Machine learning and wireless: new teacher at Duke targets emerging technologies

0


[ad_1]

DURHAM – Christ Richmond will join faculty in the Department of Electrical and Computer Engineering at Duke University effective January 1, 2022. With decades of experience designing and testing new technologies and algorithms to improve wireless applications such as radar and communications, Richmond will join longtime colleagues at Duke in applying emerging techniques such as machine learning in the field.

After earning undergraduate degrees in electrical engineering at the University of Maryland at College Park and mathematics at Bowie State University, Richmond completed masters and doctoral programs at the Massachusetts Institute of Technology. For more than two decades, Richmond worked as a senior staff member in the Advanced Sensor Techniques group at MIT Lincoln Laboratory before joining the Arizona State University faculty in 2017.

Through all of his work, Richmond has pushed the boundaries of what modern technology can do with electromagnetic and acoustic waves. While most people are more familiar with the spectrum of electromagnetic waves that we can see (visible light), other frequencies are used for a variety of purposes such as radio, radar, WiFi, Bluetooth, satellite communications, cell phones, 5G devices, etc. . If that sounds like a crowded space to play, that’s because it is.

“Think of the electromagnetic spectrum as a parking lot and each of those frequency bands as parking spaces,” said Richmond. “Just like real estate, some spots are more attractive than others, and everyone wants the right ones.

The agency that decides who gets which spaces is the Federal Communications Commission, or FCC. According to Richmond, the FCC has historically reserved the best locations for the military and civilian organizations with important purposes, such as atmospheric observation. But a few decades ago, a large chunk of those precious frequencies were sold to private companies on the promise that researchers would be able to figure out how to do more with less electromagnetic real estate.

Fast forward to today, and Richmond is one of the researchers still building these bridges. With colleagues Robert calderbank, Charles S. Sydnor Distinguished Professor of Computer Science and Director of the Information Initiative at Duke, and Vahid Tarokh, Rhodes Family Professor of Electrical and Computer Engineering, Richmond is working on a proposal that would allow spectrum users to share the same frequency band, or perhaps even coexist simultaneously within the same band (or in the parlance of cars and parking spaces, these cars will share parking spaces, or maybe even park on top of each other).

“We have to find a way to make all of these signals dance together in a coordinated fashion without stepping on each other,” said Richmond. “It requires the radar to communicate with satellite signals through computers and algorithms. But if we can get them to work together as an extension of each other, maybe we can make the two work better as a team than as individuals.

Richmond’s other main line of research, which is also a collaboration with Calderbank and Tarokh, is to apply evolving machine learning techniques to wireless communications. The trio already have a good start. In October 2020, the team won a five-year, $ 5 million grant from the Air Force to develop AI-based communication and networking protocols fast and reliable enough to meet the demands of the Air Force. ‘Air Force.

To help explain their efforts in this area, Richmond says to consider that all of today’s wireless communication algorithms are based on a model of wave behavior. As long as the signal is strong and the assumed pattern is valid, the technology can decrypt the incoming data. But when the incoming waves no longer look like expected due to interference or degradation in time and space, the model breaks down and the signal is lost.

“We are moving away from developing model-based algorithms and basing them on AI instead,” said Richmond. “These types of approaches are based on data rather than a model. As long as you train it with enough data from a wide range of less than ideal scenarios, it can adapt to changes in the environment. The potential is truly incredible.

With strong associates at Duke and a multi-million dollar center already in the works, the question might have been when Richmond joined faculty rather than if. Either way, Richmond says he’s excited about the opportunities the move will create for him across a wide variety of subjects.

“I have stayed in touch with a lot of people now at Duke for a long time. They kept telling me I should be thinking about coming here too, and once I looked at what was going on it was very appealing in a lot of ways, ”said Richmond. “I’ve been told the students are very good, so I’m excited about that. There are also a lot of fantastic young professors and I’m also interested in a bunch of projects going on in medical school. I think the longer I stay here, the more opportunities I will find for new collaborations.

(C) Duke University

[ad_2]

Share.

About Author

Comments are closed.