By Heather Hamilton, contributing writer
Professor Dina Katabi and a group at MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) unveiled a device on Monday that measures the walking speed of multiple people with an accuracy of 85% to 99%, which is significant because mounting research suggests walking speed to be a better predictor of a variety of health issues.
While walking speed can be an indicator of cognitive decline, cardiac or pulmonary diseases, and falls, measuring it is both intrusive and requires continuous measurement. WiGait, as it is named in a press release from MIT, uses wireless signals, eliminating problems with measuring walking speed. Katabi’s team presented an earlier version of the device to President Obama in 2015.
No larger than a small picture, Katabi’s device is to be placed on the wall. The idea builds on previous work, which analyzed wireless signals reflected off of people’s bodies to measure other behaviors, including emotion. WiGait boasts a high degree of accuracy and measures stride length, which will help diagnose diseases like Parkinson’s, which is characterized by a reduction in step size.
“By using in-home sensors, we can see trends in how walking speed changes over longer periods of time. This can provide insight into whether someone should adjust their health regimens, whether that’s doing physical therapy or altering their medications,” says PhD student Chen-Yu Hsu, who is also the paper’s lead author.
Currently, walking speed is measured with a stopwatch and some assistance from wearables, which provide estimates based on step count. While VICON motion-tracking also provides an accurate measurement wirelessly, it is not widely available and is impractical for identifying day-to-day changes.
WiGait analyzes wireless signals and their reflections off of a person’s body, distinguishing walking from other movements. Katabi believes that the device has the potential to improve the lives of many by revealing a plethora of health information.
“Many avoidable hospitalizations 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. Reducing the number of hospitalizations, even by a small amount, could vastly improve healthcare costs,” said Katabi.
For those concerned about privacy in an increasingly less private world, WiGait shows nothing more than a moving dot on a screen. In the future, the research team hopes to train the device on people with walking impairments to help doctors track disease progression and adjust medication for people with diseases like MS, Alzheimer’s, or Parkinson’s.
Katabi and Hsu’s team also included Zachary Kabelac, CSAIL PhD student; Rumen Hristov, CSAIL master's student; Yuchen Liu, undergraduate from the Hong Kong University of Science and Technology; and Boston University School of Medicine Assistant Professor Christine Liu. The team’s research will be presented at Colorado’s ACM’s CHI Conference on Human Factors in Computing Systems in May.
Advertisement
Learn more about Electronic Products Magazine
