Abstract: The performance of deep learning (DL) empowered wireless communications, networking, and sensing depends on the availability of sufficient high-quality radio frequency (RF) data, which is more difficult and expensive to collect than other types. To overcome this obstacle, we propose several AIGC approaches to generate synthetic RF data labeled with specified human activities for multiple wireless sensing platforms, such as WiFi, RFID, mmWave radar, including a conditional Recurrent Generative Adversarial Network (R-GAN) approach and diffusion model based approaches. The high quality of the generated RF data is validated by metrics of Structural Similarity Index (SSIM) and Frechet Inception Distance (FID), as well as representative downstream tasks of human activity recognition (HAR), where the model trained with sufficient synthesized data outperforms the model trained by real data.
[]
Bio: Shiwen Mao (S'99-M'04-SM'09-F'19) is a Professor and Earle C. Williams Eminent Scholar, and Director of the Wireless Engineering Research and Education Center at Auburn University. Dr. Mao's research interest includes wireless networks, multimedia communications, and smart grid. He is the editor-in-chief of IEEE Transactions on Cognitive Communications and Networking. He received the IEEE ComSoc MMTC Outstanding Researcher Award in 2023, the 2023 SEC Faculty Achievement Award for Auburn, the IEEE ComSoc TC-CSR Distinguished Technical Achievement Award in 2019, the Auburn University Creative Research & Scholarship Award in 2018, the NSF CAREER Award in 2010, and several service awards from IEEE ComSoc. He is a co-recipient of several best journal and conference paper awards from the IEEE.
Agenda:
11:30AM-12:00PM: Lunch & networking
12:00PM-1:30PM: Talk and Q&A
Room: Auditorium, Bldg: Building Q, 6455 Lusk Blvd, San Diego, California, United States, 92121
This event has passed.
