OCT 31, 2018 3:55 PM PDT

Improving Wireless Communication: Brain-Inspired Machine Learning

WRITTEN BY: Nouran Amin

Seeking reliable and efficient communication is a must and as always been a hot-bed of research. Now, a technique creating the latest buzz involves a combination of multiple-input multiple-output techniques with orthogonal frequency division multiplexing—generating high signal quality.

The technique, from the study titled "Realizing Green Symbol Detection Via Reservoir Computing: An Energy-Efficiency Perspective”, was recognized at the IEEE Transmission, Access, and Optical Systems Technical Committee.

Image via Virginia Tech News

Conducted by researchers at Virginia Technical Institute, the technique utilized brain-inspired machine learning methods for the purpose of increasing the energy efficiency of wireless receivers. More specifically, they are using artificial neural networks influenced by the inner workings of the brains in order to minimize the inefficiency.

"Traditionally, the receiver will conduct channel estimation before detecting the transmitted signals," says Yang (Cindy) Yi, an assistant professor at Bradley Department of Electrical and Computer Engineering. "Using artificial neural networks, we can create a completely new framework by detecting transmitted signals directly at the receiver."

Essentially, it is a combination of techniques that will allow signals, using multiple paths simultaneously, to move from the transmitter to the receiver.

"A combination of techniques and frequency brings many benefits and is the main radio access technology for 4G and 5G networks," explains Lingjia Liu, an associate professor at Bradley Department of Electrical and Computer Engineering. "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.”

Learn more about wireless communication: 

Additionally, the technique requires the minimum interference needed and an advantage over easier paths for avoiding multipath fading: it "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," explains John Matyjas, the technical advisor of AFRL's Computing and Communications Division and an Air Force Research Laboratory Fellow.

Source: Virginia Technical Institute

About the Author
Doctorate (PhD)
Nouran is a scientist, educator, and life-long learner with a passion for making science more communicable. When not busy in the lab isolating blood macrophages, she enjoys writing on various STEM topics.
You May Also Like
Loading Comments...