The number of smart devices is expected to reach billions in the coming decade. Our mission is to make these intelligent, networked devices more pervasive and interactive. Our research focuses on ambient data acquisition, analysis, and presentation to enhance human-centric intelligent systems..

[Pervasive Sensing] Seamless and continuous monitoring of physical and behavioral conditions is crucial for human-centric smart applications. We convert everyday objects into sensors, enabling contact-based sensing without disrupting their regular usability.

• Vibration of Everything

• Physical Augmentation for Sensing 

[Adaptive Learning] The complexity of the physical world causes variability in sensing quality and data distributions, leading to potential inaccuracies. We leverage multimodal sensor data with complementary characteristics to develop efficient inference and model transfer schemes tailored to these conditions.

• Multi-Modal Collaborative Learning for Internet of Things (IoT)

• Physics and Data-Driven Spatiotemporal Modeling

[Ubiquitous Interaction] To enable efficient interaction between humans and intelligent systems, we explore new ways to acquire user input, present system output,  and model user preference.

• AR/VR-based IoT System Privacy Visualization

• Unvoiced Speech (with Stony Brook and UMass)

• LLM-Enabled User Preference Modeling

UC Merced is located between Silicon Valley and the beautiful Yosemite National Park
#14 in Mobile Computing and #59 in HCI by CSRankings
#60 in U.S. News College Ranking
Established in 2005 and achieved R1 in 2025

I'm looking for highly motivated PhD students. 

Please contact me via email (span24@ucmerced.edu)

Sponsors

Alumni/Student Spin-off