Wearables

MagnifiSense uses electromagnetic signatures to keep tabs on your energy use

The MagnifiSense prototype detects what electronic devices and motor vehicles an individual is interacting from their unique electromagnetic signatures
The MagnifiSense prototype detects what electronic devices and motor vehicles an individual is interacting from their unique electromagnetic signatures
View 3 Images
The MagnifiSense prototype detects what electronic devices and motor vehicles an individual is interacting from their unique electromagnetic signatures
1/3
The MagnifiSense prototype detects what electronic devices and motor vehicles an individual is interacting from their unique electromagnetic signatures
MagnifiSense relies on the unique pattern of electromagnetic radiation emitted by appliances and vehicles such as cars, buses and trains
2/3
MagnifiSense relies on the unique pattern of electromagnetic radiation emitted by appliances and vehicles such as cars, buses and trains
Unique electromagnetic radiation patterns enable MagnifiSense to identify what devices its wearer is using
3/3
Unique electromagnetic radiation patterns enable MagnifiSense to identify what devices its wearer is using

From the Fitbit to the Apple Watch, there'sno shortage of wearable devices that track your daily activity with an eye onyour personal health and wellbeing, but a new device developed at the University ofWashington (UW) can track your activity as it pertains to the health of theplanet. Called MagnifiSense, the wrist-worn prototype detects what devicesand vehicles the wearer interacts with throughout the day to help track theircarbon footprint.

MagnifiSense senseswhat electronic devices and motor vehicles an individual is interacting with bydetecting their unique electromagnetic signatures.

"When a blender turns on, forinstance, modulators change the current profile of the device and createsomething similar to a vocal cord pattern," explains study lead author andUW electrical engineering student Edward Wang. "A blender 'sings' quitedifferently than a hair dryer even though to our ears they sound similar."

Theprototype combines three basic, off-the-shelf sensors that use coils of wirearound magnets (inductors), to accurately capture a broad frequency range ofelectromagnetic radiation without being too power hungry. Signal processing andmachine learning algorithms developed by the team match the electromagneticsignatures to a particular type of device.

MagnifiSense relies on the unique pattern of electromagnetic radiation emitted by appliances and vehicles such as cars, buses and trains
MagnifiSense relies on the unique pattern of electromagnetic radiation emitted by appliances and vehicles such as cars, buses and trains

Withoutcalibration, the team says the MagnifiSense correctly identified 12 commondevices, including microwaves, blenders, remote controls, toothbrushes,laptops, light dimmers, and cars and buses, with 83 percent accuracy. However,a quick one-time calibration upped the accuracy to 94 percent.

"It’sanother way to log what you’re interacting with so at the end of the day ormonth you can see how much energy you used," said Shwetak Patel, anAssociate Professor in UW's departments of Computer Science & Engineeringand Electrical Engineering. "Right now, we can know that lights are 20 percent of yourenergy use. With this, we divvy it up and say who consumed that energy."

Overa 24-hour test, in which a single person wearing the prototype went about theirday performing everyday tasks such as using a laptop, cooking dinner andriding a bus, the research team says the system correctly identified 25 out of29 interactions with various devices and vehicles.

Inaddition to tracking an individual's carbon footprint through the devices theyinteract with throughout the day, the UW team says the MagnifiSense systemcould also find use in smart home and aged care applications. For example, itcould identify when an individual is interacting with a specific device, suchas a tablet, so the experience can be customized appropriately, or track howelderly people are faring with cooking and grooming in an assisted living ornursing home setting. It could also identify if an appliance, such as a stove,has been left on for an extended period.

"The nice thing withMagnifiSense is that you don’t have to instrument every single appliance inyour house, which gets expensive and cumbersome," says Wang. "It canalso sense some of the blank spots that other technologies can’t, likebattery-powered devices."

The team plans to continuedevelopment of the Magnifiense, with the aim of expanding the variety ofdevices it can detect and improve its ability to distinguish between multipledevices in close proximity. Additionally, they plan to miniaturizethe technology so that it could be embedded within a smartwatch or wristband –this could be relatively simple, with the team believing that a small improvementin the update rate of magnetic sensors already found in such devices could enableMagnifiSense functionality with nothing more than a software update.

The team will present their studythis week at the 2015 ACM International Joint Conference on Pervasive andUbiquitous Computing (UbiComp 2015).

Source: University of Washington

0 comments
There are no comments. Be the first!
Thanks for reading our articles. Please consider subscribing to New Atlas Plus.
By doing so you will be supporting independent journalism, plus you will get the benefits of a faster, ad-free experience.