Dr. Ruolin Zhou, assistant professor of Electrical and Computer Engineering, received a National Science Foundation award of $199,902 for her research project “ERI: An Adaptive Incremental Deep Learning Architecture for Real-Time Inference of RF Signals in Dynamic Spectrum Sharing Environments.”
/filters:quality(90)/prod01/production-cdn-pxl/media/umassdartmouth/profiles/engineering/Ruolin-ZHOU-39-1-668X700.jpg?text=945+WebP)
Due to the dramatic growth of wireless devices and the high demands of faster speeds and better quality of service (QoS), the electromagnetic spectrum is crowded and seems scarce. Dynamic spectrum sharing in 5G and beyond is able to solve the problem of spectrum scarcity.
Learning surrounding wireless signals is essential to support wireless user coexistence over a shared spectrum. Dr. Ruolin Zhou's project titled “ERI: An Adaptive Incremental Deep Learning Architecture for Real-Time Inference of RF Signals in Dynamic Spectrum Sharing Environments” focuses on developing an adaptive incremental deep learning architecture to efficiently detect, classify, and demodulate radio frequency signals in dynamic spectrum sharing environments in real-time with online learning capabilities.
"Specifically, the adaptive architecture can learn a wide range of wireless communication scenarios starting from a small dataset with limited known signals and then incrementally learn new signals and update the deep learning network in an online manner without interruption to re-train the whole network and a man-in-the-middle to label the signals," Zhou explains.
As a working group member of IEEE Standard P1900.8 (a new standard of machine-learned spectrum awareness under development), Dr. Zhou, based on this research finding, will provide recommendations on criteria for evaluating the performance of machine learning models for spectrum awareness. Both undergraduate and graduate students as well as underrepresented groups in Electrical Engineering and Computer Engineering will be recruited under this project.
Zhou joined UMass Dartmouth as an assistant professor at the College of Engineering in 2018. Her research interests and expertise include software-defined radio, machine learning-assisted intelligent radio, and cyber radio frequency (RF). Her research has been funded by the Office of Naval Research (ONR), Air Force Research Laboratory (AFRL), NAVAIR, and industry such as Lockheed Martin. She has been appointed as a Senior Level Fellow at NUWC Division Newport in the ONR Summer Faculty Research Program in summer 2022.