New Sensory Alert System Automatically Detects When A Person Falls
September 9, 2013

New Sensory Alert System Automatically Detects When A Person Falls

Brett Smith for - Your Universe Online

Since the late 1980s, wearable alert devices have been marketed to the elderly who are at risk of falling and not being able to get up. However, a 2008 study found that 80 percent of elderly adults who owned such devices didn't use them and likely weren't wearing them when they had a serious fall.

Now, University of Utah engineers have announced a new system capable of automatically detecting a fall and contacting a service that would call for emergency help.

According to their presentation at the 24th Annual Institute of Electrical and Electronics Engineers International Symposium on Personal, Indoor and Mobile Radio Communications in London, the engineers’ system uses a two-level array of sensors placed around the perimeter of a room at heights that correlate to a person either standing or lying down. Similar to those used in home wireless networks, the sensor pairs transmit to one another and anyone standing -- or falling -- inside the sensor network affects the path of signals being sent between each pair of sensors.

After establishing “proof-of-concept,” the Utah team said they plan to develop their technology into a commercial product through the Utah-based startup company, Xandem Technology.

"The idea of 'aging-in-place,' in which someone can avoid moving to a nursing home and live in their own home, is growing," said Neal Patwari, an associate professor of electrical and computer engineering at the University of Utah and founder of Xandem. "Ideally, the environment itself would be able to detect a fall and send an alert to a caregiver. What's remarkable about our system is that a person doesn't need to remember to wear a device."

The smart network measures the signal strength between each link to create an image showing the location of a person in the room within about six inches. Applying a technique called radio tomography, the system uses the one-dimensional link from the sensor network to engineer a three-dimensional image.

"With this detection system, a person's location in a room or building can be pinpointed with high accuracy, eliminating the need to wear a device," said system co-creator Brad Mager, a graduate student in electrical and computer engineering at the university. "This technology can also indicate whether a person is standing up or lying down."

The system is also able to tell the difference between a dangerous fall and someone simply lying down on the floor. After conducting a series of tests recording the amount of time for a fall as opposed to a safe activity like sitting or lying down, the researchers were able to incorporate a time threshold for accurately distinguishing a fall. This information was incorporated into algorithms designed to determine if a given event was a fall or a more benign activity.

According to a 2010 data set from the Centers for Disease Control and Prevention, about 26,000 Americans die from a fall-related incident each year, regardless of age.