I am a Ph.D. candidate supervised by Prof. Kaishun WU in the Data Science and Analytics (DSA) Thrust at the Hong Kong University of Science and Technology (Guangzhou) (HKUST(GZ)). I recently passed my Ph.D. defense.

Research Overview

My research lies at the intersection of AI, ubiquitous computing, and healthcare. I design sensing systems that transform mobile devices, wireless signals, and wearable platforms into practical tools for health monitoring and human-computer interaction.

I am especially interested in building systems that work beyond controlled laboratory settings, where signals are noisy, users are diverse, and sensing pipelines need to be both accurate and deployable.

Current Focus

• AI-driven mobile and wireless sensing
• Contactless and wearable healthcare sensing
• Physiological signal understanding and reconstruction
• Human-centered sensing systems for everyday interaction
• Machine learning for noisy, real-world sensor data

Selected Projects

• Med2ECG: Medical-Guided BCG-to-ECG Reconstruction for Diverse Populations
  Med2ECG reconstructs clinically useful ECG waveforms from passive, contactless BCG signals by aligning latent cardiac event structures. The system is designed for diverse populations across healthy and clinical settings.

• Wandatch: Infrastructure-Free Point-to-Command with Smartwatches and Speakers
  Wandatch enables users to point at and control smart-home appliances using only a smartwatch and existing speakers, without cameras, tags, anchors, or room-specific calibration.

• Sensing Life in Stillness: Unified Dynamic and Static Human Mesh Reconstruction with mmWave Radar
  This work explores mmWave radar-based human mesh reconstruction for both dynamic motion and static human presence, aiming to sense human states even when visible movement is limited.