Communications of the ACM
New Wearable Technology Can Sense Appliance se, Help Track Carbon Footprint
This MagnifiSense research prototype can sense what appliances its wearer is using, based on the electromagnetic radiation emanating from devices such as blenders, remote controls or even automobiles.
Credit: University of Washington
University of Washington (UW) researchers have developed MagnifiSense, wearable technology that can sense what devices and vehicles the user interacts with throughout the day.
The researchers say the technology could help track the user's carbon footprint, enable smart home applications, or assist with elder care. In a study, MagnifiSense correctly classified 94 percent of users' interactions with 12 common devices after a quick one-time calibration.
The system includes a sensor worn on the wrist that uses unique electromagnetic radiation signatures generated by electrical components or motors in those devices to identify when the user completes certain actions. In one 24-hour test, MagnifiSense correctly identified 25 out of 29 interactions with various devices and vehicles.
The researchers combined three off-the-shelf sensors that use inductors, which proved to be the most accurate without being so power-hungry that wearing them would be impractical. In addition, the sensors capture a broad frequency range that enables the system to differentiate between electromagnetic radiation emanating from the unique combinations of different electronic components. The researchers also developed signal-processing and machine-learning algorithms to help the system correctly match those patterns with a certain kind of device.
"The next steps are really to look at what other devices we can detect and work on a prototype that's wearable," says UW professor Shwetak Patel.
From University of Washington News and Information
View Full Article
Abstracts Copyright © 2015 Information Inc., Bethesda, Maryland, USA
No entries found