November 5, 2013
Mobile App Uses New Algorithm To Track Physical Activity Anywhere
Peter Suciu for redOrbit.com - Your Universe Online
There are a plethora of devices as well as mobile phone apps that promise to track a wearers’ activity, including daily movements, and provide ongoing health monitoring. However, most of these devices have required the use of a special pulse or heart rate monitor.
One noted example is those who suffer from Parkinson’s disease.
Previous studies of activity tracker apps reported that throughout the day the wearers typically carried the devices in a pocket or on a belt, but using a purse or a bag was also reported. Many patients were not aware that the placement of the devices in proximity to the body could affect how well the tracker can work.
A new algorithm has been devised by an interdisciplinary team at Northwestern that can be used with a physical activity app that can predict the location of a handset throughout the day with near perfect accuracy. While the tracking of activity is paramount, the app apparently has fashion and comfort in mind.
“While it remains true that smart phone activity trackers are the most accurate when the phone is placed in the pocket or on a belt, with this algorithm we can provide an estimate of error associated with other locations where the phone is carried,” Konrad Kording, principal investigator of the study, said in a statement.
Kording’s research has looked at how people move and how their movements are affected by uncertainty. The findings are important,, as studies have suggested it is unrealistic to assume that people will carry devices in the same way every time.
“Most women carry their phones in a purse,” added Stephen Antos, first author of the study. “Some people carry theirs on their belt or in their hand. We may change where we carry our phone throughout the day as well. We wanted to solve this problem and find a way to make these trackers as accurate as possible no matter where you carry your phone.”
The team of researchers with Feinberg’s Center for the Behavioral Intervention Technologies recruited a dozen healthy subjects, who participated in pre-arranged activities that included walking, sitting and standing while carrying a smartphone in various places – such as purse/backpack, belt, hand and pocket. The same method was also used on two individuals with Parkinson’s disease.
The National Parkinson Foundation, the the National Institute of Neurological Disorders and Stroke (NINDS) of the National Institutes of Health (NIH) and the Washington Square Health Foundation supported the study, which is one of several now taking place at Northwestern’s Center for Behavioral Intervention Technologies that utilizes smartphone apps to improve health.
In this particular study data was collected and used to train a computer algorithm to predict where a phone might be carried and to detect second-by-second activity such as sitting, standing and walking.
“I believe we will have apps running on smartphones that will know exactly what we're doing activity-wise and will warn us of diseases before we even know that we have those diseases,” Kording said. “In the future, phones will have a major role in motivating people towards behavior that is good for their health.”
Kording is an associate professor of physical medicine and rehabilitation and of physiology at Northwestern University Feinberg School of Medicine and a research scientist at the Rehabilitation Institute of Chicago.
Antos is a PhD candidate in the department of biomedical engineering at Northwestern University's McCormick School of Engineering and Applied Science and a research scientist in the Sensory Motor Performance Program, Rehabilitation Institute of Chicago.
It is at the Rehabilitation Institute of Chicago where the first brain-controlled bionic leg is being developed and tested.