Cost-Aware Design of a Discrimination Strategy for Unexploded Ordnance Cleanup

Abstract

The objective of this project was to conduct a preliminary investigation into the potential benefit of awareness of the specific performance criterion (100% UXO detection) in each stage of the UXO discrimination processing strategy. This project consisted of several large-scale classification studies to carefully analyze the performance of different classification algorithms and the effects of training data when operating at 100% UXO detection. The various classification algorithms included in this study provide a diverse representation of the different theoretical approaches to pattern classification, and allow for comparison of the effect of different classifier properties on performance at the 100% detection operating point. This study provides evidence that the desire to operate at 100% detection may lead to a preference for certain algorithms in the different stages of the discrimination strategy. Careful consideration and selection of methods used in each stage of discrimination strategy may greatly impact performance at the 100% detection goal.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Feb 25, 2011
Accession Number
ADA575248

Entities

People

  • Jeremiah Remus
  • Kenneth Morton
  • Leslie Collins
  • Stacy Tantum

Organizations

  • Clarkson University

Tags

Communities of Interest

  • Autonomy
  • Human Systems
  • Sensors

DTIC Thesaurus Topics

  • Bayesian Networks
  • Computational Science
  • Data Mining
  • Detection
  • Detectors
  • Information Processing
  • Information Science
  • Information Systems
  • Machine Learning
  • Neural Networks
  • Particle Swarm Optimization
  • Signal Processing
  • Supervised Machine Learning
  • Two Dimensional
  • Unexploded Ammunition
  • United States
  • Uxo Detection

Readers

  • Computer Vision.
  • Military/Explosive Ordnance Disposal (EOD) Technology
  • Systems Analysis and Design