research showcase
Interactive demonstrations of intelligent wireless sensing, communication, and MIMO systems.
Explore working demonstrations of my research in communication-native sensing and AI-driven MIMO systems.
Featured Demos
BandWeave
An intelligent MIMO channel-estimation system that fuses observations across frequency bands. BandWeave improves channel acquisition by learning complementary propagation information from multiple bands.
Related project · Paper · Code
Wi-BFI
An open-source Wi-Fi sensing platform that extracts beamforming feedback information from commercial devices, enabling protocol-compliant MIMO feedback to support a broad range of integrated sensing and communication applications.
Related project · Paper · Code
BeamSense
Standard-compliant multi-person sensing using beamforming feedback from commercial Wi-Fi devices. BeamSense turns communication-native feedback into robust sensing features without requiring specialized sensing hardware.
Related project · Paper · Code
Research Datasets
Public datasets and reproducible pipelines for communication-native sensing and radio fingerprinting across Wi-Fi and mmWave MIMO systems.
M3-CFR
A bi-static mmWave MIMO CFR dataset collected with the MAGIC platform for fine-grained recognition under domain shifts. It contains 10 micro-gesture classes, 3 subjects, 3 indoor environments, 3,000 labeled gesture instances, and approximately 1.5 million CFR frames.
CSI-BFI-HAR
Paired channel state information and beamforming feedback traces for 20 activities. The collection supports single- and simultaneous multi-subject recognition across multiple indoor environments, device placements, orientations, and LoS/NLoS conditions.
Download dataset · Documentation & extraction tools · IEEE DataPort · Paper
DeepCSIv2
A 60.9 GB collection of over-the-air Wi-Fi traces and reconstructed beamforming feedback matrices for physical-layer identification of client devices. The release includes raw captures, processed V matrices, extraction tools, and the learning pipeline.
BeamID
Complex-valued beamforming feedback measurements for domain-adaptive radio fingerprinting. Organized by client radio and collection location, the dataset supports source-domain training and few-shot adaptation to changing deployment environments.