Zhaoshuo Jiang
San Francisco State University, CA·Engineering
Small changes in how an older adult walks can signal declining health long before anyone notices. A system that tracks walking continuously at home, without cameras or wearable devices, could catch these changes early while protecting privacy.
- Fields
Engineering
Biomedical Engineering
Computer Science
- Topics
structural health monitoring
floor vibration sensing
gait analysis
- Grants
- 1 known grant, through May 2027
What they work on
- Develop a robust data-driven classification model that detects walking events from floor vibration signals recorded by sensors in a home.
- Build a deep learning model that estimates gait parameters, the measurable features of a person's walk, from floor vibration data.
- Create general and personalized walker models that enable real-time, non-intrusive health monitoring of older adults from floor vibrations.
More about the research
This project aims to build the foundations for such a system. It senses the vibrations people create in the floor as they walk and uses artificial intelligence (AI) to interpret them.
Why it matters
Aging adults and their caregivers could benefit from continuous, privacy-preserving in-home monitoring that flags changes in walking early. The grant states such detection could catch health declines sooner, reduce hospital stays and readmissions and improve quality of life for older people living at home.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Closest labs
Najim Dehak
Johns Hopkins University, MD·Engineering
Provide engineering and technology expertise, including mobile digital health tools, robotics and AI, to support translational research on frailty in older adults.
Yan Yan
University of Illinois Chicago, IL·Computer Science
Develop unsupervised learning models for re-identifying and tracking people and vehicles across a network of city cameras, processing video in real time across edge devices and the cloud.
Hamed Tabkhi
University of North Carolina at Charlotte, NC·Computer Science
Develop a semi-supervised transformer model that detects unusual or threatening behavior in real time from surveillance video. Use identity-neutral visual features so that no personally identifiable information is needed.
The school
San Francisco State University: 3 labs on PI Pages, $42M a year on research, 17 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.