Academic sessions health, risk and data protection
summary
A prototype called MURSI detects corridor falls with live video, running three modes: default automated detection with immediate deletion, assessment via anonymized silhouette video, and emergency with full stream plus front‑camera link; a user study favors silhouette filters and backend usage‑control + information‑flow tracking to block screenshots. A separate evidence review finds maladministration as top cause of health data breaches, cites higher breach costs and vague harm timelines, and proposes purpose‑based taxonomies (quantified, predictive personalization, clinical) to guide governance.
AI-written summary · about
chapters (6)
- 0:00Introduction
- 1:11Privacy-aware fall detection
- 13:23Risk reduction in health data
- 30:10Personal health data taxonomy
- 42:14Q&A
- 1:00:17Summary
related talks
01h 12mModelling Privacy Threats of Medical Data and Health Data Spaces
19mGDPR, AI & use of Video data
32mPrivacy Protection. Privacy by Design: Strengthening Compliance
22mPrivacy Threat Modeling
01h 12mACADEMIC SESSION 1
40mPersonal Threat Models and, Speculatively, Privacy Governance
31mPanel on Privacy
01h 14mSenior Academic Session I
