Kinect Assists At-risk Older Adults

When Microsoft unveiled its Kinect motion-sensing input device for the Xbox 360 video game console last November, its target audience was mainly young athletic gamers.

But today, Kinect — and other computer technology, like Doppler radar — are being used for an older adult demographic — seniors in an assisted-living facility — to detect the early onset of illness and risk of falling.

The research consists of nine projects being conducted by the Center for Eldercare and Rehabilitation Technology (CERT), a group at the University of Missouri composed of engineering and computer science people, as well as nursing, medicine, social work, and physical therapy professionals. Almost $8 million in funding is coming from the U.S. National Science Foundation, the National Institutes of Health, the Agency for Healthcare Research and Quality, the U.S. Administration on Aging, the RAND/Hartford Foundation, and the Alzheimer's Association.

For almost six years, the CERT program has focused on simple motion and video sensors, plus bed sensors that utilize ballistocardiograph signals, to capture pulse and respiration levels, as well as detect restlessness. The systems, which do not require subjects to wear or handle any equipment were installed in 40 apartments at TigerPlace, a senior residence in Columbia, MO.

The goal is to use the collected data to develop algorithms for identifying alert conditions, such as falls, as well as extracting typical daily activity patterns for an individual — and then recognize when activity patterns begin to deviate from the norm. In doing so, researchers aim to provide early detection of potential problems which may lead to serious health events if left unattended.

Recently, the program was expanded to include an off-the-shelf General Electric pulse-Doppler range control radar, a box just slightly bigger than a cigarette pack, that detects whether a person is falling by measuring object movement and changes in speed regardless of light conditions, according to Mihail Popescu, assistant professor in the department of Health Management and Informatics at the University of Missouri.

And, since July, the Microsoft Kinect has been added to focus on "gait information," a sophisticated early indicator of both cognitive and physical problems.

"We are measuring things like walking speed, step time, step length, body sway, and how long it takes someone to move from a sitting to a standing position," says Marjorie Skubic, professor of electrical and computer engineering in the Missouri University College of Engineering and CERT's director. "These are all gait parameters that go into being able to detect changes in health and being able to assess whether somebody is at risk for falling."

The Kinect uses infrared light to create a depth image that produces data in the form of a silhouette instead of a video or photo [see video]. This is said to alleviate many seniors' concerns about privacy when traditional Web camera-based monitoring systems are used.

Researchers say the two additions to the program — the Kinect and the Doppler radar — is giving them a far richer set of data than the motion and bed sensors.

A paper about usage of the Kinect, "Evaluation of an Inexpensive Depth Camera for Passive In-Home Fall Risk Assessment," won the best paper award at the Pervasive Health Conference in Dublin, Ireland in May. And a paper on the Doppler radar system, "Automatic Fall Detection Based on Doppler Radar Motion," received the best poster award at the conference.

Ultimately, Skubic hopes to see the system commercialized and "put into peoples' homes where it will be a big aid to help people be as safe and as independent as possible." To that end, she has been "talking to some companies interested in manufacturing the system."

Paul Hyman was editor-in-chief of several hi-tech publications at CMP Media, including Electronic Buyers' News.