Alternative Representation of Information for Acoustics (ARIA)

Abstract

Classification of objects based on acoustic or electromagnetic measurements is performed in many remote sensing applications underwater and in-air. Active sonar in sonification induces multiple types of acoustic scattering phenomena including direct reflection as well as structural resonance. It is observed that the choice of representation for the raw measurement affects the shape and strength of discriminatory features and the classification performance that utilize them. Using in-air acoustic measurements collected in a noise-controlled laboratory setting, this work develops a statistical model for discriminatory features and a framework to identify the discriminatory pixels in multiple representations as well as an approach to quantify their discriminatory power in the presence of additive noise of varying levels. This framework is used to compare the relative classification performance bounds under independent pixels assumption as well as conventional feature energy detector.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Oct 28, 2022
Accession Number
AD1183900

Entities

People

  • J. Daniel Park

Organizations

  • Pennsylvania State University

Tags

Communities of Interest

  • Energy and Power Technologies
  • Sensors

DTIC Thesaurus Topics

  • Accuracy
  • Acoustic Measurement
  • Acoustic Phenomena
  • Acoustics
  • Artificial Intelligence Software
  • Automated Target Recognition
  • Computer Vision
  • Detection
  • Detectors
  • Frequency
  • Image Processing
  • Information Theory
  • Machine Learning
  • Neural Networks
  • Random Variables
  • Reliability
  • Remote Sensing
  • Scattering
  • Signal Processing
  • Sonar
  • Synthetic Aperture Radar
  • Target Recognition
  • Two Dimensional

Readers

  • Acoustical Oceanography.
  • Distributed Systems and Data Platform Development
  • Theoretical Analysis.