UXO Discrimination Study Pole Mountain Target and Maneuver Area, WY

Abstract

This report details the application of the SIG statistical learning approach to UXO discrimination at Pole Mountain Target and Maneuver Area, Wyoming. This technology has been developed and validated under previous SERDP/ESTCP efforts by SIG and Duke University. Specific core technologies were used in this discrimination. One important subset of the classification technology tested in this demonstration was multi-task learning (MTL); where information from previous sites is incorporated into the current classification. The multi-task classifier outperformed the single-task classifier. All performance objectives were achieved. All of the UXO were classified as targets. The number of false alarms was fewer than 30% of the total. An additional approach was tested, a generative model, that reduced the number of false alarms to 32. This represents about 2% of the total false alarms.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Feb 01, 2012
Accession Number
ADA571969

Entities

People

  • Larry Carin
  • Levi Kennedy
  • Todd Jobe
  • Xianyang Zhu

Organizations

  • Signal Innovations Group, Inc.

Tags

Communities of Interest

  • Human Systems
  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Artificial Intelligence Software
  • Classification
  • Cost Models
  • Data Analysis
  • Demonstrations
  • Detectors
  • Discrimination
  • False Alarms
  • Feature Selection
  • Gaussian Distributions
  • Generative Models
  • Information Science
  • Machine Learning
  • Probability
  • Supervised Machine Learning
  • Unexploded Ammunition
  • Warning Systems

Readers

  • Military/Explosive Ordnance Disposal (EOD) Technology
  • Neural Network Machine Learning.

Technology Areas

  • AI & ML