Kettnaker’s proposed “video-equipped intelligent environment” will be able to analyze an elderly person’s movement patterns to detect a potential problem and, if needed, summon help automatically. Her system could someday allow seniors to be safer in their own homes and self-reliant for many more years.
The CAREER award provides a grant of $400,000 over five years and is the most prestigious honor the NSF presents to junior faculty. Kettnaker is one of 22 Rensselaer faculty members to receive this award in the past four years.
The Possibility of Automatic Protection
Current safety monitoring devices for seniors require injured or ill individuals to manually request assistance with the push of a button or a tug on a string. Such otherwise helpful devices are of no use following accidents resulting in loss of consciousness, such as falls or stroke.
Kettnaker’s planned surveillance system would “learn” the pattern of a person’s regular activities during a two- or three-week training period. Using a mathematical model similar to those used for voice recognition and natural language processing, it would analyze the person’s locations and activities and how they change over time. The system would then be able to project expected or “normal” patterns of behavior for the resident individual.
Kettnacker says it is much easier to track seniors than say, a teenager, since their life patterns are well-established.
“Once you are 85-years-old, you’ve found your routine,” Kettnaker says. “You probably minimize trips around your home and generally have more structure in your life.”
Keeping an Electronic Eye Out for Trouble
Similar to an in-home fire alarm system, Kettnaker’s system would require one ceiling-mounted camera to be installed in each room of a person’s home. If the prototype developed over the next five years shows promise as a consumer product, the cameras could be integrated with the necessary data-processing equipment. “To make this product truly useful,” Kettnaker says, “people would need to be assured of their privacy as much as possible.” In practical use, each camera unit would output only the current coordinates of the person for processing — video data would never have to be transmitted at all.
Time- and/or place-related deviations from usual patterns — such as staying in the tub for an hour rather than the usual 20 minutes, or failing to rise from bed in the morning — would alert the system that a dangerous event may have occurred. In that case, a recorded message would automatically ask the individual if help is needed. The lack of an answer would signal “yes,” and the system would send an electronic call for assistance.
Kettnaker hopes that this system will afford solo seniors a greater degree of safety, without compromising their privacy or limiting their ability to move about naturally.
About Rensselaer
Rensselaer Polytechnic Institute, founded in 1824, is the nation's oldest technological university. The school offers degrees in engineering, the sciences, information technology, architecture, management, and the humanities and social sciences. Institute programs serve students and working professionals around the world. Rensselaer faculty members are known for pre-eminence in research conducted in a wide range of research centers characterized by strong industry partnerships. The Institute is especially well known for its success transferring technology from the laboratory to the marketplace allowing new discoveries and inventions to benefit human life, protect the environment, and strengthen economic development.