Samsung and the University of Georgia have developed a personalized energy score that will be a key feature of the new Galaxy Watch. (Andrew Davis Tucker/UGA)
Why do we feel tired and lethargic? one day and full of energy the next?
While there are many factors that go into measuring energy levels, users of the upcoming Galaxy Watch may be able to answer these questions based on their personalized Energy Score, a collaborative metric developed by Samsung and the University of Georgia.
To improve the digital healthcare experience, Samsung Research collaborated with Patrick O’Connor, professor in the Department of Kinesiology at Mary Frances Early College of Education, to design a new metric that records energy as a daily score.
Although it is difficult to create an objective measure of energy, O’Connor’s extensive research in exercise and psychobiology provides a basis for identifying relationships between cognitive and physical capacity, two concepts considered in calculating the energy score.
Energy is needed to support both physical and mental activities, and while most existing energy metrics rely solely on physical aspects, Samsung’s Energy Score also takes into account assessments that can influence mental performance such as the amount of sleep an individual gets at night, as well as its quality based on the watch’s sensors.
“The decision on which factors to include in the energy score was influenced by the accuracy of the watch’s sensors, combined with the results of research our team conducted with the watch and a careful review of variables that have been adequately linked to mental or physical performance in the scientific literature,” O’Connor said.
For the study, O’Connor’s team not only looked at cognitive and physical performance in correlation with energy, but also quantified daily variations in several parameters measured by the Galaxy Watch, including physical activity, sleep, heart rate, and heart rate variability, all of which are factored into the calculation of the energy score. Heart rate variability measures the variation in time between heartbeats, measured in milliseconds.
His research team conducted experiments that included cognitive tests as well as self-assessments of energy and fatigue symptoms, which revealed a significant correlation between the energy scores generated by the Samsung models and clinical data collected by O’Connor’s team.
“From a scientific perspective, the energy score reflects the expected variation in the ability to perform brief cognitive tests of attention over the course of a day based on objective information obtained from smart device sensors over several previous days,” O’Connor said.
The energy score assesses the amount of activity a person can maintain relative to their total capacity, both physical and mental. If a person significantly exceeds their usual physical or mental load during a day, their energy is reduced in the short term.
For example, if a person usually exercises at a low intensity for 30 minutes a day, but decides to exercise at a moderate intensity for more than an hour one day, their energy score should drop the next day.
However, regular exercise accompanied by adequate rest can gradually improve overall capacity, which can potentially translate into a higher energy score for the same training 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.
Sleep heart rate and sleep heart rate variability can reflect physical and mental abilities and can predict energy by comparing recent measurements to long-term data trends, with prediction accuracy improved by analyzing stable heart rate and sleep heart rate variability.
In addition to UGA’s research, Samsung used AI technologies that use factors such as age and gender to determine optimal weights for an individual’s energy score. Ultimately, users are provided with brief daily health suggestions based on each day’s energy score.
O’Connor’s research, along with Samsung’s AI technologies, aims to improve the accuracy of each individual energy score.
“Through our collaboration with Professor O’Connor, we were able to address this challenge in a scientifically relevant way,” said Lee Yunsu, head of the Data Intelligence Team at Samsung Research. “We will continue to dedicate our efforts to developing data and AI technologies to ensure that Samsung’s various devices are more widely used to improve users’ health.”
