Dense Urban Environment Dosimetry for Actionable Information and Recording Exposure (DUE DARE)

Abstract

In dense urban environments there is currently a lack of accurate actionable information on atmospheric composition (gaseous and particulate) on fine spatial and temporal scales. By simultaneously measuring both the environmental state and the human biometric response we propose a holistic sensing environment and methodology for providing accurate actionable information. A state of the art sensor network involving fixed and mobile sensors using machine learning calibration and uncertainty estimation. Comprehensive wearable biometric sensors are used to characterize the real-time human response to the composition of the air, making the human response an integral part of the sensor network. The holistic sensor network incorporates embedded real time machine learning to increase functionality in providing actionable insights for active human participants.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Oct 01, 2021
Accession Number
AD1155393

Entities

People

  • David J. Lary

Organizations

  • University of Texas at Dallas

Tags

Communities of Interest

  • Autonomy
  • Sensors

DTIC Thesaurus Topics

  • Air Pollution
  • Aircrafts
  • Artificial Intelligence Software
  • Artificial Satellites
  • Bayesian Networks
  • Chemistry
  • Climate Change
  • Computer Vision
  • Data Curation
  • Data Mining
  • Dimensionality Reduction
  • Health Services
  • Information Processing
  • Information Science
  • Machine Learning
  • Measurement
  • Medical Personnel
  • Neural Networks
  • Scattering
  • Supervised Machine Learning
  • Unmanned Aerial Vehicles
  • Urban Areas

Readers

  • Sensor Fusion and Tracking Systems.
  • Team-Based Human-Centered Cognitive Task Decision Making and Information Performance.

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - DoD AI Strategy
  • AI & ML - Neural Networks