Join us for the next instalment of the National Edge AI Hub’s webinar series, featuring Shuokang Huang, who will present his latest research in his talk “Edge Computing for RF-based Human Sensing.” His talk will explore how edge computing and machine learning can enhance device-free RF sensing in IoT systems by extracting meaningful features from complex, interference-prone signals to improve detection accuracy and efficiency.
Shuokang Huang will delve into the technical foundations, practical implementations, and emerging use cases that are shaping the future of human-centric edge AI systems.
Whether you’re a researcher, engineer, or innovator in AI, IoT, or cyber-physical systems, this webinar offers valuable insights into one of the most exciting intersections of edge computing and human sensing.
When: October 23rd, 2025 at 2 PM BST
Where: Zoom, link will be provided to all who register.
Abstract: In the Internet of Things (IoT), Radio Frequency (RF) sensing plays a crucial role by detecting objects/events with RF signals. One of the latest RF sensing approaches is device-free RF sensing which utilizes signals from existing edge devices (e.g., WiFi routers, mobile phones, smart watches). These edge devices were initially designed for wireless communication but not for sensing, so device-free RF sensing may fail to achieve satisfactory detection accuracy due to radio frequency interference (RFI). To improve the accuracy of device-free RF sensing, machine learning (ML) is a promising solution because ML can find approximately optimal solutions to the complex objectives of RF sensing, whose factors (e.g., frequency, signal-to-noise ratio) are too complicated to express with explicit mathematical formulations. To this end, we investigate edge computing to learn from the vast amounts of RF data (e.g., RF signals, channel states) and thereby extract informative features from overlapping signals, balancing sensing performance and communication overhead. Overall, our investigation not only poses new challenges for existing studies but also opens up new opportunities for future work.
About the Speaker: Shuokang Huang is a Ph.D. student supervised by Prof. Julie A. McCann in AESE Group, Department of Computing, Imperial College London. His research focuses on human sensing with WiFi channel state information (CSI), device-free radio frequency (RF) sensing, and applied machine learning on RF sensing. His previous experiences involve semi-supervised adversarial learning, federated learning, etc. In 2021, he received his M.Sc. degree in Computer Applied Technology from Peking University. In 2018, he obtained his B.Eng. degree in Electronic Information Science and Technology from Sun Yat-sen University.