Friday, 23 September 2016

Fitness Trackers - How they work.

In recent years, the popularity of fitness trackers has increased exponentially. These pieces of wearable technology claim to be able to monitor a persons activity levels throughout the day, by identifying exactly what it is the wearer is doing at all times, whether it be sleeping, walking or exercising. But how so these trackers receive this data, and how do they interpret these findings accurately?
In order to fully understand how these trackers work, we must first understand the technology behind them. Fitness trackers contain an accelerometer, an electromechanical device used to track both static and dynamic acceleration forces (the intensity and direction of movement). It looks like a simple circuit, however it consists of many different components, including the piezoelectric effect and the capacitance sensor. 

The piezoelectric effect is the most common form of accelerometer and uses microscopic crystal structures that become stressed due to accelerative forces. These crystals create a voltage from the stress, and the accelerometer interprets the voltage to determine velocity and orientation.
The capacitance accelerometer senses changes in capacitance (ability to store an electric charge) between microstructures located next to the device. If an accelerative force moves one of these structures, the capacitance will change and the accelerometer will translate that capacitance to voltage for interpretation.
Typical accelerometers are made up of multiple axes, two to determine most two-dimensional movement with the option of a third for 3D positioning. The sensitivity of these devices is quite high as they’re intended to measure even very minute shifts in acceleration. The more sensitive the accelerometer, the more easily it can measure acceleration.
A regular accelerometer within the fitness tracker consists of two electrically charged plates, with a small counter balance in between. Whenever the wearer, and therefore the tracker, is still the counterbalance remains steady in the middle. However, once the wearer begins to move the counterbalance moves between the two plates and the sensors begin to register movement.

Once the tracker receives data about the wearers movements across the 3D axes, it then needs to interpret this to establish what particular activity these movements represent. One axis represents the body moving up and down (z axis), one left and right (y axis) and the third forwards and backwards (x axis). By combining this information the tracker is able to detect patterns of movement, and establish which activity the wearer is currently engaged in.

For example, if the wearer is cycling then the reading on the x axis would be high as the wearer leans forward, but the z axis would be relatively continuous. However if the wearer were to be running, the high reading on the x axis would be accompanied by a rapidly changing reading on the z axis as the runner moves onwards. Software also interprets the frequency of these movements, in order to distinguish between similar activities such as walking and running.

One of the greatest advantages of this technology is that they do not rely on the wearers location, so the technology records data exactly the same whether the wearer is running along the street or on a treadmill. 


(1) Ravi N, Dandekar N, Mysore P, Littman ML. Activity recognition from accelerometer data. AAAI. 2005 Jul 9;5:1541-1546.

(2) Troiano RP, Berrigan D, Dodd KW, Masse LC, Tilert T, McDowell M. Physical activity in the United States measured by accelerometer. Medicine and science in sports and exercise. 2008 Jan 1;40(1):181-188. Available from: doi:10.1249/mss.0b013e31815a5lb3


No comments:

Post a Comment