Demonstration and Validation of Statistical Analysis Techniques for TOI Discrimination Using Advanced EMI Sensor Systems

Abstract

This report details the application of the SIG statistical learning approach to UXO discrimination for Camp Butner, North Carolina. 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. These technologies fall broadly into the four analysis categories: the sensor/target model, feature selection, classification, and active label selection. The non-linear classifier outperformed the linear classifier. Both linear and non-linear classifiers would have left more than 75% of the clutter in the ground. The stopping point for both classifiers left UXO in the ground, however. Two of these anomalies could have been captured earlier by selecting additional features. This study validated the robustness of key SIG technologies for target/sensor models, feature selection, classification, and active learning.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jun 01, 2012
Accession Number
ADA574274

Entities

People

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

Organizations

  • Signal Innovations Group, Inc.

Tags

Communities of Interest

  • Materials and Manufacturing Processes
  • Sensors
  • Weapons Technologies

DTIC Thesaurus Topics

  • Algorithms
  • Classification
  • Cost Models
  • Data Analysis
  • Detection
  • Detectors
  • Dimensionality Reduction
  • Discrimination
  • False Alarms
  • Feature Selection
  • Gaussian Distributions
  • Kernel Functions
  • Machine Learning
  • Munitions
  • North Carolina
  • Supervised Machine Learning
  • Unexploded Ammunition

Readers

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