Smart Campus
UMBC’s campus as a living testbed for privacy-preserving IoT sensing and data management
Several of the group’s systems are deployed and evaluated on UMBC’s campus, which doubles as a living testbed for research on IoT data management and privacy. This page collects that campus-deployment work; new deployments are added here as they are published.
LOADS — privacy-preserving queue monitoring with LiDAR
LOADS is an end-to-end, single-sensor LiDAR system for queue-occupancy and wait-time estimation. LiDAR measures only distances and angles, so it avoids the identification risk of camera-based monitoring and the carried-device requirement of WiFi or RFID approaches. HDBSCAN clustering separates people from noise in real time, and a SARIMAX model forecasts queue lengths from the history it accumulates.Highlights
- LOADS: queue occupancy and wait-time estimation from a single LiDAR sensor — no cameras, and nothing for people to carry
- Real-time separation of people from sensor noise with HDBSCAN clustering; SARIMAX forecasting of queue lengths from the history it accumulates
- Privacy by design: LiDAR records only distances and angles, so individuals cannot be identified from the data
Team
- Saisricharan Malkireddy
- Sumedh Kane
- Sourimitra Medepalli
- Satvik Racharla
- Bharg Barot
-
Christian BadolatoPhD Student, University of Maryland, Baltimore County
-
Roberto YusAssistant Professor, University of Maryland, Baltimore County
Roberto Yus
Assistant Professor
My research interests include Data Management, Knowledge Representation, the Internet of Things, and Privacy.
