Zhiyuan Wang is currently a third-year PhD candidate in Systems and Information Engineering at the University of Virginia, working with Prof. Laura Barnes. He obtained his Bachelor's degree in Computer Science from Xiamen University in 2021. His research lies at the intersection of mobile sensing, AI, and health. In collaboration with interdisciplinary collaborators and stakeholders from medicine, nursing, psychology, and bioethics, he strives to develop innovative and adaptive ubiquitous health sensing and intervention systems to enhance human well-being. He have published in venues such as ACM IMWUT, CSCW, IEEE IoTJ, TMC, and SPJ Health Data Science, interned at industry companies including Johnson & Johnson and Baidu Research, and been awarded departmental and UVA Engineering Teaching fellowships.
In the modern era, smart devices, such as smartphones and wearables are ubiquitous and transforming how we think about healthcare moving from a one-size-fits-all model to more personalized interventions. These devices provide a lens into human behavior and a scalable, accessible vehicle to intervene to influence and promote positive behaviors. Although there has been research in mobile health (mHealth) related to modeling and understanding health states in context, there has been little to no advancement in leveraging this information to personalize and adapt interventions. In my research, I aim to pioneer in the design of an ecosystem to realize context-aware just-in-time adaptive interventions (JITAIs) providing context-sensitive, personalized support to individuals when and where they need it most. My work is applied in two use cases- 1) Personalized interventions for individuals elevated in social anxiety and 2) A wearable sensing system to provide real-time feedback for promoting compassionate communication between clinical care providers and patients. Consequently, my research aims to answer questions into how we can leverage mobile devices to sense context such as social threat and momentary states like anxiety or to detect when a provider is using excessive jargon regardless of patient’s cognitive burden. My subsequent work is identifying how these contexts can be leveraged to tailor interventions and improve health outcomes.