If you’ve read articles about fitness trackers, they were probably written by compulsive workout junkies who compare them for how well they can track those zillion mile bicycle rides or marathon training runs. Well, I’m not just one of them. But the technology in sleep and fitness trackers is quite amazing and well worth writing about.
And yes, they can provide health advantages for ordinary people who get exercise as time permits. Trackers, as with a lot of the digital health motion, have come quite a distance within the last couple of years. From the easy and not-very-accurate step counters of a couple of years ago, they have progressed into devices that can monitor your heartrate, sleep, and other essential signs. However, they’re far from perfect, so they can provide an undeserved impression of accuracy also. The simplest form of counting steps is to use the data from the device’s accelerometer and Inertial Measurement Unit (IMU) to identify rhythmic motions that are consistent with the back-and-forth movement that typically goes along with walking or running.
By using the data from both receptors, the device attempts to filter false positives. After the device has a step count number, then it multiplies that by an estimate of your stride to determine how far you’ve walked or run. Worst case it runs on the generic guess at the stride, but typically you’re able to enter your height to give it a far more accurate starting place, or enter your stride length directly even.
- 477 U.S. at 248
- Some issues with GPS monitoring and calories burned
- High fructose corn syrup (in manufactured products and sodas)
- “Bad fat” = Trans Fat
- What other health factors should I have regarding surgery for weight reduction
Some devices go a bit further and will calibrate your stride by evaluating GPS results using its quotes. Because consumer GPS has limited accuracy, this process requires several minutes of traveling at a constant speed usually. Some calculate separate stride lengths for walking and running also. Until recently, that meant remembering to tell the tracker when you started a hike or run. But many newer devices do a good job of auto-detecting when you start some form of exercise and classifying it appropriately. From having owned various fitness trackers over the years, it’s clear that counting steps and stairs is as much of an art as a research at this point.
Even when using several current state-of-the-art trackers at the same time, their step counts can differ by as much as 15 percent. Typical wrist trackers and watches don’t have the control power to run a lot of advanced AI-based analytics to help tidy up the info, either. Devices with altimeters often also enable you to count how many plane tickets of stairs (or equal) you’ve climbed. Here, too, sensor fusion is required, so that altitude gained while generating or soaring doesn’t get acknowledged to your fitness (a shame for tech journalists who spend lots of time on airplanes). Monitoring climbing can become more of the crapshoot even.
For example, my Fitbit Versa regularly reports dozens of flooring climbed while I’m playing golf – even though each floor is meant to stand for 10 ft of altitude gained while walking or operating. In contrast, my Huawei Band 3 Pro isn’t fooled. However, during the day the Versa does a better job keeping up with my running up and down stairs. Much like so many areas of technology, digital health has been improved by using AI vastly. For example, instead of writing long sequences of complicated code predicated on physical models to count steps, modern trackers rely on neural networks that use machine understanding how to determine strides.
Similarly, rather than relying on human being analysis of rest data for each patient, trackers have systems that are trained on huge amounts of human-labeled test data. As a total result, they can categorize the sensor information from users into not only sleeping or awake, but even the specific type of rest.