Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
May 3, 2026MicromachinesOpen Access

A Physics–Data Hybrid Framework Using Uncalibrated Consumer CMOS Vision: Pilot Study on Monocular Automatic TUG Assessment Towards Early Parkinson’s Disease Risk Screening

View Full Paper
Ask AI
Bookmark
Share

Authors

YQYuxiang QiuXSXiaodong SunFYFan Yang

Discussion

Loading...

Member takes

Overview

Pilot study introduces a novel framework for risk screening in early Parkinson's disease, facilitating automated mobility assessment.

Key Points

  • To develop a low-cost, automated framework using uncalibrated cameras for early screening of Parkinson’s disease risk.
  • Introduced a Physics–Data Hybrid framework for processing data from consumer-grade CMOS cameras.
  • Utilized a noise-adaptive fusion strategy to extract spatiotemporal gait parameters without manual calibration.
  • Evaluated the system's performance using a pilot study with 10 subjects to assess screening accuracy.
  • Achieved 98% screening accuracy using extracted metric features.
  • Overall classification accuracy reached 87.32% for Parkinson’s disease risk assessment.
  • Demonstrated the ability to capture subtle motor fluctuations better than conventional systems.

Cite This Study

Qiu et al. (2026) studied this question.

synapsesocial.com/papers/69f6e5f38071d4f1bdfc6932https://doi.org/10.3390/mi17050523
View Full Paper
Ask AI
Bookmark
Share