As we age, we gain many wonderful experiences and memories, but it’s important to be aware that the risk of falls can also increase, potentially leading to serious injuries, such as hip fractures, head injuries, and even death.
Although not all falls result in injury, the incident can often result in a person losing confidence in their abilities and withdrawing from life to avoid the risk of suffering a fall again.
While falls can happen anywhere, they are particularly dangerous at home, where most people spend the majority of their time.
To help older adults get the care they need after a fall at home, Binghamton University researchers are developing a faster response system. Using a human action recognition (HAR) algorithm and local computing power to analyse sensor data to swiftly detect abnormal movements such as falls.
Professor Yu Chen and PhD student Han Sun from the Thomas J. Watson College of Engineering and Applied Science’s Department of Electrical and Computer Engineering developed the Rapid Response Elderly Safety Monitoring (RESAM) system, harnessing cutting-edge edge computing technology.
In a paper recently published in the IEEE Transactions on Neural Systems and Rehabilitation Engineering, it was shown that the RESAM system can run using a smartphone, smartwatch, laptop, or desktop computer with 99 per cent accuracy and a 1.22-second response time, ranking among the most accurate methods available today.
“When many people talk about high tech, they are discussing something cutting edge, like a fancier algorithm, a more powerful assistant to do jobs faster or having more entertainment available,” Chen explained.
“We observed a group of people — senior citizens — who need more help but normally do not have sufficient resources or the opportunity to tell high-tech developers what they need.”
Chen also explained that by using devices that are already familiar to older adults the system will provide users with a greater feeling of control over their health.
Additionally, RESAM safeguards privacy by converting monitored images into skeletons. This method enables analysis of crucial points like arms, legs, and torso to identify whether someone has fallen or encountered another accident that may result in injury.
“The most dangerous place for falls is the bathroom, but nobody wants to set up a camera there,” Chen said.
“People would hate it.”
Looking ahead, Chen envisions expanding the system to incorporate thermal or infrared cameras along with other sensors, allowing for remote assessment of additional aspects of a person’s environment and well-being.
“Adding more sensors can make our system more powerful because we are not only monitoring someone’s body movements — we can monitor someone’s health with one more dimension, so we better predict if something’s going to happen before it happens,” he said.