A new algorithm invented at the University of Sussex enables smartwatches to learn your everyday activities. Source: University of Sussex

While standard smartwatches are preprogrammed to detect specific moves likes those associated with running and yoga, scientists from the University of Sussex have developed an algorithm that will help smartwatches detect a variety of movements, all without having to be preprogrammed.

The new algorithm discovers new activities, such as teeth brushing or vegetable cutting, as they happen, and counts them among the moves a person makes throughout the course of the day.

Additionally, the algorithm can even distinguish between stationary activities such as sleeping and sitting.

Dr. Hristijan Gjoreski of the University of Sussex said: "Current activity-recognition systems usually fail because they are limited to recognizing a predefined set of activities, whereas of course human activities are not limited and change with time. Here we present a new machine-learning approach that detects new human activities as they happen in real time, and which outperforms competing approaches."

The scientists believe that the algorithm will have a number of uses, including in the health care field and in the research of consumer behavior.

According to Dr. Daniel Roggen, head of the Sensor Research Technology Group at the University of Sussex, "Future smartwatches will be able to better analyze and understand our activities by automatically discovering when we engage in some new type of activity. This new method for activity discovery paints a far richer, more accurate, picture of daily human life."

Details about the new algorithm will be presented this month in Hawaii at the International Symposium on Wearable Computers.