Using functional data analysis-aided learning methods to improve wireless measurements
Wireless Engineering
By Joe McAdory
Shiwen Mao, director of the Wireless Research and Education Center, is principal investigator on a $400,000 National Science Foundation grant “Functional data analysis-aided learning Methods for robust wireless measurements.”
Along with co-PI Guanqun (Vivian) Cao, associate professor in the Department of Mathematics and Statistics, and Dr. Xuyu Wang with Florida International University, Mao aims to develop a deep learning-based approach to address fundamental regression problems in functional data; a better understanding of functional data regression and classification under the distribution between test data and training data for effective wireless measurements in dynamic environments; a deep learning-based approach to address the fundamental bottleneck of quantile regression-based methods; and wireless measurement applications for integration and validation.
This was just one of three NSF-funded grants that Mao, the Earle C. Williams Scholar, was awarded in summer of 2023, combining for $2.2 million.
“NSF programs are known to be very competitive,” said Mao. “One effective approach to get funded is simply to submit more proposals. If you do not submit any, the chance of funding will be zero. Another approach I tried is exploring a variety of programs. Don’t keep focusing on just the core program of your field. My area of expertise is wireless engineering, but I also submitted to education, outreach and diversity programs.
“Lastly, quality of research is very important. One way to improve your quality of research is to collaborate with colleagues across colleges and universities, who often share a variety of viewpoints and bring in complementary expertise that help broaden the scope and strengthen the depth of the proposal.”
Researchers