Communications of the ACM
A Step Toward Personalized, Automated Smart Homes
The new Duet system developed by researchers at the Massachusetts Institute of Technology uses reflected wireless signals to identify occupants within a home, even when they are not carrying mobile devices.
Credit: Chelsea Turner/MIT
Massachusetts Institute of Technology researchers have developed a system that uses reflected wireless signals to identify occupants within a home, even when they are not carrying mobile devices.
The Duet system relies on algorithms that ping nearby mobile devices to predict individuals' identities, based on who last used the device and their anticipated movement trajectory.
The researchers tested Duet in an apartment with four people and in an office with nine people; in those respective scenarios, Duet identified individuals with 96% accuracy and 94% accuracy, respectively.
Duet utilizes a device-based localization system that uses a central node to calculate the time it takes wireless signals to hit a person's device and travel back; the researchers integrated Duet with a device-free tracking system that localizes people by measuring the reflections of wireless signals off their bodies.
Microsoft Researchers Ranveer Chandra said the system “takes a smart approach of combining the location of different devices and associating it to humans, and leverages device-free localization techniques for localizing humans.”
From MIT News
View Full Article
Abstracts Copyright © 2018 Information Inc., Bethesda, Maryland, USA
No entries found