Proving the Business Case for the Internet of Things

MIT device wirelessly monitors walking speed

Steve Rogerson
May 9, 2017

Massachusetts Institute of Technology has developed a device the size of a small painting that can be hung on a wall and measure the walking speed of multiple people with 95 to 99 per cent accuracy using wireless signals.
How fast people walk can be a predictor of health issues such as cognitive decline, falls and even certain cardiac or pulmonary diseases.
Unfortunately, it’s hard to monitor walking speed accurately in a way that’s both continuous and unobtrusive. Professor Dina Katabi’s group at MIT’s Computer Science & Artificial Intelligence Laboratory (CSAIL) has been working on the problem, and believes the answer is to go wireless.
In a paper, the team presented WiGait, a device that can be placed on the wall of a person’s house and its signals emit roughly one-hundredth the amount of radiation of a standard mobile phone. It builds on Katabi’s previous work on WiTrack, which analyses wireless signals reflected off people’s bodies to measure a range of behaviour from breathing and falling to specific emotions.
“By using in-home sensors, we can see trends in how walking speed changes over longer periods of time,” said lead author and student Chen-Yu Hsu. “This can provide insight into whether someone should adjust their health regimen, whether that’s doing physical therapy or altering their medications.”
WiGait is also 85 to 99 per cent accurate at measuring a person’s stride length, which could allow researchers to understand conditions such as Parkinson’s disease that are characterised by reduced step size.
Hsu and Katabi developed WiGait with CSAIL students Zachary Kabelac and Rumen Hristov, alongside undergraduate Yuchen Liu from the Hong Kong University of Science & Technology, and assistant professor Christine Liu from the Boston University School of Medicine. The team are presenting their paper this week’s ACM CHI Conference on Human Factors in Computing Systems in Colorado.
Today, walking speed is measured by physical therapists or clinicians using a stopwatch. Wearables such as FitBit can only roughly estimate speed based on step count, and GPS-enabled smartphones are similarly inaccurate and can’t work indoors. Cameras are intrusive and can only monitor one room. Vicon motion tracking is the only method that’s comparably accurate to WiGate, but it is not widely available enough to be practical for monitoring day-to-day health changes.
Meanwhile, WiGait measures walking speed with a high level of granularity, without requiring that the person wear or carry a sensor. It does so by analysing the surrounding wireless signals and their reflections off a person’s body. The CSAIL team’s algorithms can also distinguish walking from other movements, such as cleaning the kitchen or brushing one's teeth.
Katabi said the device could help reveal a wealth of important health information, particularly for the elderly. A change in walking speed, for example, could mean that the person has suffered an injury or is at an increased risk of falling. The system's feedback could even help the person determine if they should move to a different environment such as an assisted-living home.
“Many avoidable hospitalisations are related to issues like falls, congestive heart disease or chronic obstructive pulmonary disease, which have all been shown to be correlated to gait speed,” Katabi said. “Reducing the number of hospitalisations, even by a small amount, could vastly improve health care costs.”
The team developed WiGait to be more privacy-minded than cameras, showing the user as nothing more than a moving dot on a screen. In the future they hope to train it on people with walking impairments from Parkinson’s, Alzheimer’s or multiple sclerosis, to help physicians accurately track disease progression and adjust medications.
“The true novelty of this device is that it can map major metrics of health and behaviour without any active engagement from the user, which is especially helpful for the cognitively impaired,” said Ipsit Vahia, a geriatric clinician at McLean Hospital and Harvard Medical School, who was not involved in the research. “Gait speed is a proxy indicator of many clinically important conditions, and down the line this could extend to measuring sleep patterns, respiratory rates and other vital human behaviour.”