Researchers are always seeking more reliable and more efficient communications, for everything from televisions and cellphones to satellites and medical devices.
One technique generating buzz for its high signal quality is a combination of multiple-input multiple-output techniques with orthogonal frequency division multiplexing.
Virginia Tech researchers Lingjia Liu and Yang (Cindy) Yi are using brain-inspired machine learning techniques to increase the energy efficiency of wireless receivers.
Their published findings, "Realizing Green Symbol Detection Via Reservoir Computing: An Energy-Efficiency Perspective," received the Best Paper Award from the IEEE Transmission, Access, and Optical Systems Technical Committee.
Liu and Yi, associate and assistant professors respectively in the Bradley Department of Electrical and Computer Engineering, along with Liu's Ph.D. student Rubayet Shafin, are collaborating with researchers from the Information Directorate of the U.S. Air Force Research Laboratory -- Jonathan Ashdown, John Matyjas, Michael Medley, and Bryant Wysocki.
This combination of techniques allows signals to travel from transmitter to receiver using multiple paths at the same time. The technique offers minimal interference and provides an inherent advantage over simpler paths for avoiding multipath fading, which noticeably distorts what you see when watching over-the-air television on a stormy day, for example.
"A combination of techniques and frequency brings many benefits and is the main radio access technology for 4G and 5G networks," said Liu. "However, correctly detecting the signals at the receiver and turning them back into something your device understands can require a lot of computational effort, and therefore energy."
Liu and Yi are using artificial neural networks -- computing systems inspired by the inner workings of the brains -- to minimize the inefficiency. "Traditionally, the receiver will conduct channel estimation before detecting the transmitted signals," said Yi. "Using artificial neural networks, we can create a completely new framework by detecting transmitted signals directly at the receiver."
This approach "can significantly improve system performance when it is difficult to model the channel, or when it may not be possible to establish a straightforward relation between the input and output," said Matyjas, the technical advisor of AFRL's Computing and Communications Division and an Air Force Research Laboratory Fellow.
The team has suggested a method to train the artificial neural network to operate more efficiently on a transmitter-receiver pair using a framework called reservoir computing--specifically a special architecture called echo state network (ESN). An ESN is a kind of recurrent neural network that combines high performance with low energy.
"This strategy allows us to create a model describing how a specific signal propagates from a transmitter to a receiver, making it possible to establish a straightforward relationship between the input and the output of the system," said Wysocki, the chief engineer of the Air Force Research Laboratory Information Directorate.
Testing the efficiency
Liu, Yi, and their AFRL collaborators compared their findings with results from more established training approaches -- and found that their results were more efficient, especially on the receiver side.
"Simulation and numerical results showed that the ESN can provide significantly better performance in terms of computational complexity and training convergence," said Liu. "Compared to other methods, this can be considered a 'green' option."
Lindsey Haugh | EurekAlert!
Marine Skin dives deeper for better monitoring
23.04.2019 | King Abdullah University of Science & Technology (KAUST)
CubeSats prove their worth for scientific missions
17.04.2019 | American Physical Society
The human eye is particularly sensitive to green, but less sensitive to blue and red. Chemists led by Hubert Huppertz at the University of Innsbruck have now developed a new red phosphor whose light is well perceived by the eye. This increases the light yield of white LEDs by around one sixth, which can significantly improve the energy efficiency of lighting systems.
Light emitting diodes or LEDs are only able to produce light of a certain colour. However, white light can be created using different colour mixing processes.
Researchers led by Francesca Ferlaino from the University of Innsbruck and the Austrian Academy of Sciences report in Physical Review X on the observation of supersolid behavior in dipolar quantum gases of erbium and dysprosium. In the dysprosium gas these properties are unprecedentedly long-lived. This sets the stage for future investigations into the nature of this exotic phase of matter.
Supersolidity is a paradoxical state where the matter is both crystallized and superfluid. Predicted 50 years ago, such a counter-intuitive phase, featuring...
A stellar flare 10 times more powerful than anything seen on our sun has burst from an ultracool star almost the same size as Jupiter
A localization phenomenon boosts the accuracy of solving quantum many-body problems with quantum computers which are otherwise challenging for conventional computers. This brings such digital quantum simulation within reach on quantum devices available today.
Quantum computers promise to solve certain computational problems exponentially faster than any classical machine. “A particularly promising application is the...
The technology could revolutionize how information travels through data centers and artificial intelligence networks
Engineers at the University of California, Berkeley have built a new photonic switch that can control the direction of light passing through optical fibers...
17.04.2019 | Event News
15.04.2019 | Event News
09.04.2019 | Event News
24.04.2019 | Life Sciences
24.04.2019 | Life Sciences
24.04.2019 | Life Sciences