portable system only requires two small sensors on the leg, a battery, and a portable microcontroller (a small computer), and costs around $ 100 to manufacture. The list of components and coded to make the system are both available.
“This is a big step forward because, so far, it takes two to six minutes and a gas mask to accurately estimate how much energy a person is burning,” said Scott Delp, Professor James H. Clark at the School of Engineering, who is a co-author of the article. “With Patrick’s new tool, we can estimate how much energy is burned with each step as an Olympic athlete races to the finish line to get a measure of what is fueling their peak performance. We can also calculate the energy expended by a patient recovering from heart surgery to better manage their exercise.
Look to the legs
The way people burn calories is complicated, but the researchers had a hunch that sensors on the legs would be a simple way to better understand this process.
“One problem with traditional smartwatches is that they only get information about your wrist movement and heart rate,” said Mykel Kochenderfer, associate professor of aeronautics and astronautics at Stanford who is co-author of the article. “The fact that Patrick’s device has a lower error rate makes sense because it senses the movement of your legs and most of your energy is spent by your legs.”
The system designed by the researchers is intentionally simple. It consists of two small sensors – one on the thigh and one on the shaft of a leg – managed by a microcontroller on the hip, which could easily be replaced by a smartphone. These sensors are called “inertial measurement units” and measure the acceleration and rotation of the leg as it moves. They are purposely lightweight, portable, and inexpensive so that they can be easily incorporated into different forms, including clothing, such as smart pants.
To test the system against similar technologies, the researchers asked study participants to wear it while also wearing two smartwatches and a heart rate monitor. With all of these sensors attached, participants performed a variety of activities, including varying speeds of walking, running, cycling, climbing stairs, and transitioning between walking and running. When all of the portable devices were compared to the calorie burn measurements captured by a lab system, the researchers found their leg-based system to be the most accurate.
By further testing the system on more than a dozen participants of different ages and weights, the researchers gathered a wealth of data that Slade used to further refine the machine learning model that calculates estimates of calories burned. This model takes the information about the movement of the legs from the sensors and calculates – using what it has learned from previous data – how much energy the user is burning at any given moment. And, while today’s state-of-the-art systems require about six minutes of data from a person hooked up to a mask in a lab, this self-service alternative can run with just a few seconds of activity.
“A lot of the steps you do each day take place in short periods of 20 seconds or less,” said Slade, who mentioned household chores as an example of short-lived activity that is often overlooked. “Being able to capture these brief activities or these dynamic changes between activities is really difficult and no other system can do it right now. “
Simplicity and affordability were important to this team, as was the provision of design, as they hope this technology can help people understand and take care of their health.
“We get everything open source in the hope that people will use it and use it and make products that can improve people’s lives,” Kochenderfer said.
They also believe that the simplicity, affordability and portability of this system could support better health policy and new avenues of human performance research. The research group led by Steve collins, associate professor of mechanical engineering and lead author of this article, is already using a similar system to study energy expended with portable robotic systems that improve performance.
“One of the most exciting things is that we can keep up with dynamically changing activities, and this accurate information will allow us to provide better policies for recommending how people should exercise or manage their weight,” Slade said.
“This opens up a whole new set of research studies we can do on human performance,” said Delp, who is also a professor of bioengineering and mechanical engineering. “How much energy you burn when you walk, when you run, when you exercise on a bicycle – all of these things are fundamental. When we have a new tool like this, it opens a new door to discovering new things about human performance.