Challenges in Bringing AI to Next Generation Edge Networks: A Physical Layer Perspective (Oct 10th)

Date: Oct 10, 2:15 – 3:05 pm

Abstract:The next generation of edge networks encompassing everything from IoT devices and smartphones to autonomous vehicles is poised to revolutionize industries by deploying AI in dynamic, real-world environments. However, these ambitions are constrained by fundamental physical-layer challenges, including network congestion, hardware imperfections, and the high cost of ensuring system reliability. This talk addresses these critical barriers by showcasing three innovative solutions that operate at the physical layer to unlock the full potential of edge intelligence. First, this talk introduces 0Cal, a zero-cost calibration system that eliminates the need for expensive laboratory equipment in millimeter-wave (mmWave) networks by leveraging real-world communication instances to correct antenna array distortions.
Second, this talk presents O-JRC (Computer Networks 2025), an open-source software platform for MIMO-OFDM mmWave Joint Radar-Communication that decouples control logic from signal processing, enabling the seamless integration and rapid prototyping of AI/ML algorithms. Finally, this talk unveils 2FiA (IEEE S&P 2025), a pioneering two-factor WiFi authentication system that enhances security by sensing a user’s involuntary heartbeat, a biometric that is inherently resistant to spoofing. Together, these systems demonstrate how physical-layer intelligence is driving the evolution of more efficient, scalable, and secure next-generation edge networks.

Biographical Sketch: Xin Liu is an Assistant Professor in the Department of Computer Science at Florida State University (FSU). His research focuses on the intersection of artificial intelligence and wireless networking. Prior to joining FSU, he was a Postdoctoral Scholar at the NSF AI-EDGE Institute at The Ohio State University from 2022 to 2024. He also worked as an Assistant Researcher at the Chinese Academy of Sciences from 2012 to 2016. Dr. Liu earned his Ph.D.
in Computer Engineering in May 2022 from the University of Maryland, Baltimore County. He also holds both a B.S. in Control Science and Engineering and an M.S. in Pattern Recognition and Intelligent System from the Beijing Institute of Technology. His research has resulted in the development of multiple novel systems, and he is committed to contributing to the research community through open-source projects such as O-JRC and 2FiA.

Location and Zoom link: LOV 307 and ZOOM Click Here