Computerized reasoning—also known as “man-made intelligence”—and remote technology to provide early identification of upcoming medical conditions and unobtrusive screening of elderly people in their living spaces.
Without the need for a wearable device, the new system, developed by researchers at the University of Waterloo, accurately and continuously monitors an individual’s activities, collects vital information, and notifies medical professionals of the need to intervene and assist.
“After more than five years of working on this technology, we’ve demonstrated that very low-power, millimeter-wave radio systems enabled by machine learning and artificial intelligence can be reliably used in homes, hospitals, and long-term care facilities,” stated Dr. George Shaker, an adjunct associate professor of electrical and computer engineering.
An added benefit is that “the system can alert healthcare workers to sudden falls without the need for privacy-invading devices like cameras.”
Shaker and his coworkers’ work comes at a time when public healthcare systems that are already overburdened are having trouble meeting the immediate needs of the rapidly growing elderly population.
Regardless of whether a senior is in long haul care, it’s remarkably difficult to screen their developments and spot issues 24 hours per day, despite the fact that their physical or state of mind can change rapidly. Additionally, existing frameworks for observing a person’s stride, or how they walk, are prohibitive for homes, difficult to implement, and expensive.
This is how the new system works, which is a significant improvement: To begin, a wireless transmitter distributes low-power waveforms throughout an interior space, such as an apartment, a house, or a long-term care facility.
The waveforms that bounce off the various objects and people being monitored are captured and processed by a receiver. A computerized reasoning motor purposes that information to translate the handled waves for applications in recognition and observing.
The system, which makes use of very low-power radar technology, does not have the drawbacks of wearable monitoring devices, like the fact that they can be uncomfortable and need to be charged frequently. Instead, it can be simply attached to a wall or the ceiling.
Shaker stated, “Incorporating our remote innovation in homes and long-term care facilities can actually screen various activities, such as resting, sitting in front of the television, eating, and the recurrence of using the restroom.”
“At this time, the system is able to notify caregivers of a general decline in mobility, an increased risk of falling, the possibility of a urinary tract infection, and the onset of several other medical conditions.”
Waterloo researchers are working with a Canadian company called Gold Sentintel to commercialize the technology, which has already been installed in a number of long-term care facilities.
An article titled AI-Powered Non-Contact In-Home Gait Monitoring and Activity Recognition System Based on mm-Wave FMCW Radar and Cloud Computing in the IEEE Internet of Things Journal provides a comprehensive account of the project.
Hajar Abedi, a doctoral student, is the primary author, with contributions from Ahmad Ansariyan, Dr. Plinio Morita, Dr. Jen Boger, and Dr. Alexander Wong.
