Skip to page content

Samsung Electronics, UGA to develop new digital health experience

  |   Kathryn Kao   |   Permalink   |   News Release,   Research,   Students and Faculty

Why do we feel tired and sluggish one day and filled with energy the next?

While there are many factors when it comes to measuring energy levels, users of the upcoming Galaxy Watch may come closer to answering these questions based on their personalized “Energy Score,” a collaborative measurement developed by Samsung and the University of Georgia.

To improve the digital healthcare experience, Samsung Research collaborated with Patrick O’Connor, a professor in the Mary Frances Early College of Education’s Department of Kinesiology, to design a new measurement that records energy as a daily score.

While creating an objective measurement of energy is difficult, O’Connor’s extensive research into exercise and psychobiology provides a foundation for identifying relationships between cognitive and physical capacity—two concepts factored into calculating the Energy Score.


Energy is required to sustain both physical and mental activities, and while most existing measurements of energy rely solely on physical aspects, Samsung’s Energy Score also factors in assessments that can influence mental performance such as the amount of sleep an individual obtains at night, as well as its quality based on sensors in the watch.

“The decision on what factors to include in the energy score was influenced by the accuracy of watch sensors combined with findings of our team’s research conducted with the watch and a careful consideration of which variables have been adequately linked to mental or physical performance in the scientific literature,” said O’Connor.

For the study, O’Connor’s team looked at not only cognitive and physical performance in correlation to energy, but also quantified daily variations in several metrics measured by the Galaxy Watch, including physical activity, sleep, heart rate, and heart rate variability—all of which are considered when calculating the Energy Score. Heart rate variability measures variation in the time between heart beats, measured in milliseconds.

His research team conducted experiments that included cognitive tests as well as energy and fatigue symptom self-reports, which found a significant correlation between the Energy Scores generated by Samsung’s models and clinical data collected by O’Connor’s team.

“From a scientific perspective, the Energy Score reflects predicted variation in the ability to perform brief cognitive tests of attention across a day based on objective information obtained from the smart device sensors across multiple prior days,” said O’Connor.

The energy score estimates the amount of activity one can sustain relative to a person’s total capacity, both physically and mentally. If people substantially exceed their typical physical or mental load on one day, their energy is reduced in the short-term.

For instance, if a person typically exercises at low intensity for 30 minutes daily but decides to engage in moderate intensity for more than an hour one day, the wearer’s Energy Score is expected to drop the following day.

However, regular exercise with appropriate rest can gradually enhance overall capacity, potentially resulting in a higher Energy Score for the same workout intensity over time.


In contrast, sleep data primarily contributes to mental capacity and is measured by the duration, timing, and consistency of sleep and wake times, as well as how quickly watch wearers fall asleep.

Heart rate during sleep and heart rate variability during sleep can reflect both physical and mental capacities and can forecast energy by comparing recent measurements to long-term data trends, with the precision of predictions enhanced by analyzing both stable heart rate and heart rate variability during sleep.

In addition to UGA’s research, Samsung employed AI technologies that use factors like age and gender to determine optimal weights for an individual Energy Score. Ultimately, brief daily health suggestions are provided to users based on each day’s Energy Score.

O’Connor’s research—along with Samsung’s AI technologies—aims to enhance the accuracy of each individual Energy Score.

“Through our collaboration with professor O’Connor, we were able to address this challenge in a scientifically meaningful way,” said Lee Yunsu, head of the data intelligence team at Samsung Research. “We will continue to devote our efforts to developing data and AI technologies to ensure that Samsung’s various devices are used more extensively to enhance users’ healthy lives.”

© University of Georgia, Athens, GA 30602