Engineers are outfitting computerized reasoning (man-made intelligence) and remote innovation to unpretentiously screen older individuals in their living spaces and give early identification of arising medical conditions.

The new system, developed by researchers at the University of Waterloo, accurately and continuously monitors an individual’s activities, gathers vital information without requiring a wearable device, and notifies medical professionals of the need to intervene and assist.

Dr. George Shaker, an adjunct associate professor of electrical and computer engineering, stated, “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.”

“The system can alert healthcare workers to sudden falls without the need for privacy-invading devices like cameras, which is an added benefit.”

The work done by Shaker and his coworkers comes at a time when overworked public healthcare systems are having trouble meeting the immediate requirements of the rapidly expanding elderly population.

Even if a senior is in long-term care, it’s almost impossible to monitor their movements and spot problems 24 hours a day, even though their physical or mental condition can change quickly. Moreover, other existing frameworks for observing stride – – how an individual strolls – – are costly, challenging to work, unrealistic for facilities and inadmissible for homes.

The new system works this way and represents a significant advancement: First, a wireless transmitter transmits low-power waveforms throughout an interior space, such as an apartment, home, or long-term care facility.

A receiver captures and processes the waveforms as they bounce off various objects and people being monitored. An artificial intelligence engine uses that data to decipher the processed waves for applications in detection and monitoring.

The system, which makes use of extremely low-power radar technology, does not suffer from the disadvantages of wearable monitoring devices, which can be uncomfortable and necessitate frequent battery charging. Instead, it can be simply mounted on the ceiling or by a wall.

“Involving our remote innovation in homes and long haul care homes can actually screen different exercises, for example, resting, sitting in front of the television, eating and the recurrence of restroom use,” Shaker said.

“At the moment, the system can 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.”

The technology, which has already been installed in several long-term care facilities, is being commercialized by Waterloo researchers in collaboration with a Canadian company called Gold Sentintel.

The work is described in detail in an article published in the IEEE Internet of Things Journal titled AI-Powered Non-Contact In-Home Gait Monitoring and Activity Recognition System Based on mm-Wave FMCW Radar and Cloud Computing.

The primary author was doctoral student Hajar Abedi, with Ahmad Ansariyan, Dr. Plinio Morita, Dr. Jen Boger, and Dr. Alexander Wong contributing.