Wireless Network Detects Falls

University of Utah engineers have developed a network of wireless sensors that can detect a person falling and can be linked to a services that is able to call emergency help for the elderly without requiring them to wear monitoring devices.

For the elderly, falling is a leading cause of injury and death. Most fall detection devices monitor a person’s posture or require a person to push a button to call for help. The problem is that these devices must be worn at all times.

A study done a few years back showed that 80 percent of elderly adults who owned call buttons didn’t use the device when they had a serious fall. This was largely because they weren’t wearing the device at the time of the fall.

The engineers at the university have constructed a fall detection system using a two-level array of radio frequency sensors that is placed around the perimeter of a room at two heights corresponding to someone standing or lying down. These sensors are similar to those used in home wireless networks and are able to transmit information from someone either standing or falling inside the network.

By measuring the signal strength between each link in the network, an image is generated to show the approximate location of a person in the room with a resolution of about six inches. This imaging technique called radio tomography uses one dimensional link measurements from the sensor network to build up 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 and it can also indicate whether a person is standing up or lying down.

In addition, the system is programmed to detect whether a fall was a dangerous or rather than someone simply lying down on the floor. By conducting a series of experiments measuring the amount of time that elapsed when a person fell, sat down, or laid down on the ground, the researchers can determine the time threshold for accurately detecting the fall. This information is then fed back into algorithms and the data is used to determine whether a given event was a fall.

The engineering team plans to develop this proof-of-concept technology into a commercial product through a Utah-based startup company, Xandem Technology which is being funded by the National Science Foundation.

For more information, contact Brad Mager, at bradmager@earthlink.net or Neal Patwari at npatwari@ece.utah.edu.